CN115805810A - Battery failure prediction method, apparatus, device, storage medium, and program product - Google Patents

Abstract

The present application relates to a battery failure prediction method, device, equipment, storage medium and program product. The method includes: acquiring state feature data of a target battery in multiple cycles, performing correlation analysis and processing on the state feature data in multiple cycles to obtain a correlation analysis processing result, and then determining a fault prediction of the target battery according to the correlation analysis processing result The result; wherein, the state feature data in each cycle includes a plurality of different battery feature data. In this method, since the real-time state characteristics in each cycle have multiple different battery characteristic data, it is equivalent to combining multiple different battery characteristic data under multiple cycles of the battery for analysis, so that from multiple dimensions The battery characteristics predict whether there is a fault in the battery, which improves the accuracy of the battery fault prediction result.

Description

Battery failure prediction method, device, device, storage medium and program product

technical field

The present application relates to the field of battery technology, in particular to a battery failure prediction method, device, equipment, storage medium and program product.

Background technique

With the rapid development of the battery industry, batteries are used more and more widely. For example, batteries are used in many new energy vehicles.

However, with the continuous improvement of new energy vehicle sales, battery capacity, and charging technology, more and more batteries have safety problems. It is very important to monitor the battery failure in the vehicle to avoid safety accidents.

However, there is a lack of a method that can accurately predict battery failure in the related art.

Contents of the invention

Based on this, it is necessary to provide a battery failure prediction method, device, equipment, storage medium and program product for the above technical problems, which can accurately predict whether the battery has a failure.

In the first aspect, the present application provides a battery failure prediction method, the method comprising:

Obtaining state characteristic data of the target battery in multiple cycles; wherein, the state characteristic data in each cycle includes a plurality of different battery characteristic data;

Perform correlation analysis and processing on the state feature data in multiple cycles to obtain correlation analysis and processing results;

According to the correlation analysis processing result, the failure prediction result of the target battery is determined.

In the embodiment of the present application, the state feature data of the target battery in multiple cycles are obtained, and the state feature data in multiple cycles are correlated and analyzed to obtain the correlation analysis processing result, and then the target battery is determined according to the correlation analysis processing result. Fault prediction results; wherein, the state feature data in each cycle includes a plurality of different battery feature data. In this embodiment, since the state feature data in multiple cycles of the battery is correlated, analyzed and processed, and the real-time state feature in each cycle has a plurality of different battery feature data, it is equivalent to combining the state feature data of the battery in multiple cycles Multiple different battery feature data are combined for analysis, so that whether the battery has a fault can be predicted from the battery features of multiple dimensions, and the accuracy of the battery fault prediction result is improved.

In one of the embodiments, correlation analysis processing is performed on the state feature data in multiple cycles to obtain correlation analysis processing results, including:

The state characteristic data in multiple cycles are input into the fault prediction model, and the state characteristic data in multiple cycles are correlated and analyzed through the fault prediction model to obtain correlation analysis and processing results.

In the embodiment of the present application, the fault prediction model is used to perform correlation analysis on the state feature data. Since the fault prediction model is pre-built from historical data, when performing battery fault prediction, it is only necessary to call the fault prediction model to collect By analyzing the state characteristic data in multiple cycles, the fault prediction result of the target battery can be obtained, which improves the fault detection efficiency of the target battery; and the fault prediction model is constructed in advance through historical data, and the historical data itself also belongs to the battery itself. Some characteristic data of the battery can accurately reflect the characteristics of the battery. Therefore, predicting the failure of the battery through the failure prediction model also ensures the accuracy of the failure prediction result of the battery.

In one of the embodiments, the fault prediction model is used to perform correlation analysis and processing on the state characteristic data in multiple cycles, and the correlation analysis processing results are obtained, including:

According to the state characteristic data in multiple cycles, obtain the abnormal distribution information of battery characteristics in each cycle, and obtain the abnormal change trend information of battery characteristics in multiple cycles;

Correlation analysis and processing are performed on the abnormal distribution information of battery characteristics in each cycle and the abnormal change trend information of battery characteristics in multiple cycles to obtain the results of correlation analysis and processing.

In the embodiment of the present application, according to the state feature data in multiple cycles, the abnormal distribution information of battery characteristics in each cycle is obtained, and the abnormal change trend information of battery characteristics in multiple cycles is obtained, and the battery in each cycle The feature abnormal distribution information and the battery feature abnormal change trend information during multiple cycles are correlated and analyzed to obtain the correlation analysis and processing results. In this embodiment, through the comprehensive analysis of the abnormal distribution information of the battery characteristics in each cycle of the target battery and the abnormal change trend information of the battery characteristics in multiple cycles, joint analysis is carried out from the information in multiple dimensions to improve the follow-up analysis of the target battery. Accuracy of battery failure prediction.

In one of the embodiments, the fault prediction model includes a classification model and a time series model, and according to the state feature data in multiple cycles, the abnormal distribution information of battery characteristics in each cycle is obtained, and the abnormal changes in battery characteristics in multiple cycles are obtained Trend information, including:

Input multiple different battery characteristic data in the state characteristic data in each cycle into the classification model to obtain abnormal distribution information of battery characteristics in each cycle;

A plurality of different battery characteristic data in the state characteristic data in each cycle are input into the time series model to obtain abnormal change trend information of battery characteristics in multiple cycles.

In the embodiment of the present application, multiple different battery characteristic data in the state characteristic data in each cycle are input into the classification model to obtain the abnormal distribution information of battery characteristics in each cycle, and the state characteristic data in each cycle Multiple different battery characteristic data in the data are input to the time series model to obtain abnormal change trend information of battery characteristics during multiple cycles. In this embodiment, the state feature data in multiple cycles are analyzed through the classification model and the time series model respectively, and the abnormal distribution information of the battery characteristics in each cycle and the abnormal change trend of the battery characteristics in the cycle are obtained. The battery characteristic data in two dimensions during the period ensures the accuracy of the subsequent target battery failure prediction results.

In one of the embodiments, the failure prediction result includes whether there is a failure or no failure in the target battery, and the method further includes:

When the target battery is faulty, obtain at least one abnormal battery cell in the target battery that has the risk of charging high and low;

Obtain the failure risk type of each abnormal cell;

According to the type of failure risk, the degree of failure risk of each abnormal cell is determined.

In the embodiment of the present application, when the target battery is faulty, at least one abnormal battery cell in the target battery that has the risk of charging high and low is obtained, and the failure risk type of each abnormal battery cell is obtained, and then according to the failure risk type, each abnormal battery cell is determined. The degree of failure risk of abnormal cells. In this embodiment, the failure risk type of each abnormal battery cell in the target battery is obtained, and the failure risk degree of each abnormal battery cell is determined based on the failure risk type, which further improves the failure accuracy of the target battery and facilitates subsequent maintenance of the target battery.

In one of the embodiments, the failure risk type includes internal resistance abnormality or capacity abnormality, and the failure risk type of each abnormal battery cell is obtained, including:

For any abnormal cell, divide the state characteristic data of the abnormal cell, and obtain the internal resistance characteristic data and capacity characteristic data of the abnormal cell;

If there is an abnormality in the characteristic data of the internal resistance of the abnormal battery cell, it is determined that the failure risk type of the abnormal battery cell is abnormal internal resistance;

If there is an abnormality in the capacity feature data of the abnormal battery cell, it is determined that the failure risk type of the abnormal battery cell is abnormal capacity.

In the embodiment of the present application, for any abnormal battery cell, the state feature data of the abnormal battery cell is divided, and the internal resistance characteristic data and capacity characteristic data of the abnormal battery cell are obtained. Among the internal resistance characteristic data of the abnormal battery cell If there is an abnormality, determine the failure risk type of the abnormal battery cell as abnormal internal resistance; if there is an abnormality in the capacity characteristic data of the abnormal battery cell, determine the failure risk type of the abnormal battery cell as capacity abnormality. In this embodiment, by dividing the real-time state data of abnormal cells into characteristic data of internal resistance and characteristic data of capacity, the accuracy of identifying whether abnormal cells are abnormal in internal resistance or abnormal in capacity is improved, and the status of abnormal cells is clarified. The fault type is convenient for subsequent maintenance and treatment of abnormal batteries.

In one of the embodiments, according to the type of failure risk, the degree of failure risk of each abnormal cell is determined, including:

For any abnormal battery cell, according to the failure risk type of the abnormal battery cell, determine the target battery characteristic data from the state characteristic data of the abnormal battery cell, and the target battery characteristic data includes at least one battery characteristic data;

According to the target battery characteristic data of the abnormal battery cell, the failure risk degree of the abnormal battery cell is determined.

In the embodiment of the present application, for any abnormal battery cell, according to the failure risk type of the abnormal battery cell, the target battery characteristic data is determined from the state characteristic data of the abnormal battery cell, and then the abnormal battery characteristic data is determined according to the target battery characteristic data of the abnormal battery cell. The failure risk degree of the battery cell; wherein, the target battery characteristic data includes at least one battery characteristic data. In this embodiment, the failure risk degree of the abnormal battery cell is determined according to at least one battery characteristic data selected from the state characteristic data of the abnormal battery cell, and the accuracy of determining the failure risk degree of the abnormal battery cell is improved.

In one of the embodiments, according to the failure risk type of the abnormal battery cell, the target battery characteristic data is determined from the state characteristic data of the abnormal battery cell, including:

When the failure risk type of the abnormal battery cell is abnormal internal resistance, determine the target battery characteristic data of the abnormal battery cell from the internal resistance characteristic data in the state characteristic data of the abnormal battery cell;

If the failure risk type of the abnormal battery cell is abnormal capacity, determine the target battery characteristic data of the abnormal battery cell from the capacity characteristic data in the state characteristic data of the abnormal battery cell.

In the embodiment of this application, when the failure risk type of the abnormal battery cell is abnormal internal resistance, the target battery characteristic data of the abnormal battery cell is determined from the internal resistance characteristic data in the state characteristic data of the abnormal battery cell, and the abnormal battery cell When the failure risk type is abnormal capacity, the target battery characteristic data of the abnormal battery is determined from the capacity characteristic data in the state characteristic data of the abnormal battery. In this embodiment, by using the target battery characteristic data corresponding to the failure risk type of the abnormal battery cell, the accuracy of subsequently determining the failure risk degree of the abnormal battery cell through the target battery characteristic data is improved.

In one of the embodiments, according to the target battery characteristic data of the abnormal battery cell, the failure risk degree of the abnormal battery cell is determined, including:

Obtain the target battery characteristic data of other normal cells in the target battery except abnormal cells;

The target battery characteristic data of the abnormal battery is compared horizontally with the target battery characteristic data of other normal batteries to determine the degree of failure risk of the abnormal battery.

In the embodiment of the present application, the target battery characteristic data of other normal batteries in the target battery are obtained, and the target battery characteristic data of the abnormal battery is compared with the target battery characteristic data of other normal batteries, To determine the degree of failure risk of abnormal cells. In this embodiment, by horizontally comparing the abnormal data with the normal data, the accuracy of determining the degree of failure risk of abnormal cells is ensured.

In one of the embodiments, if the target battery characteristic data is an internal resistance value, horizontally compare the target battery characteristic data of the abnormal battery with the target battery characteristic data of other normal batteries to determine the degree of failure risk of the abnormal battery, include:

Obtain the internal resistance value of the abnormal cell, and obtain the median internal resistance value of the abnormal cell and other normal cells;

Obtain the ratio of the internal resistance value to the median internal resistance value;

According to the ratio and a plurality of preset ranges of different failure risk levels, the failure risk level of the abnormal battery cell is determined.

In the embodiment of the present application, the internal resistance value of the abnormal cell is obtained, and the median internal resistance value of the abnormal cell and other normal cells is obtained, and the ratio of the internal resistance value to the median internal resistance value is obtained. According to the ratio and A plurality of different failure risk level ranges are preset to determine the failure risk level of abnormal batteries. In this method, the internal resistance value of the abnormal cell and the median internal resistance value of other normal cells are considered, and the fault risk degree of the abnormal cell is determined based on the ratio and the preset different fault risk level ranges , which ensures the accuracy of the determined failure risk degree of the abnormal battery cell.

In the second aspect, the present application also provides a battery failure prediction device, which includes:

An acquisition module, configured to acquire state characteristic data of the target battery in multiple cycles; wherein, the state characteristic data in each cycle includes a plurality of different battery characteristic data;

The analysis module is used to perform correlation analysis and processing on the state characteristic data in multiple periods, and obtain correlation analysis processing results;

The determination module is used to determine the failure prediction result of the target battery according to the correlation analysis processing result.

In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method provided in any embodiment of the first aspect above when executing the computer program.

In a fourth aspect, the embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method provided in any embodiment of the above-mentioned first aspect are implemented.

In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method provided in any one of the embodiments of the first aspect above are implemented.

The above description is only an overview of the technical solution of the present application. In order to better understand the technical means of the present application, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and understandable , the following specifically cites the specific implementation manner of the present application.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the application. Also, the same reference numerals are used to denote the same components throughout the drawings. In the attached picture:

Fig. 1 is an application environment diagram of the battery failure prediction method in an embodiment;

FIG. 2 is a schematic flow chart of a battery failure prediction method in an embodiment;

FIG. 3 is a schematic flow chart of a battery failure prediction method in another embodiment;

FIG. 4 is a schematic flow chart of a battery failure prediction method in another embodiment;

FIG. 5 is a schematic flow chart of a battery failure prediction method in another embodiment;

Fig. 6 is a schematic flow chart of a battery failure prediction method in another embodiment;

Fig. 7 is a schematic flow chart of a battery failure prediction method in another embodiment;

Fig. 8 is a schematic flow chart of a battery failure prediction method in another embodiment;

Fig. 9 is a schematic flow chart of a battery failure prediction method in another embodiment;

Fig. 10 is a schematic flow chart of a battery failure prediction method in another embodiment;

Fig. 11 is a schematic flow chart of a battery failure prediction method in another embodiment;

Fig. 12 is a schematic flow chart of a battery failure prediction method in another embodiment;

Fig. 13 is a structural block diagram of a battery failure prediction device in an embodiment;

Figure 14 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

Embodiments of the technical solutions of the present application will be described in detail below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present application more clearly, and therefore are only examples, rather than limiting the protection scope of the present application.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the application; the terms used herein are only for the purpose of describing specific embodiments, and are not intended to To limit this application; the terms "comprising" and "having" and any variations thereof in the specification and claims of this application and the description of the above drawings are intended to cover a non-exclusive inclusion.

In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects, and should not be understood as indicating or implying relative importance or implicitly indicating the number, specificity, or specificity of the indicated technical features. Sequence or primary-secondary relationship. In the description of the embodiments of the present application, "plurality" means two or more, unless otherwise specifically defined. Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two).

In practical applications, the phenomenon of high charge and low charge of the battery will seriously affect the performance of the battery. In the related art, the phenomenon of high charge and low discharge of the battery is monitored, mainly by obtaining the battery data of the battery, and performing data analysis on the battery data to determine whether the battery data is within the safety threshold. When the battery is charged high and low, the battery data exceeds safety threshold.

The applicant found that the above-mentioned comparison of battery data with the safety threshold to monitor whether the battery is overcharged and lowered can be monitored for batteries that have already occurred, and it is impossible to check whether the battery has been overcharged or lowered. phenomena are predicted.

Based on the above considerations, in order to predict the phenomenon of high charging and low charging of the battery, the inventors have conducted in-depth research and proposed a battery fault prediction method. By performing correlation analysis on multiple different battery characteristic data of the battery in multiple cycles, To determine the failure prediction results of the battery.

In such a battery fault prediction method, by analyzing the battery characteristic distribution information in each cycle and the battery characteristic change trend in multiple cycles, and analyzing the battery characteristic distribution information in each cycle and the battery characteristic distribution information in multiple cycles Correlation analysis is carried out on the change trend to determine whether the battery may be charged high or low, which improves the accuracy of battery failure prediction results.

Of course, it should be understood that the technical effects that can be achieved by the battery failure prediction method provided in the embodiment of the present application are not limited to this, and other technical effects can also be achieved, for example, predicting the phenomenon of high charge and low charge of the battery, reducing the Safety risks caused by high charging and low charging of the battery, etc. For specific technical effects that can be achieved in the embodiments of the present application, refer to the following embodiments.

It should be noted that the battery failure prediction scheme provided by this application is applicable to all new energy-related fields, including but not limited to batteries in new energy vehicles, energy storage and quick-change modules, which are not limited in the embodiments of this application.

The batteries disclosed in the embodiments of the present application can be used, but not limited to, in electric devices such as vehicles, ships or aircrafts.

The embodiment of the present application provides an electric device using a battery as a power source. The electric device can be, but not limited to, a mobile phone, a tablet, a notebook computer, an electric toy, an electric tool, a battery car, an electric car, a ship, a spacecraft, and the like. Among them, electric toys may include fixed or mobile electric toys, such as game consoles, electric car toys, electric boat toys, electric airplane toys, etc., and spacecraft may include airplanes, rockets, space shuttles, spaceships, etc.

For the convenience of description, the following embodiments are described with an electric device according to an embodiment of the present application, as shown in FIG. 102 is the power source of the electrical device 100 .

The fault pre-warning of the target battery will be described below with the controller in the electrical device as the execution subject (the controller is not shown in FIG. 1 ).

In one embodiment, as shown in FIG. 2 , a battery failure prediction method is provided, which is described by taking the method applied to the controller of the electric device in FIG. 1 as an example, including the following steps:

S201. Obtain state feature data of a target battery in multiple cycles; wherein, the state feature data in each cycle includes a plurality of different battery feature data.

Wherein, the target battery is a battery that requires fault identification, and the target battery includes at least one battery cell; the state feature data may include the state feature data of the target battery, and may also include the state feature data of the battery cells in the target battery, battery feature data Include multiple.

Therefore, when it is necessary to identify the fault of the target battery, the state characteristic data of the target battery in multiple cycles can be obtained, and the prediction result of the fault of the battery can be judged according to the state characteristic data in multiple cycles.

Wherein, each cycle in the plurality of cycles can be a preset duration, and the preset duration is variable, for example, 1 day, 3 days, 7 days or a charging cycle, a discharging cycle, or a charging and discharging cycle of the entire battery; multiple The cycle can be a continuous cycle; it can be understood that the cycle is preset, and the cycle does not change during the process of obtaining the state characteristic data of multiple cycles, and the multiple cycles include at least two cycles. In this application In the embodiment, the application does not limit the specific number of cycles.

Battery characteristic data include: charging high frequency, low frequency, voltage difference, voltage difference current slope, voltage difference state of charge (State of Charge, SOC) slope, internal resistance value, etc.

Among them, the high charging frequency indicates the frequency of the high charging phenomenon within a preset cycle; the low frequency indicates the frequency of the low phenomenon within a preset cycle; The voltage difference within a cycle; the voltage difference current slope indicates the slope of the curve between the voltage difference value and the current value of the cell in the battery; the voltage difference SOC slope indicates the cell voltage difference and SOC value of the battery within a cycle The slope of the curve between; the internal resistance value represents the internal resistance value of all cells in a cycle of the battery.

Optionally, the voltage difference can be the difference between the maximum voltage of the cell in the battery and the minimum voltage of the cell in one cycle, and the voltage difference can also be the average maximum voltage of the cell in the battery and the average minimum voltage of the cell in one cycle The difference between them; the internal resistance value can be the average value of all cells in a cycle of the battery, or it can be calculated according to the measured current and voltage of each cell, and then based on each The internal resistance of the cell is used to calculate the internal resistance of the battery.

It should be noted that, in the embodiment of the present application, the calculation method of the battery characteristic data is not limited, and may be determined according to actual requirements.

In one embodiment, the sensor can be used to obtain the initial characteristic data of each cell in the target battery in multiple cycles, and then based on the initial characteristic data of each cell, the state characteristics of the target battery in multiple cycles can be determined based on the above calculation method Data; the state characteristic data of the target battery in multiple cycles can be directly measured or indirectly calculated.

S202. Perform correlation analysis processing on the state characteristic data in multiple periods to obtain correlation analysis processing results.

The charging and discharging phenomenon of the battery cannot be directly determined by the variable test value, but can only be characterized by the associated phenomenon. It can be judged comprehensively by using multiple associated features through the state characteristic data in multiple cycles; the judgment method can be comprehensive and different. The change trend of the state characteristic data during the period is judged whether there is an amplification trend.

Therefore, after obtaining the state feature data of the target battery in multiple cycles, the state feature data in multiple cycles can be processed by means of correlation analysis to obtain a correlation analysis processing result.

Among them, association analysis can discover the correlation or correlation between data in a large number of data sets; therefore, through correlation analysis, it can find the correlation or correlation in the state characteristic data in multiple cycles, so as to obtain more accurate analysis results.

In one embodiment, the association analysis processing is performed on the state characteristic data in multiple periods through the preset association rules, and the association analysis processing results are obtained, wherein the association rules may be the association relationship between the state characteristic data, for example , there is an association between the A feature data and the B feature data, then the B feature data can be predicted by the value of the A data feature. Therefore, the state feature data in multiple cycles can be analyzed according to the preset association rules. Analyzing whether the state characteristic data in multiple cycles conforms to the preset association rule to obtain the association analysis processing result; the A characteristic data includes at least one characteristic, and the B characteristic data includes at least one characteristic.

For example, if the state feature data includes pressure difference and internal resistance value, therefore, correlation analysis and processing can be performed on the pressure difference and internal resistance value in multiple cycles to determine the correlation analysis processing result; specifically, the pressure difference and internal resistance value of the target battery Correspondingly, if the pressure difference is within the range of A, the internal resistance value should be within the range of B. Correlation analysis and processing is carried out for the pressure difference and internal resistance value. When the pressure difference of the target battery is not within the range of A, and the internal resistance value is not within the B range, it is determined that there is an abnormality in the target battery, and according to the pressure difference and internal resistance value of the target battery, and the deviation value in the corresponding preset range, determine the correlation analysis processing result of the target battery, correlation analysis processing The result can be a numeric value.

S203. Determine the failure prediction result of the target battery according to the correlation analysis processing result.

The failure prediction result of the target battery can be whether the target battery will be overcharged or undercharged, and if the target battery has overcharged or undercharged phenomenon, it will cause the target battery to fail.

The result of the above correlation analysis processing can be a data feature value after comprehensive processing of the state feature data in multiple cycles, the data feature value can be a value in the range of 0 to 1, and the distribution of the data feature value in the range of 0 to 1 The closer the data characteristic value is to 0, the smaller the fault is, and the closer the data characteristic value is to 1, the more serious the fault is; for example, if the data characteristic value is 0, it can indicate that the target battery is not High charge and low charge will occur. If the characteristic value of this data is 1, it means that the target battery will fail, and the risk of failure is serious.

Optionally, it is also possible to compare the data feature value with a preset feature threshold, and determine the failure prediction result of the target battery according to the comparison result; specifically, if the feature data value is greater than the preset feature threshold, then determine the target battery The battery has failed; otherwise, the target battery has not failed.

In the above battery failure prediction method, the state characteristic data of the target battery in multiple cycles are obtained, and the state characteristic data in multiple cycles are correlated and analyzed to obtain the correlation analysis processing result, and then the target battery is determined according to the correlation analysis processing result. The fault prediction results of ; wherein, the state feature data in each cycle includes a plurality of different battery feature data. In this embodiment, since the state feature data in multiple cycles of the battery is correlated, analyzed and processed, and the real-time state feature in each cycle has a plurality of different battery feature data, it is equivalent to combining the state feature data of the battery in multiple cycles Multiple different battery feature data are combined for analysis, so that whether the battery has a fault can be predicted from the battery features of multiple dimensions, and the accuracy of the battery fault prediction result is improved.

In one embodiment, performing correlation analysis processing on the state feature data in multiple cycles to obtain the correlation analysis processing results includes: inputting the state feature data in multiple cycles into the fault prediction model, and using the fault prediction model to The state characteristic data within a cycle is correlated with analysis and processing, and the results of correlation analysis and processing are obtained.

The way of performing correlation analysis and processing on the state feature data in multiple cycles can be through the neural network model, specifically, input the state feature data of the battery in multiple cycles into the fault prediction model, and use the fault prediction model to The state characteristic data in multiple cycles are analyzed to obtain the correlation analysis processing results.

Optionally, the fault prediction model is pre-built from historical data, and the construction process of the fault prediction model can be as follows: Obtain the historical state characteristic data of the sample battery in multiple cycles, and then use the historical state characteristic data to carry out the initial fault prediction model Training until the initial fault prediction model satisfies the preset convergence condition, then the fault prediction model is obtained.

It should be noted that, in the embodiment of the present application, there is no limitation on the network architecture adopted when constructing the fault prediction model.

In the following, an embodiment is used to describe how to perform correlation analysis processing on the state feature data in multiple cycles through the fault prediction model. In one embodiment, as shown in Figure 3, the fault prediction model is used to analyze the The characteristic data is subjected to correlation analysis processing, and the correlation analysis processing result is obtained, including the following steps:

S301. According to the state feature data in multiple cycles, acquire abnormal battery feature distribution information in each cycle, and acquire battery feature abnormal change trend information in multiple cycles.

Analyze the state characteristic data in each cycle to determine the abnormal distribution information of battery characteristics in each cycle. The abnormal distribution information of battery characteristics indicates the abnormality of the battery characteristic data of the target battery in this cycle, which may include abnormal battery characteristics data, the cell identification corresponding to abnormal battery characteristic data, etc.

Analyze the state feature data in multiple cycles to determine the battery feature abnormal change trend information of the battery feature data between cycles. The battery feature abnormal change trend information indicates the abnormal change of the battery feature data between cycles, which may include: During multiple cycles, the change trend of a certain battery characteristic data is abnormal, and there is a sudden change.

The way to obtain the abnormal distribution information of battery characteristics in each cycle can be to analyze multiple battery characteristic data in a cycle for any cycle, and take the battery characteristic data including charging high frequency and low frequency as an example to judge respectively Whether the charging frequency and lowering frequency of the target battery in this cycle meet the safe frequency, and determine the abnormal distribution of battery characteristics of the charging higher frequency and lowering frequency in this cycle.

The way to obtain the abnormal change trend information of the battery characteristics during multiple cycles may be to take the battery characteristic data of the target battery including the charging frequency and the lowering frequency as an example, and judge the charging frequency and the lowering frequency of the target battery respectively during the cycle. Abnormal change trend, to determine whether there is a sudden change in the charging frequency and lowering frequency, so as to determine the abnormal change trend information of battery characteristics during multiple cycles.

S302. Perform correlation analysis processing on the battery characteristic abnormality distribution information in each cycle and the battery characteristic abnormality change trend information in multiple cycles to obtain a correlation analysis processing result.

Correlation analysis is performed on the above-mentioned abnormal distribution information of battery characteristics in each cycle and the abnormal change trend information of battery characteristics in multiple cycles to obtain a correlation analysis processing result.

For example, taking the high-charging frequency as an example, for example, if there is abnormal distribution information of the high-charging frequency, but there is no abnormal change trend in the high-charging frequency in multiple cycles, the abnormal distribution information of the high-charging frequency can be analyzed to determine the charging frequency. For the high-frequency association analysis processing result, for example, if the abnormal distribution information of the high-fill frequency is not obvious, it can be determined that the high-fill frequency correlation analysis processing result is normal.

If there is abnormal distribution information of the high charging frequency, but there is no abnormal change trend of the high charging frequency in multiple cycles, but the abnormal distribution information of the high charging frequency is obvious, then it can be determined that the correlation analysis and processing result of the high charging frequency is abnormal.

If the battery characteristic data includes the charging high frequency and the low frequency, the correlation analysis processing results of the high charging frequency and the low frequency correlation analysis processing results can be comprehensively analyzed to obtain the final correlation analysis processing result.

In one embodiment, the battery characteristic abnormal distribution information in each cycle of the target battery corresponds to a data distribution abnormal value, and the battery characteristic abnormal change trend during multiple cycles corresponds to a data change abnormal value, and the data distribution abnormal value and data Perform a comprehensive analysis of the abnormal value of the change to determine the correlation analysis result of the target battery; Determined as the result of correlation analysis processing, etc.

In the above battery fault prediction method, according to the state feature data in multiple cycles, the abnormal distribution information of battery characteristics in each cycle is obtained, and the abnormal change trend information of battery characteristics in multiple cycles is obtained, and the The abnormal distribution information of the battery characteristics and the abnormal change trend information of the battery characteristics in multiple cycles are correlated and analyzed to obtain the correlation analysis and processing results. In this method, through the comprehensive analysis of the abnormal distribution information of battery characteristics in each cycle of the target battery and the abnormal change trend information of battery characteristics in multiple cycles, the joint analysis of information from multiple dimensions is carried out to improve the subsequent evaluation of the target battery. Accuracy of failure prediction.

If the above fault prediction model includes a classification model and a time series model, in one embodiment, as shown in Figure 4, according to the state feature data in multiple cycles, the abnormal distribution information of the battery characteristics in each cycle is obtained, and multiple The abnormal change trend information of the battery characteristics during the period includes the following steps:

S401. Input a plurality of different battery characteristic data in the state characteristic data in each cycle into the classification model to obtain abnormal distribution information of battery characteristics in each cycle.

A classification model is used to classify a plurality of different battery characteristic data in the state characteristic data in each cycle, and determine the abnormal distribution information of the battery characteristics in the plurality of battery characteristic data in each cycle, and the abnormal distribution information of the battery characteristics can include each Abnormal battery characteristic data and corresponding cell identification in the cycle.

The way to determine the abnormal distribution information of battery characteristics in each cycle through the classification model can be to input multiple different battery characteristic data in the state characteristic data in multiple cycles into the classification model at the same time to obtain the battery characteristics in each cycle. Feature anomaly distribution information.

Optionally, a plurality of different battery feature data among the state feature data in each cycle may be input into the classification model to obtain abnormal distribution information of battery features in each cycle.

The construction process of the classification model can be to obtain the historical state characteristic data of the sample battery in multiple cycles, and then train the initial classification model through the historical state characteristic data until the initial classification model satisfies the preset convergence condition, then the classification model is obtained .

S402. Input a plurality of different battery characteristic data in the state characteristic data in each cycle into the time series model, and obtain abnormal change trend information of the battery characteristics in a plurality of cycles.

The time series model is a model that uses time as an independent variable to study the trend of the corresponding data itself. The time series can be used to analyze the battery characteristic data in multiple consecutive cycles to obtain a time series model; the state in multiple cycles can be analyzed through the time series model. The characteristic data is analyzed to determine the abnormal change trend information of the battery characteristics during multiple cycles. The abnormal change trend information of the battery characteristics may include the battery characteristic data with abnormal change trends during multiple cycles and the corresponding cell identification.

The method of determining the abnormal change trend information of battery characteristics in multiple cycles through the time series model may be to input multiple different battery characteristic data in the state feature data in multiple cycles into the time series model at the same time, through the time series model Analyze and obtain the abnormal change trend information of battery characteristics during multiple cycles.

Optionally, it is also possible to respectively input different battery characteristic data during multiple periods into the time series model, and respectively obtain battery characteristic data with an abnormal variation trend during the period.

The construction process of the timing model can be to obtain the historical state characteristic data of the sample battery in multiple cycles, and then train the initial timing model through the historical state characteristic data until the initial timing model satisfies the preset convergence condition, then the timing model is obtained .

In the above battery failure prediction method, a plurality of different battery characteristic data in the state characteristic data in each period are input into the classification model to obtain the abnormal distribution information of the battery characteristics in each period, and the state characteristic data in each period Multiple different battery characteristic data in the characteristic data are input into the time series model to obtain abnormal change trend information of battery characteristics during multiple cycles. In this method, the state characteristic data in multiple cycles are analyzed through the classification model and the time series model respectively, and the abnormal distribution information of the battery characteristics in each cycle and the abnormal change trend of the battery characteristics in the cycle are obtained. The two-dimensional battery feature data ensures the accuracy of the subsequent target battery failure prediction results.

If the fault prediction result includes that the target battery has a fault or does not have a fault, then in one embodiment, as shown in Figure 5, this embodiment includes the following steps:

S501. If the target battery is faulty, acquire at least one abnormal battery cell in the target battery that has a risk of being overcharged or lowered.

The prediction result includes whether there is a fault in the target battery or there is no fault. If the fault prediction result is that the target battery is faulty, the corresponding fault prediction result may also include the identification of the battery cells in the target battery that have high charge and low discharge phenomena. The battery cell identification corresponds to the abnormal battery cell; therefore, the identification of the battery cell in the target battery that has the risk of charging high and low can be obtained directly from the fault prediction result; the abnormal battery includes at least one.

Optionally, the method of obtaining at least one abnormal battery cell in the target battery that has the risk of charging high and discharging low can also be to first obtain the characteristic data of each battery cell in the target battery in multiple cycles, and then determine according to the characteristic data Abnormal battery.

For example, if the characteristic data include voltage difference, voltage difference current slope and internal resistance, you can compare the voltage difference, voltage difference current slope and internal resistance of each battery cell with the preset safety conditions. For any battery cell, if the battery When there is any characteristic data of pressure difference, voltage difference current slope and internal resistance in the cell that does not meet the preset safety conditions, it is determined that the cell is an abnormal cell.

Wherein, the safety condition may be that the value corresponding to the corresponding feature data is less than a preset safety threshold, or greater than a preset safety threshold, or within a preset safety range.

It should be noted that in this application, a fault in the target battery means that the target battery is overcharged or lowered, and an abnormal cell means that there is a risk of overcharging or lowering.

S502. Obtain the failure risk type of each abnormal battery cell.

The failure risk corresponding to abnormal cells is failure risk, and the types of failures include abnormal internal resistance and abnormal capacity.

Therefore, after determining the abnormal cell in the target battery, the fault type that causes the abnormal risk of the cell can be further determined.

In one embodiment, as shown in FIG. 6 , the failure risk type includes abnormal internal resistance or abnormal capacity, and obtaining the failure risk type of each abnormal cell includes the following steps:

S601. For any abnormal battery cell, divide the state characteristic data of the abnormal battery cell, and obtain the internal resistance characteristic data and capacity characteristic data of the abnormal battery cell.

S602. If there is an abnormality in the characteristic data of the internal resistance of the abnormal battery cell, determine that the failure risk type of the abnormal battery cell is abnormal internal resistance.

S603. If there is an abnormality in the capacity feature data of the abnormal battery cell, determine that the failure risk type of the abnormal battery cell is abnormal capacity.

Before determining the failure risk type of each abnormal battery cell, firstly, obtain the state characteristic data of each abnormal battery cell, and then divide the state characteristic data according to the failure risk type to obtain the internal resistance characteristic data and capacity characteristic data, among which, the internal resistance Resistance feature data is the state feature data that can represent the phenomenon of charging up and down due to abnormal internal resistance of the battery cell. Through the internal resistance feature data, it can be determined whether the failure risk type that causes the abnormality of the battery core is abnormal internal resistance; the capacity feature data Indicates the state characteristic data that can characterize the phenomenon of high charge and low discharge caused by abnormal battery capacity. Through the capacity characteristic data, it can be determined whether the failure risk type that causes abnormal battery capacity is abnormal capacity.

In the phenomenon of high charge and low discharge, if there is an abnormal ratio of the median value of the abnormal cell to the normal cell, the absolute value of the voltage difference and current slope of the abnormal cell is amplified (large voltage difference under high current), and the abnormal voltage of the discharge back section is abnormal. If the cell voltage rises rapidly and other characteristics, it is determined that the failure risk type of the abnormal cell is internal resistance abnormality; in the phenomenon of charging high and low, the voltage difference is not directly related to the current. If the abnormal cell is low in SOC, it is the lowest voltage cell. High SOC is the highest voltage cell, and the absolute value of the voltage difference and SOC slope is amplified (the voltage difference is related to SOC), etc., so it is determined that the failure risk type of the abnormal cell is capacity abnormality.

Based on the above description, the characteristic data of internal resistance can include: the maximum voltage cell frequency in the recharging phase, the voltage difference current slope, the internal resistance value, the ratio of the internal resistance of the abnormal cell to other normal cells, and the absolute value of the voltage difference and current slope. value, cell voltage during discharge and recharge phase, etc.

Among them, the maximum voltage cell frequency in the recharging stage indicates the frequency at which the cell is at the maximum voltage during the recharging stage; the ratio of the internal resistance of the abnormal cell to other normal cells can be expressed as the internal resistance of the abnormal cell to that of other normal cells The ratio of the median internal resistance value can also be expressed as the ratio of the internal resistance value of the abnormal cell to the average internal resistance value of other normal cells; the absolute value of the voltage difference and the current slope represents the voltage difference value of the cell The absolute value of the slope of the curve between the current value and the current value, the cell voltage in the discharge and recharge stage indicates the voltage of each cell in the battery during the discharge and recharge stage.

Capacity characteristic data may include: minimum frequency under low SOC conditions regardless of current, maximum frequency under high SOC conditions regardless of current, voltage drop, current, minimum voltage under low SOC conditions, high SOC conditions The maximum voltage, the absolute value of the voltage difference and the SOC slope under the condition, etc.

Among them, the minimum frequency under the low SOC condition without considering the current indicates the minimum frequency under the low charge condition of the cell without considering the current, and the maximum frequency under the high SOC condition without considering the current indicates It is the maximum frequency of the high charge condition of the cell without considering the current, and the current can be the current of each cell in the battery; the lowest voltage under the low SOC condition indicates the minimum voltage of the cell under low charge; The highest voltage under high SOC conditions indicates the maximum voltage of the cell under high charge; the absolute value of the voltage difference and the SOC slope indicates the absolute value of the slope of the curve between the cell voltage difference and the SOC value.

For any abnormal cell, if there is an abnormality in the internal resistance characteristic data of the abnormal cell, it is determined that the failure risk type of the abnormal cell is abnormal internal resistance; if there is an abnormality in the capacity characteristic data of the abnormal cell, determine The failure risk type of abnormal cells is abnormal capacity.

Wherein, the abnormality in the characteristic data of the internal resistance of the abnormal cell may be an abnormality of any characteristic data of the internal resistance, and the abnormality in the characteristic data of the capacity of the abnormal battery may be the abnormality of any characteristic data of the capacity.

For example, a standard range can be set for the characteristic data of the internal resistance of the battery, that is, a characteristic data of the internal resistance corresponds to a standard range. If it is within the standard range, it is determined that the characteristic data is abnormal, and the failure risk type of the corresponding abnormal cell is abnormal internal resistance.

Correspondingly, a standard range can also be set for the capacity feature data of the battery, that is, a capacity feature data corresponds to a standard range. If it is within the range, it is determined that the characteristic data is abnormal, and the failure risk type of the corresponding abnormal cell is abnormal capacity.

It can be understood that, for any abnormal cell, if there is any abnormality in the characteristic data of the internal resistance of the abnormal cell, and there is any abnormality in the characteristic data of the capacity of the abnormal cell, then determine The abnormal cell has abnormal internal resistance and capacity.

S503. Determine the degree of failure risk of each abnormal battery cell according to the type of failure risk.

Determine the degree of failure risk of each abnormal cell based on the above determined type of failure risk. First, the degree of failure risk of each abnormal cell can be determined through the type of failure risk of the abnormal cell and the state characteristic data corresponding to the abnormal cell.

If the failure risk degree of each abnormal battery cell is abnormal internal resistance, the failure risk degree of each abnormal battery cell is further determined according to the internal resistance characteristic data of each abnormal battery cell, for example, the risk level of each characteristic data is preset, The risk level corresponding to each internal resistance characteristic data is determined as the failure risk degree of the abnormal battery cell.

If the failure risk degree of each abnormal battery cell is abnormal capacity, the failure risk degree of each abnormal battery cell is further determined according to the capacity characteristic data of each abnormal battery cell, for example, the risk level of each characteristic data is preset, and each The risk level corresponding to the capacity characteristic data is determined as the failure risk degree of abnormal batteries.

Optionally, if there are two abnormal characteristic data for the abnormal battery, corresponding to two risk levels, then a comprehensive judgment can be made on the abnormal characteristic data and the corresponding two risk levels to determine the degree of failure risk of the abnormal battery; for example, for the two A weighted judgment is carried out based on each risk level to determine the final failure risk level.

If there are internal resistance abnormalities and capacity abnormalities in the failure risk type of each abnormal cell, the risk level corresponding to the internal resistance abnormality and the risk level corresponding to the capacity abnormality can be determined based on the above method, and then according to the weight of the internal resistance abnormality and the weight of capacity abnormality, determine the final risk level of each abnormal battery, and determine the risk level of each abnormal battery as the failure risk degree of each abnormal battery.

Optionally, the failure risk level may include slight overcharge and undercharge, moderate overcharge and undercharge, and severe overcharge and undercharge.

In the above battery failure prediction method, if the target battery is faulty, obtain at least one abnormal battery cell in the target battery that has the risk of charging high and discharging low, obtain the failure risk type of each abnormal battery cell, and then determine according to the failure risk type The failure risk level of each abnormal cell. In this embodiment, the failure risk type of each abnormal battery cell in the target battery is obtained, and the failure risk degree of each abnormal battery cell is determined based on the failure risk type, which further improves the failure accuracy of the target battery and facilitates subsequent maintenance of the target battery.

The following describes in detail how to determine the degree of failure risk of each abnormal battery cell through an embodiment. In one embodiment, as shown in FIG. 7 , according to the type of failure risk, the degree of failure risk of each abnormal battery cell is determined, including the following step:

S701. For any abnormal battery cell, according to the failure risk type of the abnormal battery cell, determine the target battery characteristic data from the state characteristic data of the abnormal battery cell.

Wherein, the target battery characteristic data includes at least one battery characteristic data; that is, at least one battery characteristic data is selected from the state characteristic data of abnormal batteries, and the selected at least one battery characteristic data is determined as the target battery characteristic data.

In one embodiment, according to the failure risk type of the abnormal battery cell, determining the target battery characteristic data from the state characteristic data of the abnormal battery cell includes: when the failure risk type of the abnormal battery cell is abnormal internal resistance, determining the target battery characteristic data from the abnormal battery cell Determine the target battery characteristic data of the abnormal battery in the internal resistance characteristic data in the state characteristic data of the abnormal battery; when the failure risk type of the abnormal battery is abnormal capacity, the capacity characteristic data in the state characteristic data of the abnormal battery Determine the target battery characteristic data of abnormal batteries in the data.

Specifically, if the fault type of the abnormal battery is abnormal internal resistance, the corresponding characteristic data of internal resistance include: the frequency of the maximum voltage battery during the recharging phase, the slope of the voltage difference current, the internal resistance value, and the difference between the abnormal battery and other normal batteries. Cell internal resistance ratio, absolute value of voltage difference and current slope, cell voltage during discharge and recharge phase, etc.; then at least one feature data can be determined in the internal resistance characteristic data as the target battery characteristic data of the abnormal cell; for example, The characteristic data of the target battery of the abnormal cell may be the voltage drop current slope, the internal resistance value, and the ratio of the internal resistance of the abnormal cell to other normal cells.

If the fault type of the abnormal cell is capacity abnormality, the corresponding capacity characteristic data include: minimum frequency under low SOC condition regardless of current, maximum frequency under high SOC condition regardless of current, voltage difference, current, The lowest voltage under low SOC conditions, the highest voltage under high SOC conditions, the absolute value of the pressure difference and SOC slope, etc.; then at least one characteristic data can be determined in the capacity characteristic data as the target battery characteristic data of abnormal cells ; For example, the target battery characteristic data of the abnormal cell may be the minimum frequency under the low SOC condition regardless of the current, and the maximum frequency under the high SOC condition regardless of the current.

It should be noted that the target battery feature data can represent the state of the abnormal battery cell and the most critical data feature of the abnormal situation.

S702. Determine the failure risk level of the abnormal battery cell according to the target battery characteristic data of the abnormal battery cell.

Since the target battery characteristic data can represent the state and abnormal situation of the abnormal battery cell, the failure risk degree of the abnormal battery cell can be determined according to the target battery characteristic data of the abnormal battery cell.

The method of determining the failure risk degree of the abnormal battery cell may be to determine the abnormal characteristic value of the abnormal battery cell according to the target battery characteristic data of the abnormal battery cell, and the abnormal characteristic value may be a value in the interval from 0 to 1. The degree of failure risk is judged at the distribution position between 0 and 1. The closer the abnormal characteristic value is to 0, the lower the degree of failure risk is, and the closer the abnormal characteristic value is to 1, the higher the degree of failure risk; for example, if the abnormal characteristic A value of 0.1 indicates that the failure risk of the abnormal battery cell is low, and if the abnormal characteristic value is 0.8, it indicates that the failure risk of the abnormal battery cell is high.

Wherein, the method of determining the abnormal characteristic value of the abnormal battery cell according to the target battery characteristic data of the abnormal battery cell may be to calculate the deviation value between the target battery characteristic data of the abnormal battery cell and the safety threshold, and determine the abnormal characteristic value of the abnormal battery cell according to the deviation value , for example, an abnormal characteristic value corresponds to an abnormal deviation range, and the abnormal characteristic value corresponding to the deviation range where the deviation value is located is determined as the abnormal characteristic value of the abnormal cell.

The method of determining the failure risk degree of the abnormal battery cell may also be to compare the target battery characteristic data of the abnormal battery cell with the preset risk level range, and determine which risk level range the target battery characteristic data of the abnormal battery cell is in, Determine the failure risk degree corresponding to the risk level range as the failure risk degree of the abnormal cell; wherein, the risk level range corresponds to the failure risk degree; for example, the risk level range can be the numerical range of the battery characteristic data, and the failure risk degree For the grade range, including first, second, third and so on.

The method of determining the failure risk degree of the abnormal battery cell can also be determined through a preset failure risk model, specifically, input the target battery characteristic data of the abnormal battery cell into the failure risk model, and use the failure risk model to determine Analyze the characteristic data of the target battery to obtain the failure risk degree of the abnormal battery.

In the above battery failure prediction method, for any abnormal battery cell, according to the failure risk type of the abnormal battery cell, the target battery characteristic data is determined from the state characteristic data of the abnormal battery cell, and then according to the target battery characteristic data of the abnormal battery cell, determine The degree of failure risk of the abnormal battery cell; wherein, the target battery characteristic data includes at least one battery characteristic data. In the method, the failure risk degree of the abnormal battery cell is determined according to at least one battery characteristic data selected from the state characteristic data of the abnormal battery cell, and the accuracy of determining the failure risk degree of the abnormal battery cell is improved.

A specific implementation of determining the degree of failure risk of abnormal cells is given below. In one embodiment, as shown in FIG. 8 , according to the target battery characteristic data of abnormal cells, the degree of failure risk of abnormal cells is determined, including the following step:

S801. Obtain target battery feature data of other normal cells in the target battery except the abnormal cells.

When determining the failure risk degree of an abnormal cell, it is necessary to obtain the target battery characteristic data of other normal cells in the target battery except the abnormal cell, and then use the target battery characteristic data of the abnormal cell and the target battery characteristic of the normal cell In this way, the degree of failure risk of abnormal batteries can be determined more reasonably.

Based on the abnormal cells in the target battery determined above, the normal cells in the target battery can be determined, and then the target battery feature data of the normal cells can be directly obtained from the database.

Among them, the battery characteristic data of each cell in the battery will be stored in the database, and the target battery characteristic data can be obtained directly through the sensor, for example, the cell voltage; the battery data can also be obtained through the sensor, and then processed through the battery data , to obtain target battery characteristic data, for example, cell voltage difference; the target battery characteristic data includes at least one battery characteristic data.

S802, horizontally comparing the target battery characteristic data of the abnormal battery cell with the target battery characteristic data of other normal batteries, so as to determine the degree of failure risk of the abnormal battery cell.

The horizontal comparison can be the comparison of the same kind of data, and the horizontal comparison between the target characteristic data of the abnormal battery and the target battery characteristic data of other normal batteries can be the same target battery characteristic data of the abnormal battery and other normal batteries in the same cycle Comparison.

In one embodiment, if the target battery characteristic data is the cell voltage difference, the cell voltage difference is the cell voltage difference within a preset period, therefore, the cell voltage difference of the abnormal cell can be compared with other normal cells. Compare the average value of the cell voltage difference of the abnormal cell to determine the failure risk of the abnormal cell; the difference between the cell voltage difference of the abnormal cell and the average value of the cell voltage difference of other normal cells can be calculated, according to the difference The absolute value of the value determines the degree of risk of failure.

For example, if the absolute value of the difference is greater than the first preset threshold, it is determined that the failure risk degree of the abnormal cell is level 1, and the absolute value of the difference is greater than the second preset threshold and less than or equal to the first preset threshold, then it is determined The failure risk degree of the abnormal battery cell is level 2, and the absolute value of the difference is greater than the third preset threshold and less than or equal to the second preset threshold value, then it is determined that the failure risk level of the abnormal battery cell is level 3, wherein the first preset threshold The threshold is set to be greater than a second preset threshold, and the second preset threshold is greater than a third preset threshold.

In the above battery fault prediction method, the target battery characteristic data of other normal cells in the target battery except abnormal cells are obtained, and the target battery characteristic data of abnormal cells and the target battery characteristic data of other normal cells are compared horizontally , to determine the degree of failure risk of abnormal cells. In this method, by comparing the abnormal data with the normal data horizontally, the accuracy of determining the failure risk degree of the abnormal battery cell is ensured.

For example, if the target battery characteristic data is the internal resistance value, then in one embodiment, as shown in Figure 9, the target battery characteristic data of the abnormal battery cell and the target battery characteristic data of other normal batteries are compared horizontally to determine The degree of risk of failure of abnormal batteries includes the following steps:

S901. Obtain the internal resistance value of the abnormal battery cell, and obtain the median internal resistance value of the abnormal battery cell and other normal battery cells.

If the characteristic data of the target battery is the internal resistance value, the internal resistance value of the abnormal cell can be horizontally compared with the median internal resistance value of other normal cells. Therefore, before the comparison, it is necessary to obtain the internal resistance of the abnormal cell value and the median internal resistance of other normal cells.

There is no direct measurement of the internal resistance of the battery cell. Therefore, the internal resistance of the battery cell needs to be calculated. One of the ways to calculate the internal resistance can be to obtain the voltage and current of the battery cell through a sensor, and determine it by the ratio of voltage to current. The internal resistance value of the battery cell can be used to obtain the internal resistance value of each battery cell in the target battery; this application does not limit the method of calculating the internal resistance value of the battery cell, and the internal resistance value can be calculated through different logics, and calculated according to different logics The internal resistance value determines the internal resistance value of the cell; for example, the average value of the internal resistance values calculated by different logics is determined as the internal resistance value of the cell.

Obtain the internal resistance value of the abnormal cell and the internal resistance value of other normal cells from the internal resistance value of each cell, and then determine the median internal resistance value from the internal resistance values of other normal cells.

It can be understood that when obtaining the internal resistance value of the abnormal battery cell and the internal resistance value of other normal battery cells, other influencing factors of the abnormal battery cell and other normal battery cells are the same.

S902. Obtain the ratio of the internal resistance value to the median internal resistance value.

Based on the above-mentioned internal resistance value of the abnormal cell and other normal median internal resistance values, the ratio of the internal resistance value of the abnormal cell to the median internal resistance value of other normal cells is calculated.

S903. Determine the failure risk degree of the abnormal battery cell according to the ratio and preset multiple different failure risk degree grade ranges.

Based on the ratio of the internal resistance value of the abnormal cell to the median internal resistance value of the normal cell, the fault risk level range is preset. For example, if the ratio range is between 1.5-2, the fault risk level is level 1. If the range of the ratio is between 2.1-2.5, the degree of risk of failure is level 2, and the range of the ratio is between 2.6-3, the level of risk of failure is level 3.

If the ratio of the internal resistance value of the abnormal cell in the target battery to the median internal resistance value of other normal cells is 1.6, it can be determined that the failure risk level of the abnormal cell is level 1.

It should be noted that the numerical value of the above-mentioned ratio range is only described as an example, and in practical applications, the present application does not limit the ranges of multiple different fault severity levels.

Optionally, for a certain abnormal cell L, if the internal resistance of the abnormal cell L at time T1 is X1, the median internal resistance value of other normal cells is X2, X1/X2=Q, and then according to Q Compared with multiple preset thresholds, different thresholds correspond to different failure risk levels, so that the failure risk level of the abnormal battery L can be determined. For example, the predicted failure risk level includes that the abnormal battery L may have a slight charge. High discharge phenomenon, the abnormal battery L may have a moderate charge high discharge phenomenon, the abnormal battery L may have a severe charge high discharge phenomenon, and the abnormal battery L may have a very serious charge high discharge phenomenon.

In one embodiment, the ratio of the internal resistance value of the abnormal cell to the median internal resistance value of other normal cells can be used to determine whether the connection between the cells is abnormal; The method of resistance value is not limited. A variety of logics can be used to calculate the internal resistance value and check each other. If the ratio is abnormal within one cycle, it will be regarded as an abnormal phenomenon; abnormal internal resistance includes abnormality of connectors.

In the above battery fault prediction method, the internal resistance value of the abnormal cell is obtained, and the median internal resistance value of the abnormal cell and other normal cells is obtained, and the ratio of the internal resistance value to the median internal resistance value is obtained, and according to the ratio and preset a plurality of different failure risk level ranges to determine the failure risk level of abnormal batteries. In this method, the internal resistance value of the abnormal cell and the median internal resistance value of other normal cells are considered, and the fault risk degree of the abnormal cell is determined based on the ratio and the preset different fault risk level ranges , which ensures the accuracy of the determined failure risk degree of the abnormal battery cell.

In one embodiment, as shown in Fig. 10, Fig. 10 is a battery fault prediction method. First, historical data is obtained in the big data platform, and the historical data is historical fault sample data, and the data characteristics are established by using the historical fault sample data. The time series change and the state time series change are connected to obtain the fault monitoring model; then the fault monitoring model is used to monitor the real-time data of the big data platform in real time, and the real-time monitoring results are obtained. Specifically, the real-time data is input into the fault monitoring model, through the fault monitoring The model analyzes real-time data to obtain real-time monitoring results.

The following is a detailed description of how to build a fault monitoring model based on historical data. As shown in Figure 11, an abnormal connection between cells will lead to abnormal internal resistance. According to the abnormal fault mechanism, the internal resistance of the cells between cells in the battery will be abnormal. As a result, the phenomenon of charging and lowering occurs in the battery cell, and the cruising range is reduced.

According to the mechanism process, the characteristics of the historical data are determined. Specifically, through the charging frequency, lowering frequency, and pressure difference, it is judged whether there is a charging phenomenon. If there is a charging phenomenon, determine the charging cell number and Lower the cell number, that is, the abnormal cell.

Then, judge whether the abnormal battery cell that causes the phenomenon of high charge and low discharge is abnormal internal resistance or abnormal capacity according to the characteristics of the battery; battery characteristics can include: high current low SOC discharge low voltage frequency, high current charging high voltage frequency, high current recharging high Voltage frequency, low SOC discharge low voltage frequency, high SOC charge high voltage frequency, dropout current slope and dropout SOC correlation, etc.

Make a horizontal comparison of abnormal cells, calculate the median internal resistance ratio of abnormal cells and other normal cells, and/or the ratio of the voltage change rate of abnormal cells to the median voltage change rate of other normal cells, etc., to determine whether Abnormal internal resistance.

Finally, based on the above analysis process, the characteristics of the historical fault samples corresponding to the historical data are extracted periodically, and the relationship between the time series change of data characteristics and the time series change of state is established to build a fault monitoring model.

Correspondingly, when the fault monitoring model monitors real-time data in real time, it can extract the characteristic data of real-time data by cycle, analyze the abnormal distribution of characteristic data within a cycle and the abnormal change trend between cycles, and analyze the abnormal distribution of characteristic data within a cycle and the abnormality between cycles. The change trend comprehensively judges whether there is a fault abnormality, and obtains real-time monitoring results; the fault monitoring model can include a classification model and a time series model, and the classification model is used to analyze the abnormal distribution of characteristics within a cycle, and the time series model is used to analyze the abnormal change trend of characteristics between cycles.

In one embodiment, the frequency of the maximum voltage cell during the recharging phase, the slope of the differential voltage current, the internal resistance, the ratio of the internal resistance of the abnormal cell to other normal cells, etc. can be used to determine whether there is an abnormal internal resistance. Among them, the internal resistance can be determined by the ratio of the current jump voltage to the current, and can also be determined by the slope of the voltage and current in a period of time window.

The minimum cell frequency under the low SOC operating condition without considering the current and the maximum cell frequency under the high SOC operating condition are comprehensively judged whether the capacity may be abnormal.

In one embodiment, as shown in Figure 11, this embodiment comprises the following steps:

S1201. Acquire state feature data of a target battery in multiple cycles, where the state feature data in each cycle includes a plurality of different battery feature data.

S1202. Determine the failure prediction result of the target battery by analyzing the state characteristic data in multiple cycles.

Wherein, the fault prediction result includes whether there is a fault in the target battery or not, and whether the target battery is charged high or low.

In the first case, multiple different models are distinguished for implementation, then S1202 includes:

First, according to a plurality of different battery characteristic data in each cycle, obtain the abnormal distribution of battery characteristics in each cycle; and, according to the state characteristic data in multiple cycles, obtain the abnormal changes of battery characteristics in the multiple cycles trend.

Among them, the abnormal distribution of battery characteristics in each cycle is obtained by analyzing a plurality of different battery characteristic data in each cycle through a classification model constructed in advance based on historical data. And, analyze the state feature data in multiple cycles through the time series model constructed in advance based on historical data, and obtain the abnormal change trend of battery characteristics in the multiple cycles.

Then, according to the abnormal distribution of battery characteristics in each cycle and the abnormal change trend of battery characteristics in the multiple cycles, the failure prediction result of the target battery is determined.

In the second case, an overall model is used to realize, then S1202 includes:

Input the state characteristic data in multiple cycles into the fault prediction model constructed in advance based on historical data, and analyze the abnormal distribution of battery characteristics within the target battery cycle and the abnormal change trend of battery characteristics between cycles through the fault prediction model, and obtain Failure prediction results for the target battery.

S1203. Determine the high-charged and low-charged battery cell from the target battery as the abnormal battery cell.

S1204. For each abnormal cell, distinguish whether each abnormal cell is abnormal in internal resistance or abnormal in capacity.

Specifically, for any abnormal cell, a plurality of characteristic data of the internal resistance of the abnormal cell is extracted, and if there is an abnormal feature in the characteristic data of the internal resistance, it is determined that the cell is abnormal in internal resistance.

For any abnormal cell, extract multiple capacity feature data of the abnormal cell, if there are abnormal features in the capacity feature data (as long as one feature is abnormal), then it is determined that the cell is abnormal in capacity .

S1205, horizontally comparing the abnormal battery cell with other normal battery cells in the target battery, so as to predict the degree of failure risk of each abnormal battery cell.

If the internal resistance is abnormal, select one or more features from the internal resistance feature data to predict the failure risk of the abnormal cell; if the capacity is abnormal, select one or more features from the capacity feature data The characteristics predict the degree of failure risk of abnormal cells.

For the specific limitations of the battery failure prediction method provided in this embodiment, refer to the above-mentioned step definitions for each embodiment of the battery failure prediction method, and details are not repeated here.

It should be understood that although the steps in the flow charts involved in the above embodiments are shown sequentially as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flow charts involved in the above-mentioned embodiments may include multiple steps or stages, and these steps or stages are not necessarily executed at the same time, but may be performed at different times For execution, the execution sequence of these steps or stages is not necessarily performed sequentially, but may be performed in turn or alternately with other steps or at least a part of steps or stages in other steps.

Based on the same inventive concept, an embodiment of the present application further provides a battery failure prediction device for implementing the above-mentioned battery failure prediction method. The solution to the problem provided by the device is similar to the implementation described in the above method, so the specific limitations in one or more embodiments of the battery failure prediction device provided below can be referred to above for the battery failure prediction method limited and will not be repeated here.

In one embodiment, as shown in FIG. 13 , a battery failure prediction device is provided, including: an acquisition module 1301, an analysis module 1302, and a determination module 1303, wherein:

An acquisition module 1301, configured to acquire state characteristic data of the target battery in multiple cycles; wherein, the state characteristic data in each cycle includes a plurality of different battery characteristic data;

An analysis module 1302, configured to perform correlation analysis processing on the state characteristic data in multiple periods, and obtain correlation analysis processing results;

The determination module 1303 is configured to determine the failure prediction result of the target battery according to the correlation analysis processing result.

In one embodiment, the analysis module 1302 includes:

The processing unit is used to input the state feature data in multiple cycles into the fault prediction model, and perform correlation analysis processing on the state feature data in multiple cycles through the fault prediction model to obtain correlation analysis processing results.

In one embodiment, the processing unit includes:

The first acquisition subunit is configured to acquire abnormal distribution information of battery characteristics in each cycle and obtain abnormal change trend information of battery characteristics in multiple cycles according to the state characteristic data in multiple cycles;

The processing subunit is used to perform correlation analysis and processing on the abnormal distribution information of battery characteristics in each cycle and the abnormal change trend information of battery characteristics in multiple cycles, and obtain the results of correlation analysis and processing.

In one embodiment, the first acquisition subunit includes:

The first input subunit is used to input a plurality of different battery characteristic data in the state characteristic data in each cycle into the classification model to obtain abnormal distribution information of battery characteristics in each cycle;

The second input subunit is used to input a plurality of different battery characteristic data in the state characteristic data in each cycle to the time series model to obtain abnormal change trend information of battery characteristics in multiple cycles.

In one embodiment, the device 1300 also includes:

The abnormal battery cell determination module is used to obtain at least one abnormal battery cell in the target battery that has a risk of charging high and discharging low when the target battery is faulty;

The fault type determination module is used to obtain the fault risk type of each abnormal cell;

The risk degree determination module is used to determine the failure risk degree of each abnormal battery cell according to the failure risk type.

In one embodiment, the fault type determination module includes:

The dividing unit is used to divide the state characteristic data of the abnormal battery for any abnormal battery, and obtain the internal resistance characteristic data and capacity characteristic data of the abnormal battery;

The first determination unit is used to determine that the failure risk type of the abnormal battery cell is abnormal internal resistance when there is an abnormality in the internal resistance characteristic data of the abnormal battery cell;

The second determining unit is configured to determine that the failure risk type of the abnormal battery cell is abnormal capacity when there is an abnormality in the capacity characteristic data of the abnormal battery cell.

In one embodiment, the risk degree determination module includes:

The third determination unit is configured to, for any abnormal battery cell, determine the target battery characteristic data from the state characteristic data of the abnormal battery cell according to the failure risk type of the abnormal battery cell, where the target battery characteristic data includes at least one battery characteristic data;

The fourth determining unit is configured to determine the degree of failure risk of the abnormal battery cell according to the target battery characteristic data of the abnormal battery cell.

In one embodiment, the third determination unit includes:

The first determination subunit is used to determine the target battery characteristic data of the abnormal battery from the internal resistance characteristic data in the state characteristic data of the abnormal battery when the failure risk type of the abnormal battery is abnormal internal resistance;

The second determination subunit is used to determine the target battery characteristic data of the abnormal battery from the capacity characteristic data in the state characteristic data of the abnormal battery when the failure risk type of the abnormal battery is abnormal capacity.

In one embodiment, the fourth determination unit includes:

The second obtaining subunit is used to obtain the target battery characteristic data of other normal cells in the target battery except abnormal cells;

The third determination subunit is used to horizontally compare the target battery characteristic data of the abnormal battery cell with the target battery characteristic data of other normal batteries, so as to determine the degree of failure risk of the abnormal battery cell.

In one embodiment, the third determining subunit includes:

The third obtaining subunit is used to obtain the internal resistance value of the abnormal cell, and obtain the median internal resistance value of the abnormal cell and other normal cells;

The fourth obtaining subunit is used to obtain the ratio of the internal resistance value to the median internal resistance value;

The fourth determination subunit is used to determine the failure risk degree of the abnormal battery cell according to the ratio and preset multiple different failure risk degree grade ranges.

Each module in the above-mentioned battery failure prediction device can be fully or partially realized by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure may be as shown in FIG. 14 . The computer device includes a processor, a memory, an input/output interface (Input/Output, I/O for short), and a communication interface. Wherein, the processor, the memory and the input/output interface are connected through the system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs and databases. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. A database of the computer device is used to store battery failure prediction data. The input/output interface of the computer device is used for exchanging data between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a battery failure prediction method is realized.

Those skilled in the art can understand that the structure shown in Figure 14 is only a block diagram of a partial structure related to the solution of this application, and does not constitute a limitation on the computer equipment on which the solution of this application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In one embodiment, there is also provided a computer device, including a memory and a processor, where a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

The implementation principles and technical effects of the various steps implemented by the processor in this embodiment are similar to those of the above battery failure prediction method, and will not be repeated here.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

The implementation principles and technical effects of the various steps implemented when the computer program is executed by the processor in this embodiment are similar to those of the battery failure prediction method described above, and will not be repeated here.

In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

The implementation principles and technical effects of the various steps implemented when the computer program is executed by the processor in this embodiment are similar to those of the battery failure prediction method described above, and will not be repeated here.

It should be noted that the data involved in this application (including but not limited to data used for analysis, stored data, displayed data, etc.) are all data authorized by the user or fully authorized by all parties, and the relevant data Collection, use and processing need to comply with relevant laws, regulations and standards of relevant countries and regions.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any reference to storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile and volatile storage. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive variable memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory, MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (Phase Change Memory, PCM), graphene memory, etc. The volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory. As an illustration and not a limitation, the RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a blockchain-based distributed database, etc., but is not limited thereto. The processors involved in the various embodiments provided by this application can be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., and are not limited to this.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be determined by the appended claims.

Claims (14)

1. A method of battery failure prediction, the method comprising:

acquiring state characteristic data of a target battery in a plurality of periods; the state characteristic data in each period comprise a plurality of different battery characteristic data;

performing correlation analysis processing on the state characteristic data in the multiple periods to obtain correlation analysis processing results;

and determining a fault prediction result of the target battery according to the correlation analysis processing result.

2. The method according to claim 1, wherein the performing correlation analysis processing on the state feature data in the plurality of cycles to obtain a correlation analysis processing result comprises:

and inputting the state characteristic data in the multiple periods into a fault prediction model, and performing correlation analysis processing on the state characteristic data in the multiple periods through the fault prediction model to obtain a correlation analysis processing result.

3. The method according to claim 2, wherein the performing, by the fault prediction model, a correlation analysis process on the state feature data in the plurality of cycles to obtain the correlation analysis process result comprises:

according to the state characteristic data in the multiple periods, acquiring battery characteristic abnormal distribution information in each period and acquiring battery characteristic abnormal change trend information in the multiple periods;

and performing correlation analysis processing on the abnormal distribution information of the battery characteristics in each period and the abnormal change trend information of the battery characteristics in the plurality of periods to obtain a correlation analysis processing result.

4. The method according to claim 3, wherein the fault prediction model comprises a classification model and a time sequence model, and the obtaining of the abnormal distribution information of the battery characteristics in each period and the abnormal variation trend information of the battery characteristics in the plurality of periods according to the state characteristic data in the plurality of periods comprises:

inputting a plurality of different battery characteristic data in the state characteristic data in each period into the classification model to obtain battery characteristic abnormal distribution information in each period;

and inputting a plurality of different battery characteristic data in the state characteristic data in each period into the time sequence model to obtain the abnormal variation trend information of the battery characteristics in the plurality of periods.

5. The method of any of claims 1 to 4, wherein the fault prediction result comprises a presence or absence of a fault in the target battery, the method further comprising:

under the condition that the target battery has a fault, acquiring at least one abnormal battery cell with high charge and discharge risks in the target battery;

acquiring the fault risk types of the abnormal battery cells;

and determining the fault risk degree of each abnormal battery cell according to the fault risk type.

6. The method of claim 5, wherein the fault risk types include internal resistance abnormality or capacity abnormality, and the obtaining the fault risk types of the abnormal battery cells includes:

for any abnormal battery cell, dividing the state characteristic data of the abnormal battery cell to obtain internal resistance characteristic data and capacity characteristic data of the abnormal battery cell;

determining the fault risk type of the abnormal battery cell as internal resistance abnormality under the condition that the internal resistance characteristic data of the abnormal battery cell is abnormal;

and under the condition that the abnormal capacity characteristic data of the abnormal electric core exists, determining that the fault risk type of the abnormal electric core is capacity abnormality.

7. The method of claim 5, wherein the determining the fault risk degree of each abnormal electrical core according to the fault risk type includes:

for any abnormal electric core, determining target battery characteristic data from state characteristic data of the abnormal electric core according to the fault risk type of the abnormal electric core, wherein the target battery characteristic data comprises at least one battery characteristic data;

and determining the fault risk degree of the abnormal battery cell according to the target battery characteristic data of the abnormal battery cell.

8. The method of claim 7, wherein the determining target battery characteristic data from the state characteristic data of the abnormal cell according to the fault risk type of the abnormal cell comprises:

determining target battery characteristic data of the abnormal electric core from the internal resistance characteristic data in the state characteristic data of the abnormal electric core under the condition that the fault risk type of the abnormal electric core is abnormal internal resistance;

and under the condition that the fault risk type of the abnormal electric core is abnormal in capacity, determining target battery characteristic data of the abnormal electric core from capacity characteristic data in the state characteristic data of the abnormal electric core.

9. The method of claim 7, wherein the determining the fault risk level of the abnormal cell according to the target battery characteristic data of the abnormal cell comprises:

acquiring target battery characteristic data of other normal cells except for the abnormal cells in the target battery;

and transversely comparing the target battery characteristic data of the abnormal electric core with the target battery characteristic data of the other normal electric cores to determine the fault risk degree of the abnormal electric core.

10. The method of claim 9, wherein if the target battery characteristic data is an internal resistance value, the transversely comparing the target battery characteristic data of the abnormal cell with the target battery characteristic data of the other normal cells to determine the fault risk level of the abnormal cell comprises:

acquiring the internal resistance value of the abnormal electric core and acquiring the median internal resistance values of the abnormal electric core and the other normal electric cores;

obtaining the ratio of the internal resistance value to the internal resistance value of the median;

and determining the fault risk degree of the abnormal electric core according to the ratio and a plurality of preset different fault risk degree grade ranges.

11. A battery failure prediction apparatus, the apparatus comprising:

the acquisition module is used for acquiring state characteristic data of the target battery in a plurality of periods; the state characteristic data in each period comprise a plurality of different battery characteristic data;

the analysis module is used for carrying out correlation analysis processing on the state characteristic data in the multiple periods to obtain correlation analysis processing results;

and the determining module is used for determining the fault prediction result of the target battery according to the correlation analysis processing result.

12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 10 when executing the computer program.

13. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 10 when executed by a processor.

Images