CN111950578A - A method and device for determining the state of a vehicle - Google Patents

Abstract

The invention discloses a method and a device for determining the state of a vehicle, which relates to the technical field of data processing to solve the problems that the fault of the vehicle cannot be determined in time and the maintenance cost is high. The method includes: acquiring monitoring data of a vehicle to be monitored, wherein the monitoring data includes real-time monitoring data of the vehicle to be monitored; classifying the monitoring data to obtain monitoring data sets of different vehicle types; targeting a target vehicle type, obtain a target correlation coefficient data set according to the target monitoring data set of the target vehicle type; perform cluster analysis on the target correlation coefficient data set to determine the state of the target vehicle with the target vehicle type. The embodiment of the present invention can improve the safety of the vehicle and reduce the maintenance cost.

Description

A method and device for determining the state of a vehicle

technical field

The present invention relates to the technical field of data processing, and in particular, to a method and device for determining vehicle status.

Background technique

In order to ensure the safe and reliable performance of the vehicle, usually the driver or maintenance personnel will check the vehicle regularly. But some real-time failures can threaten driving safety, and post-mortem inspections are difficult to correct. The method of regular inspection cannot predict the failure cycle of the vehicle, which will cause waste of resources. Routine inspections require specialized knowledge, equipment and space, and are costly. Therefore, by analyzing the state data of the vehicle, the failure information of the vehicle can be analyzed.

For example, in the patent document US20180315260A1, the status information and fault records of the same vehicle model are used to train a fault determination model, and faults are determined according to the model and real-time status information. Among them, the state data in the case of vehicle failure and the corresponding failure records are obtained by collecting data for artificially manufactured failures. The patent also designs a method to motivate the driver to upload the failure records.

Patent documents WO2017/129510A1, CN140214329A, CN 103135515A, etc., propose methods for determining vehicle faults by utilizing the professional knowledge of vehicle experts and thresholds of certain state data.

However, the fault record required in the patent document US20180315260A1 is difficult to obtain, or the structure of the fault record is complicated and difficult to be processed by a computer. At the same time, the invention requires data for a long time and is difficult to implement. The patent documents WO2017/129510A1, CN140214329A, CN 103135515A, etc. require professional knowledge and equipment, the cost is high, and at the same time, they cannot be applied to different vehicle models.

Therefore, with the above methods of the prior art, the failure of the vehicle cannot be determined in time, and the maintenance cost is relatively high.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a method and device for determining a vehicle state, so as to improve the safety of the vehicle and reduce maintenance costs.

In a first aspect, an embodiment of the present invention provides a method for determining a state of a vehicle, including:

acquiring monitoring data of the vehicle to be monitored, wherein the monitoring data includes real-time monitoring data of the vehicle to be monitored;

Classifying the monitoring data to obtain monitoring data sets of different vehicle types;

For the target vehicle type, obtain a target correlation coefficient data set according to the target monitoring data set of the target vehicle type;

Cluster analysis is performed on the target correlation coefficient data set to determine the state of the target vehicle having the target vehicle type.

Wherein, the monitoring data further includes historical monitoring data of the vehicle to be monitored, and the monitoring data set includes a real-time monitoring data set and a historical monitoring data set;

The said monitoring data are classified to obtain monitoring data sets of different vehicle types, including:

Classifying the real-time monitoring data to obtain real-time monitoring data sets of different vehicle types;

Classify the historical monitoring data to obtain historical monitoring data sets of different vehicle types.

Wherein, obtaining the target correlation coefficient data set according to the target monitoring data set of the target vehicle type includes:

For the data items in the target monitoring data set, calculate the correlation coefficient between every two data items;

Using the calculated correlation coefficients, the target correlation coefficient data set is formed.

Wherein, for the data items in the target monitoring data set, calculating the correlation coefficient between every two data items, including:

A first matrix is formed by using multiple data items at the same sampling time in the target monitoring data set;

splitting the first matrix into a second matrix and a third matrix;

Calculate the product of the second matrix and the first result to obtain a fourth matrix;

Wherein, each element in the fourth matrix represents a correlation coefficient; the first result is the result of performing a matrix pseudo-inverse operation on the second matrix and the third matrix.

Wherein, performing cluster analysis on the target correlation coefficient data set to determine the state of the target vehicle with the target vehicle type includes:

Perform cluster analysis on the target correlation coefficient data set to obtain a cluster analysis result;

determining that the state of the target vehicle in the first class is normal, and determining that the state of the target vehicle in other classes is faulty;

The first category is the category that contains the most data points in the cluster analysis result, and the other categories are categories other than the first category in the cluster analysis result.

Wherein, after the determining the state of the target vehicle having the target vehicle type, the method further includes:

Sending prompt information to the target vehicle, where the prompt information includes a second fault type corresponding to the second category, and the second category is any one of the other categories.

Wherein, before the sending prompt information to the target vehicle, the method further includes:

The physical meaning of the second fault type is acquired, and the prompt information further includes the physical meaning of the second fault type.

Wherein, after the determining the state of the target vehicle having the target vehicle type, the method further includes:

Calculate the degradation index of the third class, where the third class is any one of the other classes.

Wherein, the calculation of the deterioration index of the third category includes:

Using the distance between the first data point in the third category and the first category, and the sampling time corresponding to the first data point, a coordinate pair is formed;

Perform fitting calculation on the coordinate pairs corresponding to all data points in the third category;

According to the result of the fitting calculation, the deterioration index of the third category is calculated.

In a second aspect, an embodiment of the present invention provides a device for determining a state of a vehicle, including:

a first acquisition module, configured to acquire monitoring data of the vehicle to be monitored, wherein the monitoring data includes real-time monitoring data of the vehicle to be monitored;

a second acquisition module, configured to classify the monitoring data to obtain monitoring data sets of different vehicle types;

A third obtaining module, configured to obtain a target correlation coefficient data set according to the target monitoring data set of the target vehicle type for the target vehicle type;

A determination module, configured to perform cluster analysis on the target correlation coefficient data set to determine the state of the target vehicle with the target vehicle type.

Wherein, the monitoring data further includes historical monitoring data of the vehicle to be monitored, and the monitoring data set includes a real-time monitoring data set and a historical monitoring data set;

The second acquisition module includes:

a first acquisition sub-module for classifying the real-time monitoring data to obtain real-time monitoring data sets of different vehicle types;

The second obtaining sub-module is configured to classify the historical monitoring data to obtain historical monitoring data sets of different vehicle types.

Wherein, the third acquisition module includes:

A calculation submodule for calculating the correlation coefficient between every two data items for the data items in the target monitoring data set;

An acquisition sub-module is used to form the target correlation coefficient data set by using the calculated correlation coefficient.

Wherein, the calculation submodule includes:

a processing unit, configured to form a first matrix by using a plurality of data items at the same sampling time in the target monitoring data set;

a splitting unit for splitting the first matrix into a second matrix and a third matrix;

a calculation unit, configured to calculate the product of the second matrix and the first result to obtain a fourth matrix;

Wherein, each element in the fourth matrix represents a correlation coefficient; the first result is the result of performing a matrix pseudo-inverse operation on the second matrix and the third matrix.

Wherein, the determining module includes:

an analysis sub-module for performing cluster analysis on the target correlation coefficient data set to obtain a cluster analysis result;

a determining submodule, used for determining that the state of the target vehicle in the first class is normal, and determining that the state of the target vehicle in other classes is faulty;

The first category is the category that contains the most data points in the cluster analysis result, and the other categories are categories other than the first category in the cluster analysis result.

Wherein, the device also includes:

The calculation module is used to calculate the deterioration index of the third category, where the third category is any category among other categories.

Wherein, the computing module includes:

a processing submodule, configured to form a coordinate pair by using the distance between the first data point in the third category and the first category, and the sampling time corresponding to the first data point;

a fitting submodule, used to perform fitting calculation on the coordinate pairs corresponding to all the data points in the third category;

The calculation sub-module is configured to calculate the deterioration index of the third category according to the result of the fitting calculation.

In the embodiment of the present invention, the state of the vehicle can be determined only according to the real-time monitoring data of the vehicle to be monitored. Compared with the prior art, the solution of the embodiment of the present invention can determine the vehicle state in time, thereby improving the safety of the vehicle and reducing the maintenance cost.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative labor.

1 is one of the flowcharts of a method for determining a vehicle state provided by an embodiment of the present invention;

2 is a system hardware structure diagram of an embodiment of the present invention;

FIG. 3 is the second flow chart of the method for determining the state of the vehicle provided by the embodiment of the present invention;

4 is a schematic diagram of a cluster analysis result in an embodiment of the present invention;

Fig. 5 is the prediction schematic diagram of the deterioration index in the embodiment of the present invention;

6 is a schematic diagram of a process of determining the physical meaning of a fault type in an embodiment of the present invention;

FIG. 7 is one of the structural diagrams of an apparatus for determining a vehicle state according to an embodiment of the present invention;

8 is a schematic diagram of a second acquisition module in an embodiment of the present invention;

9 is a schematic diagram of a third acquisition module in an embodiment of the present invention;

10 is a schematic diagram of a computing submodule in an embodiment of the present invention;

11 is a schematic diagram of a determination module in an embodiment of the present invention;

FIG. 12 is the second structural diagram of the apparatus for determining the state of the vehicle according to the embodiment of the present invention;

FIG. 13 is a third structural diagram of an apparatus for determining a vehicle state according to an embodiment of the present invention;

FIG. 14 is the fourth structural diagram of the apparatus for determining the state of the vehicle according to the embodiment of the present invention;

15 is a schematic diagram of a computing module in an embodiment of the present invention;

FIG. 16 is a schematic diagram of a device for determining a state of a vehicle according to an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Referring to FIG. 1, FIG. 1 is a flowchart of a method for determining a vehicle state provided by an embodiment of the present invention. As shown in FIG. 1, the method includes the following steps:

Step 101: Obtain monitoring data of the vehicle to be monitored, wherein the monitoring data includes real-time monitoring data of the vehicle to be monitored.

In the embodiment of the present invention, a monitoring device may be installed on the vehicle, and then the monitoring data of the vehicle is obtained through the monitoring device. For example, monitoring data can be acquired through OBD (On-Board Diagnostics, on-board determination system) on the vehicle to be monitored.

Here, the monitoring data includes real-time monitoring data of the vehicle to be monitored at a certain sampling moment. Further, in order to improve the safety of the vehicle, in the embodiment of the present invention, the monitoring data may further include historical monitoring data of the measurement to be monitored. That is, the monitoring data before the current sampling time. Wherein, the monitoring data may include, for example, engine state, oil quantity, and the like.

Step 102: Classify the monitoring data to obtain monitoring data sets of different vehicle types.

In the embodiment of the present invention, the monitoring data is classified based on the vehicle type, so as to obtain monitoring data sets corresponding to different vehicle types.

If the monitoring data includes real-time monitoring data, in this step, the real-time monitoring data is classified according to the vehicle type, and real-time monitoring data sets of different vehicle types are obtained.

If the monitoring data includes real-time monitoring data and historical monitoring data, then, in this step, according to the vehicle type, the real-time monitoring data is classified to obtain real-time monitoring data sets of different vehicle types; and, according to the vehicle type, the The historical monitoring data is classified to obtain historical monitoring data sets of different vehicle types.

Step 103: For the target vehicle type, obtain a target correlation coefficient data set according to the target monitoring data set of the target vehicle type.

For each vehicle type, a correlation coefficient data set is obtained here according to its corresponding monitoring data set. Wherein, the target vehicle type refers to any vehicle type.

In this step, taking the target vehicle type as an example, for the data items in the target monitoring data set, the correlation coefficient between every two data items is calculated, and then, the target correlation coefficient is formed by using the calculated correlation coefficient data set.

Specifically, a first matrix is formed by using multiple data items at the same sampling time in the target monitoring data set, and then the first matrix is divided into a second matrix and a third matrix. Then, the product of the second matrix and the first result is calculated to obtain a fourth matrix; wherein, each element in the fourth matrix represents a correlation coefficient; the first result is the second matrix and the The result of performing the matrix pseudo-inverse operation on the third matrix.

For each time period, the data at the same sampling moment forms a first matrix. The number of rows represents different data items, and the number of columns represents different sampling moments, or vice versa.

Split the first matrix into two matrices: X and Y, where X=(x(t,1),x(t,2),x(t,3),...x(t,m)), Y=(y(t,1),y(t,2),y(t,3),...,y(t,n)).

After that, the correlation coefficient matrix Tr is calculated using the following formula (1):

Tr=X*pinv((X, Y)), namely:

Among them, pinv represents the matrix pseudo-inverse operation. Among them, t is the current moment, and k+l is greater than or equal to m+n. Each element in the calculated matrix Tr represents a correlation coefficient at the current time t.

After obtaining Tr, it can also be converted into a one-dimensional vector, then each element in the one-dimensional vector represents a correlation coefficient.

For both the real-time monitoring data set and the historical monitoring data set, the corresponding correlation coefficient data set can be calculated according to the same method as above.

Step 104: Perform cluster analysis on the target correlation coefficient data set to determine the state of the target vehicle having the target vehicle type.

Here, any method can be used to perform cluster analysis on the target correlation coefficient data set to obtain a cluster analysis result. For example, DBSCAN (Density-Based Spatial Clustering of Applications with Noise, density-based noise application spatial clustering), k-means clustering algorithm (k-means clustering algorithm) and so on.

In the obtained cluster analysis result, it is determined that the state of the target vehicle in the first class is normal, and the state of the target vehicle in other classes is determined to be faulty; The class with the most data points, and the other classes are classes other than the first class in the cluster analysis result.

For other classes, one or more classes may be included. Each class represents a different failure type. Then, in practical applications, different numbers or texts can be used to represent different fault types or normal states.

In the embodiment of the present invention, the state of the vehicle can be determined only according to the real-time monitoring data of the vehicle to be monitored. Compared with the prior art, the solution of the embodiment of the present invention can determine the vehicle state in time, thereby improving the safety of the vehicle and reducing the maintenance cost.

On the basis of the above embodiment, in order to further improve the safety of the vehicle, prompt information can also be sent to the target vehicle, and the prompt information includes the second fault type corresponding to the second category, and the second category is other any of the classes. If there is a physical meaning of the second fault type, here, the physical meaning of the second fault type can also be obtained, and the prompt information also includes the physical meaning of the second fault type. The physical meaning refers to the meaning represented by the second fault type. For example, the second fault type can be some symbols, then, its physical meaning can be understood as a text description corresponding to the symbol, etc.

For each fault type, in order to make the maintenance personnel or drivers further understand its development and improve the safety of the vehicle, here, the deterioration index of the third type can also be calculated, and the third type is any one of the other types. Thereby, the change trend of the third type of fault types is estimated. Specifically, the coordinate pair is formed by using the distance between the first data point in the third category and the first category, and the sampling time corresponding to the first data point. Then, a fitting calculation is performed on the coordinate pairs corresponding to all the data points in the third category. Finally, according to the result of the fitting calculation, the deterioration index of the third category is calculated.

As shown in FIG. 2 , it is a system hardware structure diagram of an embodiment of the present invention. In conjunction with Figure 2, the system includes:

The data access devices on the multiple monitored vehicles 201-203 may be connected to the OBD interface or other types of interfaces.

Data storage and analysis computing server 210, which can be a single device, a group of devices, or a virtual computing cloud.

Historical database 211 (optional).

The display device 214 is used to display failure analysis results and real-time monitoring data; it can be applied to automobile companies, insurance companies, institutions, and so on.

Historical database 211 and display device 214 may communicate with server 210 through wired or wireless connection networks 212-213.

The first mobile front end 216, operated by maintenance personnel, may be a mobile terminal installed with an APP of the maintenance personnel.

The second mobile front end 218, used by the driver, may be the driver's APP-installed terminal.

Among them, 207-209, 215, and 217 represent wireless communication networks.

The fault analysis result is transmitted to the maintenance personnel through the wireless network 215, and the maintenance personnel's fault definition is returned to the server 220; the fault analysis result is transmitted to the driver through the wireless network 217, and the driver's definition of the fault is fed back to the server.

FIG. 3 is a flowchart of a method for determining a vehicle state according to an embodiment of the present invention. With reference to FIG. 3 , the method of the embodiment of the present invention includes:

Step 301: Acquire real-time vehicle status data of the vehicle to be monitored.

Obtain real-time vehicle status data through the OBD of the vehicle to be monitored. If there is historical vehicle status data, the historical status data can also be obtained here.

Step 302: Classify the obtained real-time vehicle state data according to the vehicle type to obtain a real-time data set.

Step 303: Calculate the correlation coefficient of each real-time data set.

For each real-time data set, a correlation coefficient between every two data items is calculated to obtain a first correlation coefficient data set.

Step 304: Classify the obtained historical vehicle state data according to the vehicle type to obtain a historical data set.

Step 305: Calculate the correlation coefficient of each historical data set.

For each historical data set, the correlation coefficient between every two data items is calculated to obtain a second correlation coefficient data set.

For the method for calculating the correlation coefficient data set, reference may be made to the description of the foregoing method embodiments.

Step 306 , for each vehicle type, perform cluster analysis based on the correlation coefficient data set.

Here, based on the results of steps 303 and 305, the correlation coefficient dataset for each vehicle type is classified.

According to the cluster analysis results, the class containing the most data points represents the normal vehicle, and other different classes represent different fault types. At the same time, different numbers or texts can be used to represent different fault or normal types.

As shown in Figure 4, it is the result of cluster analysis. Among them, the class represented by 401 indicates that the vehicle is normal, and the classes represented by 402 and 403 indicate that the vehicle is faulty. This figure is only a schematic diagram. In practical applications, the number of features (or the coordinate dimension of the correlation coefficient) may not be 3, and the determined fault types may not be 2.

Step 307: For each fault type, calculate the fault deterioration index.

Each fault type of each model corresponds to a deterioration state calculation process. Here, first calculate the distance between each data point in the same fault class and the normal class, that is, the distance between the data point and the center point or the mean point of the normal class. The larger the distance, the higher the degree of failure. Then, use the distance and the corresponding moment of the data point to form a set of coordinates. Based on all the coordinates in the same fault class, the fitting calculation is performed to obtain a fitting curve. Based on the fitting curve, the deterioration state at a certain future time is calculated as the deterioration index of the fault type at the future time.

As shown in FIG. 5 , a fitting curve 502 is formed by using the coordinates of each data point in a certain fault class (501 in the figure, etc.). Then, according to the trend of the fitting curve, the deterioration state of the fault can be predicted. Among them, the deterioration index refers to the distance between a certain data point in Figure 5 and the center point or the mean point of the normal class at a certain moment.

Step 308 , output the fault analysis result.

In this embodiment of the present invention, the determined fault types and their corresponding physical meanings are distributed to each result display terminal. If the physical meaning of a fault type does not exist, then only the fault type is distributed to each result display terminal.

Here, in order to make the user understand the fault information more completely, the user's feedback on the fault type can be collected, and the physical meaning of a certain fault type, that is, the meaning represented by the fault type, can be defined according to the feedback.

As shown in Figure 6, the following processes may be included:

Output fault analysis results to users, and display them to maintenance personnel or drivers through the display terminal. Afterwards, feedback from maintenance personnel or drivers on fault type results is received. The feedback information corresponding to each type of vehicle and each fault type is counted, and the most frequent feedback information or the most frequent keyword is selected as the physical meaning of the fault type. When any fault type is determined, check whether the physical meaning corresponding to the fault type exists. If it exists, distribute the determined fault type and its physical meaning to each result display terminal. If it does not exist, Then only the identified fault types are distributed to the respective result display terminals.

It can be seen from the above analysis that the embodiments of the present invention can perform remote intelligent fault determination according to the real-time status of multiple vehicles, which can improve the safety of vehicles and reduce maintenance costs.

Referring to FIG. 7, FIG. 7 is a structural diagram of an apparatus for determining a vehicle state provided by an embodiment of the present invention. As shown in FIG. 7, the apparatus for determining a vehicle state includes:

The first acquisition module 701 is configured to acquire monitoring data of the vehicle to be monitored, wherein the monitoring data includes real-time monitoring data of the vehicle to be monitored;

A second obtaining module 702, configured to classify the monitoring data to obtain monitoring data sets of different vehicle types;

A third obtaining module 703, configured to obtain a target correlation coefficient data set according to the target monitoring data set of the target vehicle type for the target vehicle type;

A determination module 704, configured to perform cluster analysis on the target correlation coefficient data set to determine the state of the target vehicle having the target vehicle type.

Optionally, the monitoring data further includes historical monitoring data of the vehicle to be monitored, and the monitoring data set includes a real-time monitoring data set and a historical monitoring data set; as shown in FIG. 8 , the second acquisition module 702 includes : The first acquisition sub-module 7021 is used to classify the real-time monitoring data to obtain real-time monitoring data sets of different vehicle types; the second acquisition sub-module 7022 is used to classify the historical monitoring data to obtain different vehicle types. A historical monitoring dataset of vehicle types.

Optionally, as shown in FIG. 9 , the third acquisition module 703 includes: a calculation sub-module 7031, configured to calculate the correlation coefficient between every two data items for the data items in the target monitoring data set; obtain Sub-module 7032, configured to use the calculated correlation coefficient to form the target correlation coefficient data set.

Optionally, as shown in FIG. 10 , the calculation sub-module 7031 includes: a processing unit 70311 for forming a first matrix by using multiple data items at the same sampling time in the target monitoring data set; a splitting unit 70312 for using is used to split the first matrix into a second matrix and a third matrix; the calculation unit 70313 is used to calculate the product of the second matrix and the first result to obtain a fourth matrix; wherein, in the fourth matrix Each element of , represents a correlation coefficient; the first result is the result of performing a matrix pseudo-inverse operation on the second matrix and the third matrix.

Optionally, as shown in FIG. 11 , the determination module 704 includes: an analysis sub-module 7041 for performing cluster analysis on the target correlation coefficient data set to obtain a cluster analysis result; a determination sub-module 7042 for It is determined that the state of the target vehicle in the first class is normal, and the state of the target vehicle in other classes is determined to be faulty; wherein, the first class is the class that contains the most data points in the cluster analysis result, and the other class A class is a class other than the first class in the cluster analysis result.

Optionally, as shown in FIG. 12 , the apparatus may further include: a prompt module 705, configured to send prompt information to the target vehicle, where the prompt information includes a second fault type corresponding to the second type, the The second category is any of the other categories.

Optionally, as shown in FIG. 13 , the apparatus may further include: a fourth obtaining module 706, configured to obtain the physical meaning of the second fault type, and the prompt information also includes the second fault type physical meaning.

Optionally, as shown in FIG. 14 , the apparatus may further include: a calculation module 707 configured to calculate the deterioration index of the third category, where the third category is any category among other categories.

Optionally, as shown in FIG. 15 , the computing module 707 includes:

The processing sub-module 7071 is used to form a coordinate pair by using the distance between the first data point in the third category and the first category, and the sampling time corresponding to the first data point; the fitting sub-module 7072 is configured with For the coordinate pairs corresponding to all the data points in the third category, perform fitting calculation; the calculation sub-module 7073 is configured to calculate the deterioration index of the third category according to the result of the fitting calculation.

For the working principle of the apparatus in the embodiment of the present invention, reference may be made to the description of the foregoing method embodiment.

In the embodiment of the present invention, the state of the vehicle can be determined only according to the real-time monitoring data of the vehicle to be monitored. Compared with the prior art, the solution of the embodiment of the present invention can determine the vehicle state in time, thereby improving the safety of the vehicle and reducing the maintenance cost.

As shown in FIG. 16 , the device for determining the state of the vehicle according to the embodiment of the present invention includes: a processor 1600, configured to read a program in the memory 1620, and perform the following processes:

acquiring monitoring data of the vehicle to be monitored, wherein the monitoring data includes real-time monitoring data of the vehicle to be monitored;

Classifying the monitoring data to obtain monitoring data sets of different vehicle types;

For the target vehicle type, obtain a target correlation coefficient data set according to the target monitoring data set of the target vehicle type;

Cluster analysis is performed on the target correlation coefficient data set to determine the state of the target vehicle having the target vehicle type.

The transceiver 1610 is used to receive and transmit data under the control of the processor 1600 .

16, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 1600 and various circuits of memory represented by memory 1620 are linked together. The bus architecture may also link together various other circuits, such as peripherals, voltage regulators, and power management circuits, which are well known in the art and, therefore, will not be described further herein. The bus interface provides the interface. Transceiver 1610 may be a number of elements, including a transmitter and a transceiver, that provide a means for communicating with various other devices over a transmission medium. The processor 1600 is responsible for managing the bus architecture and general processing, and the memory 1620 may store data used by the processor 1600 in performing operations.

The processor 1600 is responsible for managing the bus architecture and general processing, and the memory 1620 may store data used by the processor 1600 in performing operations.

The monitoring data also includes historical monitoring data of the vehicle to be monitored, and the monitoring data set includes a real-time monitoring data set and a historical monitoring data set; the processor 1600 is also configured to read the computer program, and perform the following steps:

Classifying the real-time monitoring data to obtain real-time monitoring data sets of different vehicle types; classifying the historical monitoring data to obtain historical monitoring data sets of different vehicle types.

The processor 1600 is also used to read the computer program, and perform the following steps:

For the data items in the target monitoring data set, calculate the correlation coefficient between every two data items;

Using the calculated correlation coefficients, the target correlation coefficient data set is formed.

The processor 1600 is also used to read the computer program, and perform the following steps:

A first matrix is formed by using multiple data items at the same sampling time in the target monitoring data set;

splitting the first matrix into a second matrix and a third matrix;

Calculate the product of the second matrix and the first result to obtain a fourth matrix;

Wherein, each element in the fourth matrix represents a correlation coefficient; the first result is the result of performing a matrix pseudo-inverse operation on the second matrix and the third matrix.

The processor 1600 is also used to read the computer program, and perform the following steps:

Perform cluster analysis on the target correlation coefficient data set to obtain a cluster analysis result;

determining that the state of the target vehicle in the first class is normal, and determining that the state of the target vehicle in other classes is faulty;

The first category is the category that contains the most data points in the cluster analysis result, and the other categories are categories other than the first category in the cluster analysis result.

The processor 1600 is further configured to read the computer program, and perform the following steps: send prompt information to the target vehicle, the prompt information includes a second fault type corresponding to the second type, and the second type is other types any of the categories.

The processor 1600 is also used to read the computer program, and perform the following steps:

The physical meaning of the second fault type is acquired, and the prompt information further includes the physical meaning of the second fault type.

The processor 1600 is also used to read the computer program, and perform the following steps:

Calculate the degradation index of the third class, where the third class is any one of the other classes.

The processor 1600 is also used to read the computer program, and perform the following steps:

Using the distance between the first data point in the third category and the first category, and the sampling time corresponding to the first data point, a coordinate pair is formed;

Perform fitting calculation on the coordinate pairs corresponding to all data points in the third category;

According to the result of the fitting calculation, the deterioration index of the third category is calculated.

In addition, the computer-readable storage medium of the embodiment of the present invention is used to store a computer program, and the computer program can be executed by a processor to implement the following steps:

acquiring monitoring data of the vehicle to be monitored, wherein the monitoring data includes real-time monitoring data of the vehicle to be monitored;

Classifying the monitoring data to obtain monitoring data sets of different vehicle types;

For the target vehicle type, obtain a target correlation coefficient data set according to the target monitoring data set of the target vehicle type;

Cluster analysis is performed on the target correlation coefficient data set to determine the state of the target vehicle having the target vehicle type.

Wherein, the monitoring data further includes historical monitoring data of the vehicle to be monitored, and the monitoring data set includes a real-time monitoring data set and a historical monitoring data set;

The said monitoring data are classified to obtain monitoring data sets of different vehicle types, including:

Classifying the real-time monitoring data to obtain real-time monitoring data sets of different vehicle types;

Classify the historical monitoring data to obtain historical monitoring data sets of different vehicle types.

Wherein, obtaining the target correlation coefficient data set according to the target monitoring data set of the target vehicle type includes:

For the data items in the target monitoring data set, calculate the correlation coefficient between every two data items;

Using the calculated correlation coefficients, the target correlation coefficient data set is formed.

Wherein, for the data items in the target monitoring data set, calculating the correlation coefficient between every two data items, including:

A first matrix is formed by using multiple data items at the same sampling time in the target monitoring data set;

splitting the first matrix into a second matrix and a third matrix;

Calculate the product of the second matrix and the first result to obtain a fourth matrix;

Wherein, each element in the fourth matrix represents a correlation coefficient; the first result is the result of performing a matrix pseudo-inverse operation on the second matrix and the third matrix.

Wherein, performing cluster analysis on the target correlation coefficient data set to determine the state of the target vehicle with the target vehicle type includes:

Perform cluster analysis on the target correlation coefficient data set to obtain a cluster analysis result;

determining that the state of the target vehicle in the first class is normal, and determining that the state of the target vehicle in other classes is faulty;

The first category is the category that contains the most data points in the cluster analysis result, and the other categories are categories other than the first category in the cluster analysis result.

Wherein, after the determining the state of the target vehicle having the target vehicle type, the method further includes:

Sending prompt information to the target vehicle, where the prompt information includes a second fault type corresponding to the second category, and the second category is any one of the other categories.

Wherein, before the sending prompt information to the target vehicle, the method further includes:

The physical meaning of the second fault type is acquired, and the prompt information further includes the physical meaning of the second fault type.

Wherein, after the determining the state of the target vehicle having the target vehicle type, the method further includes:

Wherein, the calculation of the deterioration index of the third category includes:

Using the distance between the first data point in the third category and the first category, and the sampling time corresponding to the first data point, a coordinate pair is formed;

Perform fitting calculation on the coordinate pairs corresponding to all data points in the third category;

According to the result of the fitting calculation, the deterioration index of the third category is calculated.

In the several embodiments provided in this application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included individually, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software functional units.

The above-mentioned integrated units implemented in the form of software functional units can be stored in a computer-readable storage medium. The above software functional unit is stored in a storage medium, and includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute part of the steps of the transceiving method described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM for short), Random Access Memory (RAM for short), magnetic disk or CD, etc. that can store program codes medium.

The above are the preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can be made. It should be regarded as the protection scope of the present invention.

Claims (16)

1. A method for determining the state of a vehicle, comprising: acquiring monitoring data of the vehicle to be monitored, wherein the monitoring data includes real-time monitoring data of the vehicle to be monitored; Classifying the monitoring data to obtain monitoring data sets of different vehicle types; For the target vehicle type, obtain a target correlation coefficient data set according to the target monitoring data set of the target vehicle type; Cluster analysis is performed on the target correlation coefficient data set to determine the state of the target vehicle having the target vehicle type. 2. The method according to claim 1, wherein the monitoring data further comprises historical monitoring data of the vehicle to be monitored, and the monitoring data set comprises a real-time monitoring data set and a historical monitoring data set; The said monitoring data are classified to obtain monitoring data sets of different vehicle types, including: Classifying the real-time monitoring data to obtain real-time monitoring data sets of different vehicle types; Classify the historical monitoring data to obtain historical monitoring data sets of different vehicle types. 3. The method according to claim 1 or 2, wherein the obtaining a target correlation coefficient data set according to the target monitoring data set of the target vehicle type comprises: For the data items in the target monitoring data set, calculate the correlation coefficient between every two data items; Using the calculated correlation coefficients, the target correlation coefficient data set is formed. 4. The method according to claim 3, wherein, for the data items in the target monitoring data set, calculating a correlation coefficient between every two data items, comprising: A first matrix is formed by using multiple data items at the same sampling time in the target monitoring data set; splitting the first matrix into a second matrix and a third matrix; Calculate the product of the second matrix and the first result to obtain a fourth matrix; Wherein, each element in the fourth matrix represents a correlation coefficient; the first result is the result of performing a matrix pseudo-inverse operation on the second matrix and the third matrix. 5. The method according to claim 1, wherein the performing cluster analysis on the target correlation coefficient data set to determine the state of the target vehicle having the target vehicle type comprises: Perform cluster analysis on the target correlation coefficient data set to obtain a cluster analysis result; determining that the state of the target vehicle in the first class is normal, and determining that the state of the target vehicle in other classes is faulty; The first category is the category that contains the most data points in the cluster analysis result, and the other categories are categories other than the first category in the cluster analysis result. 6 . The method of claim 5 , wherein after the determining the state of the target vehicle having the target vehicle type, the method further comprises: 6 . Sending prompt information to the target vehicle, where the prompt information includes a second fault type corresponding to the second category, and the second category is any one of the other categories. 7 . The method according to claim 6 , wherein before the sending prompt information to the target vehicle, the method further comprises: 8 . The physical meaning of the second fault type is acquired, and the prompt information further includes the physical meaning of the second fault type. 8 . The method of claim 5 , wherein after the determining the state of the target vehicle having the target vehicle type, the method further comprises: 8 . Calculate the degradation index of the third class, where the third class is any one of the other classes. 9. The method according to claim 8, wherein the calculating the deterioration index of the third category comprises: Using the distance between the first data point in the third category and the first category, and the sampling time corresponding to the first data point, a coordinate pair is formed; Perform fitting calculation on the coordinate pairs corresponding to all data points in the third category; According to the result of the fitting calculation, the deterioration index of the third category is calculated. 10. A device for determining a state of a vehicle, comprising: a first acquisition module, configured to acquire monitoring data of the vehicle to be monitored, wherein the monitoring data includes real-time monitoring data of the vehicle to be monitored; a second acquisition module, configured to classify the monitoring data to obtain monitoring data sets of different vehicle types; a third obtaining module, configured to obtain a target correlation coefficient data set according to the target monitoring data set of the target vehicle type for the target vehicle type; A determination module, configured to perform cluster analysis on the target correlation coefficient data set to determine the state of the target vehicle with the target vehicle type. 11. The device according to claim 10, wherein the monitoring data further comprises historical monitoring data of the vehicle to be monitored, and the monitoring data set comprises a real-time monitoring data set and a historical monitoring data set; The second acquisition module includes: a first acquisition sub-module for classifying the real-time monitoring data to obtain real-time monitoring data sets of different vehicle types; The second obtaining sub-module is configured to classify the historical monitoring data to obtain historical monitoring data sets of different vehicle types. 12. The apparatus according to claim 10 or 11, wherein the third acquiring module comprises: A calculation submodule for calculating the correlation coefficient between every two data items for the data items in the target monitoring data set; An acquisition sub-module is used to form the target correlation coefficient data set by using the calculated correlation coefficient. 13. The apparatus according to claim 12, wherein the calculation submodule comprises: a processing unit, configured to form a first matrix by using a plurality of data items at the same sampling time in the target monitoring data set; a splitting unit for splitting the first matrix into a second matrix and a third matrix; a calculation unit, configured to calculate the product of the second matrix and the first result to obtain a fourth matrix; Wherein, each element in the fourth matrix represents a correlation coefficient; the first result is a result of performing a matrix pseudo-inverse operation on the second matrix and the third matrix. 14. The apparatus according to claim 10, wherein the determining module comprises: an analysis sub-module for performing cluster analysis on the target correlation coefficient data set to obtain a cluster analysis result; a determining submodule, used for determining that the state of the target vehicle in the first class is normal, and determining that the state of the target vehicle in other classes is faulty; The first category is the category that contains the most data points in the cluster analysis result, and the other categories are categories other than the first category in the cluster analysis result. 15. The apparatus of claim 14, wherein the apparatus further comprises: The calculation module is used to calculate the deterioration index of the third category, where the third category is any category among other categories. 16. The apparatus according to claim 15, wherein the computing module comprises: a processing submodule, configured to form a coordinate pair by using the distance between the first data point in the third category and the first category, and the sampling time corresponding to the first data point; a fitting submodule, used to perform fitting calculation on the coordinate pairs corresponding to all the data points in the third category; The calculation sub-module is configured to calculate the deterioration index of the third category according to the result of the fitting calculation.

Images