Power battery abnormality assessment method, assessment device and computer readable storage medium

Through the power battery abnormality evaluation method, the median normalization value and machine learning algorithm are used to identify the abnormal characteristics of the battery, which solves the safety hazards of short circuit and thermal runaway in the power battery in new energy vehicles, and realizes effective risk assessment and early warning of the power battery , improves security.

CN115635882BActive Publication Date: 2024-11-19SHANGHAI MOTOR VEHICLE INSPECTION CERTIFICATION & TECH INNOVATION CENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211386520.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-07
Publication Date
2024-11-19
Estimated Expiration
2042-11-07

AI Technical Summary

Technical Problem

The performance attenuation and spontaneous combustion of power batteries in new energy vehicles lead to safety hazards. The existing technology is difficult to effectively evaluate the initial abnormal characteristics of short circuit and thermal runaway in power batteries, and there is a lack of effective risk assessment methods and equipment.

Method used

A method of abnormality evaluation of power batteries is proposed, through data acquisition, median normal value calculation, multi-dimensional evaluation parameter establishment, machine learning algorithm training and abnormal risk score, combined with Kalman filtering algorithm and segmented sampling method, the abnormal characteristics of battery are identified And generate an early warning signal.

Benefits of technology

Automatic identification and risk assessment of abnormal characteristics of power batteries is realized, potential faults are locked in advance, and the safety guarantee of new energy vehicles is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115635882B_ABST
    Figure CN115635882B_ABST
Patent Text Reader

Abstract

The present invention relates to a power battery abnormality assessment method, an assessment device and a computer-readable storage medium. The power battery abnormality assessment method comprises S1, data acquisition; S2, obtaining a median normalized value; S3, establishing a multi-dimensional evaluation parameter; S4, calculating an abnormality risk score; S5, abnormality assessment determination, determining whether a single cell has an abnormality based on the abnormality risk score. The present invention proposes a power battery abnormality assessment method, an assessment device and a computer-readable storage medium, which can perform an effective abnormality risk assessment on a power battery and prepare for subsequent early warning work.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power battery testing for new energy vehicles, and in particular to a power battery abnormality evaluation method, an evaluation device, and a computer-readable storage medium. Background Art

[0002] The promotion and use of new energy vehicles will not only help the industry structure to adjust and reduce the consumption of non-renewable resources by traditional vehicles, but also help promote the gradual transformation of my country's energy consumption structure. However, with the increasing number of new energy vehicles in my country, the resulting automobile safety issues such as battery performance degradation and vehicle spontaneous combustion can no longer be ignored. The safety issues caused by short circuits and thermal runaway in the battery are the main causes of power battery failures. If technical means can be used to amplify and lock in advance the initial abnormal characteristics of short circuits and thermal runaway in the power battery, it can give warnings to testers and vehicle drivers in advance to improve safety.

[0003] At the same time, new energy vehicles generate and accumulate a large amount of data during actual use. Deep mining, deep processing, and deep analysis of big data based on the entire life cycle of new energy vehicles are of great significance and can be used to discover and evaluate potential failure risks inside power batteries. With the application and continuous development of big data technology and various algorithm models, how to effectively evaluate the risks of internal short circuits and thermal runaway based on massive data has become an urgent problem to be solved. Summary of the invention

[0004] In view of the above problems in the prior art, the present invention proposes a power battery abnormality assessment method, an assessment device and a computer-readable storage medium, which can effectively perform abnormal risk assessment on the power battery and prepare for subsequent early warning work.

[0005] Specifically, the present invention proposes a method for evaluating abnormality of a power battery, comprising the steps of:

[0006] S1, data acquisition, the power battery includes a plurality of single cells, and operation data of the single cells are acquired;

[0007] S2, obtain the median normalized value, the median normalized value K i,j The calculation formula is:

[0008] K i,j =(V i,j -M i ) / (Vmax i -Vmin i );

[0009] Wherein, the subscript i represents the serial number of the time frame, j represents the serial number of the battery cell; V i,j is the voltage of a single cell in a certain time frame; Mi Vmax is the median value of the voltage of all battery cells of the power battery within the time frame; i 、Vmin i Respectively represent the maximum and minimum values ​​of the voltage of all battery cells in the corresponding time frame;

[0010] S3, establish multi-dimensional evaluation parameters;

[0011] Get the median normalized value K of each battery cell in all time frames i,j The first and last difference K1, the extreme difference K2, and the variance K3 are used as evaluation parameters;

[0012] Use segmented sampling to divide all time frames into n segments, and obtain the median normalized value K corresponding to the last time frame in each segment. i,j The absolute value Ln of n is an integer greater than 3, and the absolute value Ln is used as the evaluation parameter;

[0013] Obtain an evaluation parameter C, which is used to characterize the median normalized value K of the first time frame of a single cell i,j With all its own median normalized value K i,j The difference in arithmetic mean C 1,j ;

[0014] Get the evaluation parameter Count and calculate the median normalized value K of a single battery in a certain time frame i,j With all its own median normalized value K i,j Arithmetic mean The difference C i,j , calculate the difference C of each single battery i,j Greater than the difference C of all single cells 1,j The total number of times the maximum value in Count j ;

[0015] S4, calculating an abnormal risk score, applying a machine learning algorithm to perform model training on the evaluation parameters K1, K2, K3, Ln, the evaluation parameter C, and the evaluation parameter Count, and obtaining an abnormal risk score for each single cell of the power battery;

[0016] S5, abnormality assessment and determination, determining whether the single cell has an abnormality based on the abnormality risk score.

[0017] According to an embodiment of the present invention, in step S1, the operating data of the single cell is obtained under actual operating conditions, test conditions or simulated conditions, and the operating data at least includes the voltage, serial number and corresponding time frame of the single cell.

[0018] According to an embodiment of the present invention, before executing step S2, a cleaning strategy is formulated, and the obtained operating data of the single battery is cleaned using the cleaning strategy.

[0019] According to one embodiment of the present invention, before executing step S3, the obtained median normalized value K i,j Perform Kalman filter algorithm processing.

[0020] According to one embodiment of the present invention, in step S3, all time frames are divided into 5 segments, and the median normalized values ​​K corresponding to 20%, 40%, 60%, 80% and 100% time frames are obtained respectively. i,j The absolute values ​​L1 to L5 are taken as evaluation parameters.

[0021] According to one embodiment of the present invention, in step S3, the difference C 1,j The calculation formula is:

[0022]

[0023] Among them, K 1,j is the median normalized value of the first time frame of a battery cell; is the median normalized value K of the corresponding battery cell in all time frames i,j The arithmetic mean of .

[0024] According to one embodiment of the present invention, the difference C i,j And the total number of Count j The calculation formula is:

[0025]

[0026] Count j =When(C i,j >Max(C 1,j )).

[0027] According to an embodiment of the present invention, in step S5, the single cells are divided into risk levels according to the abnormal risk scores, and different warning signals are set for different risk levels.

[0028] The present invention also provides a power battery abnormality assessment device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned power battery abnormality assessment methods when executing the computer program.

[0029] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the aforementioned power battery abnormality assessment methods are implemented.

[0030] The power battery abnormality assessment method, assessment device and computer-readable storage medium provided by the present invention can automatically identify abnormal characteristics of the power battery, thereby performing effective risk assessment of the power battery abnormality.

[0031] It is to be understood that both the foregoing general description and the following detailed description of the present invention are exemplary and explanatory and are intended to provide further explanation of the invention as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings are included to provide further explanation of the present invention, and are incorporated into and constitute a part of this application. The accompanying drawings illustrate embodiments of the present invention and together with the description serve to explain the principle of the present invention.

[0033] In the attached figure:

[0034] Figure 1 A flowchart of a power battery abnormality assessment method according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0035] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other.

[0036] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present application and its application or use. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0037] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0038] Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments do not limit the scope of the application. Meanwhile, it should be understood that, for ease of description, the sizes of the various parts shown in the accompanying drawings are not drawn according to actual proportional relationships. The technology, methods and equipment known to those of ordinary skill in the relevant art may not be discussed in detail, but in appropriate cases, the technology, methods and equipment should be considered as a part of the specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters represent similar items in the following drawings, and therefore, once a certain item is defined in an accompanying drawing, it does not need to be further discussed in subsequent drawings.

[0039] In the description of the present application, it should be understood that the directions or positional relationships indicated by directional words such as "front, back, up, down, left, right", "lateral, vertical, perpendicular, horizontal" and "top, bottom" are usually based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the device or element referred to must have a specific direction or be constructed and operated in a specific direction, and therefore cannot be understood as limiting the scope of protection of the present application; the directional words "inside and outside" refer to the inside and outside relative to the contours of each component itself.

[0040] In addition, it should be noted that the use of words such as "first" and "second" to define components is only for the convenience of distinguishing the corresponding components. If not otherwise stated, the above words have no special meaning and cannot be understood as limiting the scope of protection of this application. In addition, although the terms used in this application are selected from well-known and commonly used terms, some terms mentioned in the specification of this application may be selected by the applicant at his or her discretion, and their detailed meanings are explained in the relevant parts of the description of this article. In addition, it is required to understand this application not only by the actual terms used, but also by the meaning implied by each term.

[0041] As we all know, new energy vehicles generate and accumulate massive amounts of data during actual use. The information contained in it can be extracted by deep mining. After the relevant features are quantified, they can be used to assess the risks of power battery short circuit and thermal runaway. With the application and continuous development of big data technology and machine learning technology, the feasibility and effectiveness of risk assessment of thermal runaway based on massive data have been greatly improved. Based on big data and algorithm modeling technology, the patent of this invention processes, analyzes and learns massive data under actual testing or operating conditions of new energy vehicle power battery systems, thereby amplifying abnormal features and identifying potential faults as early as possible, promoting the safe use of new energy vehicles.

[0042] Figure 1 A flowchart of a power battery abnormality assessment method according to an embodiment of the present invention is shown. As shown in the figure, a power battery abnormality assessment method provided by the present invention comprises the following steps:

[0043] S1, data acquisition, the power battery includes multiple single cells, and the operating data of the single cells is acquired;

[0044] S2, get the median normalized value, median normalized value K i,j The calculation formula is:

[0045] K i,j =(V i,j -M i ) / (Vmax i -Vmin i );

[0046] Wherein, the subscript i represents the serial number of the time frame, j represents the serial number of the battery cell; V i,j is the voltage of a single cell in a certain time frame; M i Vmax is the median value of the voltage of all battery cells of the power battery within the time frame; i 、Vmin i Respectively represent the maximum and minimum values ​​of the voltage of all battery cells in the corresponding time frame. Median normalized value K i,j It reflects the fluctuation amplitude of the single cell voltage. The purpose of obtaining the median normalized value is to normalize the voltage data of the single cell, further improve the convergence speed, and perform early locking operations for the subsequent amplification of abnormal features.

[0047] S3, establish multi-dimensional evaluation parameters;

[0048] Get the median normalized value K of each battery cell in all time frames i,jThe first and last difference K1, the extreme difference K2, and the variance K3 are used as evaluation parameters. The first and last difference K1, the extreme difference K2, and the variance K3 reflect the fluctuation range of the single battery.

[0049] Use segmented sampling to divide all time frames into n segments, and obtain the median normalized value K corresponding to the last time frame in each segment. i,j The absolute value Ln of n is an integer greater than 3, and the absolute value Ln is used as the evaluation parameter;

[0050] Get the evaluation parameter C, which is used to characterize the median normalized value K of the first time frame of a single cell i,j With all its own median normalized value K i,j The difference in arithmetic mean C 1,j ;

[0051] Get the evaluation parameter Count and calculate the median normalized value K of a single battery in a certain time frame i,j With all its own median normalized value K i,j Arithmetic mean The difference C i,j , calculate the difference C of each single battery i,j Greater than the difference C of all single cells 1,j The total number of times the maximum value in Count j ;

[0052] S4, calculate the abnormal risk score, apply the machine learning algorithm to the evaluation parameters K1, K2, K3, Ln, the evaluation parameter C, and the evaluation parameter Count to perform model training, and obtain the abnormal risk score of each single cell of the power battery. The obtained abnormal risk score is a single parameter, and the abnormal risk score integrates the information contained in all the aforementioned evaluation parameters. It is easy to understand that model training includes establishing a computer learning model, assigning different weights to each evaluation parameter, and the weight can be fine-tuned according to the vehicle model / power battery model. Multiply the value of the evaluation parameter of each battery cell by the weight, and finally get a comprehensive score as the abnormal risk score after summing up.

[0053] S5, abnormality assessment and determination, based on the abnormality risk score, determine whether the single battery has an abnormality. Generally, the higher the abnormality risk score, the greater the probability that the battery single battery has an abnormality.

[0054] Preferably, in step S1, the operating data of the single cell is obtained under actual operating conditions, test conditions or simulated conditions, and the operating data at least includes the voltage, serial number and corresponding time frame of the single cell. It is easy to understand that the operating data may also include data information such as temperature, current, state of charge, battery charge and discharge state reflecting the operating state of the single cell.

[0055] Preferably, before executing step S2, a cleaning strategy is formulated, and the obtained operating data of the single battery is cleaned using the cleaning strategy. Since there may be various abnormal situations in the obtained operating data, such as data dislocation, data jump, data missing, etc., it is necessary to formulate corresponding cleaning strategies for different abnormal data situations.

[0056] Preferably, before executing step S3, the obtained median normalized value K i,j Perform Kalman filter algorithm processing. Since some operating data may be contaminated by noise due to low voltage sampling accuracy and complex working conditions, the optimal filtered value can be obtained by applying the five formulas of Kalman filter for this part of the operating data. i,j Serves as the basis for calculating subsequent evaluation parameters.

[0057] Preferably, in step S3, all time frames are divided into 5 segments, and the median normalized values ​​K corresponding to 20%, 40%, 60%, 80% and 100% time frames are obtained respectively. i,j The absolute values ​​L1 to L5 are used as evaluation parameters. The absolute values ​​L1 to L5 reflect the degree of outliers of the single cell. As an example and not a limitation, all time frames can be divided into 6, 7 or more segments according to actual needs to more accurately reflect the degree of outliers of the single cell. Optionally, all time frames can be segmented in an unequal manner according to actual needs.

[0058] Preferably, in step S3, the difference C 1,j The calculation formula is:

[0059]

[0060] Among them, K 1,j is the median normalized value of the first time frame of a battery cell; is the median normalized value K of the corresponding battery cell in all time frames i,j The evaluation parameter C is a set. If the power battery contains 92 battery cells, then the set contains all the corresponding 92 difference values ​​C. 1,1 ~C 1,92 .

[0061] Preferably, it is characterized in that the difference C i,j And the total number of Count j The calculation formula is:

[0062]

[0063] Countj=When(Ci,j >Max(C 1,j )).

[0064] The evaluation parameter Count is a set. If the power battery includes 92 battery cells, the set includes 92 values.

[0065] Preferably, in step S5, the risk level of the single cells is divided into risk levels according to the abnormal risk score, and different warning signals are set for different risk levels. Specifically, the risk level may include four levels: high, relatively high, medium and low. For the high level, a three-level warning signal is generated and reported; for the relatively high level, a two-level warning signal is generated and reported; for the medium level, a first-level warning signal is generated and reported; and for the low level, no warning signal is generated. In actual operation, the warning signals at each level can be used as safety warning prompts through hardware devices that generate sound and light signals.

[0066] The present invention provides a power battery abnormality assessment method, which obtains a median normalized value reflecting the voltage change of a point battery through operating data, and iteratively calculates multi-dimensional evaluation parameters based on the median normalized value, thereby realizing the amplification and automatic identification of the abnormal characteristics of the single cell. Compared with the original direct fault diagnosis through voltage data changes, the method can provide prediction for the discovery of power battery faults and provide early warning signals.

[0067] The present invention also provides a power battery abnormality assessment device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned power battery abnormality assessment methods when executing the computer program.

[0068] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned power battery abnormality assessment methods are implemented.

[0069] Among them, the specific implementation methods and technical effects of the power battery abnormality assessment device and computer-readable storage medium can be referred to the embodiments of the power battery abnormality assessment method provided by the present invention, and will not be repeated here.

[0070] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. The technician may implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present invention.

[0071] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or executed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in cooperation with a DSP core, or any other such configuration.

[0072] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read and write information from / to the storage medium. In an alternative, a storage medium may be integrated into a processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and the storage medium may reside in a user terminal as discrete components.

[0073] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented as a computer program product in software, each function may be stored on or transmitted by a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, including any medium that facilitates the transfer of a computer program from one place to another. Storage media may be any available medium that can be accessed by a computer. As an example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer. Any connection is also properly referred to as a computer-readable medium. For example, if the software is transmitted from a website, a server, or other remote source using a coaxial cable, a fiber optic cable, a twisted pair, a digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of the medium. Disk and disc as used herein include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, wherein disk often reproduces data magnetically, while disc reproduces data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0074] It will be apparent to those skilled in the art that various modifications and variations may be made to the above exemplary embodiments of the present invention without departing from the spirit and scope of the present invention. Therefore, it is intended that the present invention covers modifications and variations of the present invention that fall within the scope of the appended claims and their equivalent technical solutions.

Claims

1. A method for evaluating abnormality of a power battery, comprising the steps of: S1, data acquisition, the power battery includes a plurality of single cells, and operation data of the single cells are acquired; S2, obtain the median normalized value, the median normalized value K i,j The calculation formula is: K i,j =(V i,j -M i ) / (Vmax i -Vmin i ); in, Subscript i represents the serial number of the time frame, j represents the serial number of the battery cell; V i,j is the voltage of a single cell in a certain time frame; M i Vmax is the median value of the voltage of all battery cells of the power battery within the time frame; i 、Vmin i Respectively represent the maximum and minimum values ​​of the voltage of all battery cells in the corresponding time frame; S3, establish multi-dimensional evaluation parameters; Get the median normalized value K of each battery cell in all time frames i,j The first and last difference K1, the extreme difference K2, and the variance K3 are used as evaluation parameters; Use segmented sampling to divide all time frames into n segments, and obtain the median normalized value K corresponding to the last time frame in each segment. i,j The absolute value Ln of n is an integer greater than 3, and the absolute value Ln is used as the evaluation parameter; Obtain an evaluation parameter C, which is used to characterize the median normalized value K of the first time frame of a single cell i,j With all its own median normalized value K i,j The difference in arithmetic mean C 1,j ; Get the evaluation parameter Count and calculate the median normalized value K of a single battery in a certain time frame i,j With all its own median normalized value K i,j Arithmetic mean The difference C i,j , calculate the difference C of each single battery i,j Greater than the difference C of all single cells 1,j The total number of times the maximum value in Count j ; The difference C 1,j The calculation formula is: Among them, K 1,j is the median normalized value of the first time frame of a battery cell; is the median normalized value K of the corresponding battery cell in all time frames i,j The arithmetic mean of S4, calculating an abnormal risk score, applying a machine learning algorithm to perform model training on the evaluation parameters K1, K2, K3, Ln, the evaluation parameter C, and the evaluation parameter Count, and obtaining an abnormal risk score for each single cell of the power battery; S5, abnormality assessment and determination, determining whether the single cell has an abnormality based on the abnormality risk score.

2. The power battery abnormality assessment method according to claim 1, characterized in that: In step S1, the operating data of the single cell is obtained under actual operating conditions, test conditions or simulated conditions, and the operating data at least includes the voltage, serial number and corresponding time frame of the single cell.

3. The power battery abnormality assessment method according to claim 1, characterized in that: Before executing step S2, a cleaning strategy is formulated, and the obtained operating data of the single battery is cleaned using the cleaning strategy.

4. The power battery abnormality assessment method according to claim 1, characterized in that: Before executing step S3, the median normalized value K is obtained. i,j Perform Kalman filter algorithm processing.

5. The power battery abnormality assessment method according to claim 1, characterized in that: In step S3, all time frames are divided into 5 segments, and the median normalized values ​​K corresponding to the 20%, 40%, 60%, 80% and 100% time frames are obtained respectively. i,j The absolute values ​​L1 to L5 are taken as evaluation parameters.

6. The power battery abnormality assessment method according to claim 1, characterized in that: The difference C i,j And the total number of Count j The calculation formula is: Count j =When(C i,j >Max(C 1,j ))。 7. The power battery abnormality assessment method according to claim 2, characterized in that: In step S5, the single cells are classified into risk levels according to the abnormal risk scores, and different warning signals are set for different risk levels.

8. A power battery abnormality assessment device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the power battery abnormality assessment method as described in any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power battery abnormality assessment method as described in any one of claims 1 to 7 are implemented.