TWI867708B - Battery state prediction system having battery voltage tracking mechanism - Google Patents

Abstract

A battery state prediction system having a battery voltage tracking mechanism is provided. The battery state prediction system determines whether a battery voltage changes linearly with a change in battery health state data when a remaining battery capacity ratio reaches each of a plurality of battery capacity ratios to set a specified lower limit battery capacity ratio and a specified upper limit battery capacity ratio. The battery state prediction system analyzes a change in the battery voltage changing with the change of the battery health state data generated when the remaining battery capacity ratio reaches respectively to the specified lower and upper limit battery capacity ratios to output a tracking rule. The battery state prediction system adjusts a sampled battery voltage range according to the tracking rule, and trains and establishes a predict model based on battery charging time data corresponding to the sampled battery voltage range that is adjusted.

Description

Battery status prediction system with battery voltage tracking mechanism

The present invention relates to a battery status prediction system, and more particularly to a battery status prediction system with a battery voltage tracking mechanism.

Batteries are widely used in all aspects of people's daily lives. Whether it is for new energy vehicles using power batteries or backup power for wireless communication base stations, battery life prediction has become a key factor in the development of various industries. In particular, rapid and accurate prediction of battery health status is the core of safety technology and also a current challenge.

In view of the shortcomings of the prior art, the present invention provides a battery status prediction system with a battery voltage tracking mechanism. The battery status prediction system includes a battery status detection module, a battery data linear analysis module, a data tracking rule analysis module and a prediction model training module. The battery status detection module is configured to detect the battery voltage and battery capacity of the battery after multiple charging and discharging. The battery data linear analysis module is connected to the battery status detection module. The battery data linear analysis module is configured to obtain the battery voltage when the remaining capacity of the battery reaches multiple battery capacity percentages. The battery data linear analysis module is configured to analyze whether the battery voltage changes linearly with the change of the battery health status data when the remaining battery capacity reaches each of the battery capacity ratios, and accordingly select two of the multiple battery capacity ratios as a specified lower limit battery capacity ratio and a specified upper limit battery capacity ratio. The specified upper limit battery capacity ratio is greater than the specified lower limit battery capacity ratio. The data tracking rule analysis module is connected to the battery data linear analysis module. The data tracking rule analysis module is configured to analyze the battery voltage change when the battery health status changes from the previous battery health status data to the next battery health status data when the battery remaining capacity reaches the specified lower limit battery capacity percentage, and to analyze the battery voltage change when the battery health status changes from the previous battery health status data to the next battery health status data when the battery remaining capacity reaches the specified upper limit battery capacity percentage, so as to output a tracking rule. The prediction model training module is connected to the data tracking rule analysis module. The prediction model training module is configured to adjust a sampled battery voltage range according to the tracking rule, collect battery charging time data corresponding to the adjusted battery voltage range to train and establish a prediction model.

The following is an explanation of the implementation of the present invention through specific concrete embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments. The details in this specification can also be modified and changed in various ways based on different viewpoints and applications without departing from the concept of the present invention. In addition, the drawings of the present invention are only for simple schematic illustrations and are not depicted according to actual sizes. Please note in advance. The following implementation will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention. In addition, the term "or" used in this article may include any one or more combinations of the related listed items depending on the actual situation.

Please refer to FIG. 1 , which is a block diagram of a battery status prediction system with a battery voltage tracking mechanism according to a first embodiment of the present invention.

As shown in FIG. 1 , in the first embodiment of the present invention, the battery status prediction system with a battery voltage tracing mechanism of the present invention may include a battery status detection module 20, a battery data linear analysis module 40, a data tracing rule analysis module 50, and a prediction model training module 60.

The battery status detection module 20 is connected to, in contact with or adjacent to the battery to sense data such as the battery voltage and battery capacity after multiple charging and discharging of the battery.

Battery health data is expressed in the following equation: , where SOH is the battery health status data, Qmax refers to the maximum amount of electricity that can be discharged when the battery is fully charged, and Qn is the rated capacity of the battery.

The battery data linear analysis module 40 is connected to the battery status detection module 20 to obtain the battery voltage when the remaining battery capacity reaches each of a plurality of battery capacity ratios (for example but not limited to a plurality of battery capacity ratios including 0% to 100%) from the battery status detection module 20.

The battery data linear analysis module 40 analyzes whether the battery voltage changes linearly with the change of the battery health status data when the remaining battery capacity reaches each of the multiple battery capacity ratios, and accordingly selects two of the multiple battery capacity ratios as a specified lower limit battery capacity ratio and a specified upper limit battery capacity ratio. The specified upper limit battery capacity ratio is greater than the specified lower limit battery capacity ratio.

The data tracking rule analysis module 50 is connected to the battery data linear analysis module 40. The data tracking rule analysis module 50 analyzes the battery voltage change when the battery health status changes from the previous battery health status data to the next battery health status data when the battery remaining capacity reaches a specified lower limit battery capacity ratio, and analyzes the battery voltage change when the battery health status changes from the previous battery health status data to the next battery health status data when the battery remaining capacity reaches a specified upper limit battery capacity ratio, so as to output a tracking rule.

The prediction model training module 60 is connected to the data tracking rule analysis module 50. The prediction model training module 60 adjusts a sampled battery voltage range according to a tracking rule obtained from the data tracking rule analysis module 50, collects battery charging time data corresponding to the adjusted battery voltage range to train and establish a prediction model.

Please refer to FIG. 2 to FIG. 9 , wherein FIG. 2 is a block diagram of a battery status prediction system with a battery voltage tracking mechanism according to a second embodiment of the present invention.

As shown in FIG. 2 , in the second embodiment of the present invention, the battery status prediction system with a battery voltage tracking mechanism of the present invention includes not only a battery status detection module 20, a battery data linear analysis module 40, a data tracking rule analysis module 50 and a prediction model training module 60, but also a battery status curve construction module 70 and a battery status tracking construction module 80.

The battery state curve construction module 70 is connected to the battery state detection module 20 and the battery data linear analysis module 40 . The battery state tracking construction module 80 is connected to the battery data linear analysis module 40 and the data tracking rule analysis module 50 .

The battery status detection module 20 can detect the battery voltage during multiple battery charging processes (e.g., the battery voltage on the horizontal axis of the graphs of FIGS. 3 to 5 ) and the battery capacity per unit battery voltage (e.g., the battery capacity per unit battery voltage on the vertical axis of the graphs of FIGS. 3 to 5 ).

The battery status curve construction module 70 can establish a first battery health status curve CU1 in a curve graph as shown in Figures 3 and 5 based on the previous battery health status data detected by the battery status detection module 20, wherein the horizontal axis data of the curve graph is the battery voltage, and the vertical axis data of the curve graph is the battery capacity per unit battery voltage.

The battery status curve construction module 70 can establish a second battery health status curve CU2 in the curve diagram as shown in FIG. 4 and FIG. 5 according to the next battery health status data detected by the battery status detection module 20.

The battery data linear analysis module 40 obtains the battery voltage when the remaining battery capacity reaches a plurality of battery capacity ratios from the battery status detection module 20, analyzes whether the battery voltage when the remaining battery capacity reaches each battery capacity ratio changes linearly with the change of the battery health status data, and accordingly selects two of the plurality of battery capacity ratios as a specified lower limit battery capacity ratio and a specified upper limit battery capacity ratio, respectively, and the specified upper limit battery capacity ratio is greater than the specified lower limit battery capacity ratio.

The battery status tracing construction module 80 can establish a first lower limit battery data tracing line (for example, but not limited to a first lower limit battery data tracing line SC11 shown in Figures 3 and 5) in the curve graph, perpendicular to the horizontal axis of the curve graph and intersecting with the first battery health status curve CU1, based on the battery voltage when the battery remaining capacity reaches a specified lower limit battery capacity percentage (for example, but not limited to 20% as shown in Figures 3 and 5) and the battery health status reaches the previous battery health status data (for example, but not limited to 99.12% as shown in Figures 3 and 5).

The battery status tracking construction module 80 can establish a first upper limit battery data tracking line (for example, but not limited to a first upper limit battery data tracking line SC12 shown in Figures 3 and 5) in the curve graph, perpendicular to the horizontal axis of the curve graph and interlaced with the first battery health status curve CU1, based on the battery voltage when the remaining battery capacity reaches a specified upper limit battery capacity percentage (for example, but not limited to 60% as shown in Figures 3 and 5) and the battery health status reaches the previous battery health status data (for example, but not limited to 99.12% as shown in Figures 3 and 5).

The battery status tracing construction module 80 can establish a second lower limit battery data tracing line (for example, but not limited to a second lower limit battery data tracing line SC21 shown in Figures 4 and 5) as shown in Figures 4 and 5 based on the battery voltage when the battery remaining capacity reaches a specified lower limit battery capacity ratio (for example, but not limited to 20% as shown in Figures 4 and 5) and the battery health status reaches the next battery health status data (for example, but not limited to 87.29% as shown in Figures 4 and 5). In the curve graph, it is perpendicular to the horizontal axis of the curve graph and interlaced with the second battery health status curve CU2.

The battery status tracking construction module 80 can establish a second upper limit battery data tracking line (for example, but not limited to a second upper limit battery data tracking line SC22 shown in Figures 4 and 5) as shown in Figures 4 and 5 based on the battery voltage when the remaining battery capacity reaches a specified upper limit battery capacity percentage (for example, but not limited to 60% as shown in Figures 4 and 5) and the battery health status reaches the next battery health status data (for example, but not limited to 87.29% as shown in Figures 4 and 5). In the curve graph, it is perpendicular to the horizontal axis of the curve graph and interlaced with the second battery health status curve CU2.

The data tracing rule analysis module 50 can calculate the movement vector from the first lower limit battery data tracing line to the second lower limit battery data tracing line (including the voltage change, for example, the change from the battery voltage of 3.59V aligned on the curve graph by the first lower limit battery data tracing line SC11 to the battery voltage of 3.66V aligned on the curve graph by the second lower limit battery data tracing line SC21 as shown in Figures 5 and 6) as a lower limit battery data tracing coefficient.

The data tracking rule analysis module 50 calculates the movement vector from the first upper limit battery data tracking line to the second upper limit battery data tracking line (including the voltage change, for example, the voltage change from 3.94V of the horizontal axis battery voltage aligned with the first upper limit battery data tracking line SC12 on the curve graph to 3.99V of the horizontal axis battery voltage aligned with the second upper limit battery data tracking line SC22 on the curve graph as shown in Figures 5 and 7) as an upper limit battery data tracking coefficient.

The data tracking rule analysis module 50 outputs a tracking rule to the prediction model training module 60 according to a lower limit battery data tracking coefficient and an upper limit battery data tracking coefficient. The prediction model training module 60 adjusts a sampled battery voltage range according to a tracking rule obtained from the data tracking rule analysis module 50, collects battery charging time data corresponding to the adjusted battery voltage range to train and establish a prediction model.

As shown in FIG9 , compared to the traditional battery status prediction system that adopts a fixed voltage range to predict the battery health status data, the battery status prediction system of the present invention (the first and second embodiments) tracks the battery charging time data corresponding to the battery voltage range to predict the battery health status data, which is closer to the actual data.

In summary, the present invention provides a battery status prediction system with a battery voltage tracking mechanism. The battery status prediction system with a battery voltage tracking mechanism of the present invention tracks a battery voltage range that changes with the battery health status under a specified battery capacity ratio (including a specified lower limit battery capacity ratio and a specified upper limit battery capacity ratio), and establishes a prediction model based on the battery charging time data corresponding to this battery voltage range, which can be used to accurately predict the battery health status data that changes with the battery charging time data after the battery has been charged and discharged for a specified number of times.

The contents disclosed above are only preferred feasible embodiments of the present invention and are not intended to limit the scope of the patent application of the present invention. Therefore, all equivalent technical changes made using the contents of the specification and drawings of the present invention are included in the scope of the patent application of the present invention.

20:Battery status detection module

40: Battery data linear analysis module

50: Data tracking rule analysis module

60: Prediction model training module

70: Battery status curve construction module

80: Battery status tracking module

CU1: First health battery status curve

CU2: Second health battery status curve

SC11: First lower limit battery data trace

SC12: First Limit Battery Data Tracking Line

SC21: Second lower limit battery data trace

SC22: Second upper limit battery data trace

FIG. 1 is a block diagram of a battery state prediction system with a battery voltage tracking mechanism according to a first embodiment of the present invention.

FIG. 2 is a block diagram of a battery state prediction system with a battery voltage tracking mechanism according to a second embodiment of the present invention.

FIG3 is a schematic diagram of a curve and a tracking line constructed when the battery health state reaches the previous battery health state data of the battery state prediction system with a battery voltage tracking mechanism according to the second embodiment of the present invention.

FIG. 4 is a schematic diagram of a curve and a tracking line constructed when the battery health state reaches the next battery health state data of the battery state prediction system with a battery voltage tracking mechanism according to the second embodiment of the present invention.

FIG5 is a schematic diagram of a curve and a tracking line constructed by the battery status prediction system with a battery voltage tracking mechanism according to the second embodiment of the present invention when the battery health status changes from the previous battery health status data to the next battery health status data.

FIG6 is a graph showing the battery voltage changing with the number of cycles when the remaining battery capacity reaches a specified lower limit battery capacity ratio in a battery status prediction system with a battery voltage tracking mechanism according to the second embodiment of the present invention.

FIG. 7 is a graph showing the battery voltage changing with the number of cycles when the remaining battery capacity reaches a specified upper limit battery capacity percentage in a battery status prediction system with a battery voltage tracking mechanism according to the second embodiment of the present invention.

FIG8 is a curve diagram of the battery voltage changing with the battery health status when the battery remaining capacity reaches a specified lower limit battery capacity ratio in the battery status prediction system with a battery voltage tracking mechanism according to the second embodiment of the present invention.

FIG9 is a graph showing the data of the battery health status predicted by the battery status prediction system of the present invention and the traditional battery status prediction system as the battery health status changes with the number of cycles, as well as the actual data.

20: Battery status detection module

40: Battery data linear analysis module

50: Data tracking rule analysis module

60: Prediction model training module

Claims (9)

A battery status prediction system with a battery voltage tracking mechanism comprises: a battery status detection module, configured to detect the battery voltage and battery capacity of the battery after multiple charging and discharging; a battery data linear analysis module, connected to the battery status detection module, configured to obtain the battery voltage when the remaining battery capacity reaches multiple battery capacity ratios, analyze whether the battery voltage when the remaining battery capacity reaches each of the battery capacity ratios changes linearly with the change of battery health status data, and accordingly select two of the multiple battery capacity ratios as a specified lower limit battery capacity ratio and a specified upper limit battery capacity ratio, wherein the specified upper limit battery capacity ratio is greater than the specified lower limit battery capacity ratio; a data tracking rule analysis module A set, connected to the battery data linear analysis module, configured to analyze the battery voltage change when the battery health status changes from the previous battery health status data to the next battery health status data when the battery remaining capacity reaches the specified lower limit battery capacity ratio, and analyze the battery voltage change when the battery health status changes from the previous battery health status data to the next battery health status data when the battery remaining capacity reaches the specified upper limit battery capacity ratio, so as to output a tracking rule; and a prediction model training module, connected to the data tracking rule analysis module, configured to adjust a sampled battery voltage range according to the tracking rule, collect battery charging time data corresponding to the adjusted battery voltage range to train and establish a prediction model. The battery status prediction system with a battery voltage tracking mechanism as described in claim 1 further comprises: a battery status curve construction module connected between the battery status detection module and the battery data linear analysis module, configured to establish a first battery health status curve in a curve graph based on the previous battery health status data detected by the battery status detection module, wherein the horizontal axis data of the curve graph is the battery voltage and the vertical axis data is the battery capacity per unit battery voltage. A battery status prediction system with a battery voltage tracking mechanism as described in claim 2, wherein the battery status curve construction module is configured to establish a second battery health status curve in the curve diagram based on the next battery health status data detected by the battery status detection module. The battery status prediction system with a battery voltage tracking mechanism as described in claim 3 further comprises: a battery status tracking construction module, connected between the battery data linear analysis module and the data tracking rule analysis module, configured to establish a first lower limit battery data tracking line in the curve graph, perpendicular to the horizontal axis of the curve graph and intersecting with the first battery health state curve, according to the battery voltage when the battery remaining capacity reaches the specified lower limit battery capacity ratio and the battery health state reaches the previous battery health state data. A battery status prediction system with a battery voltage tracking mechanism as described in claim 4, wherein the battery status tracking construction module establishes a first upper limit battery data tracking line in the curve graph, perpendicular to the horizontal axis of the curve graph and intersecting with the first battery health state curve, based on the battery voltage when the remaining battery capacity reaches the specified upper limit battery capacity ratio and the battery health state reaches the previous battery health state data. A battery status prediction system with a battery voltage tracking mechanism as described in claim 5, wherein the battery status tracking construction module establishes a second lower limit battery data tracking line in the curve graph, perpendicular to the horizontal axis of the curve graph and interlaced with the second battery health state curve, based on the battery voltage when the remaining battery capacity reaches the specified lower limit battery capacity ratio and the battery health state reaches the next battery health state data. A battery status prediction system with a battery voltage tracking mechanism as described in claim 6, wherein the battery status tracking construction module establishes a second upper limit battery data tracking line in the curve graph, perpendicular to the horizontal axis of the curve graph and intersecting with the second battery health state curve, based on the battery voltage when the remaining battery capacity reaches the specified upper limit battery capacity ratio and the battery health state reaches the next battery health state data. A battery status prediction system with a battery voltage tracking mechanism as described in claim 7, wherein the data tracking rule analysis module calculates the movement vector from the first lower limit battery data tracking line to the second lower limit battery data tracking line as a lower limit battery data tracking coefficient, and the tracking rule output by the data tracking rule analysis module includes the lower limit battery data tracking coefficient. A battery status prediction system with a battery voltage tracking mechanism as described in claim 8, wherein the data tracking rule analysis module calculates the movement vector from the first upper limit battery data tracking line to the second upper limit battery data tracking line as an upper limit battery data tracking coefficient, and the tracking rule output by the data tracking rule analysis module further includes the upper limit battery data tracking coefficient.

Images