CN-122017645-A - Risk assessment method, risk assessment device, risk assessment terminal and storage medium

CN122017645ACN 122017645 ACN122017645 ACN 122017645ACN-122017645-A

Abstract

The application relates to the technical field of battery management and discloses a risk assessment method, a risk assessment device, a risk assessment terminal and a risk assessment storage medium, wherein the risk assessment method comprises the steps of respectively obtaining the health state change quantity of each target battery cell through first charge and discharge operation, and screening out first battery cells with first risk levels from all the target battery cells based on the health state change quantity; the method comprises the steps of obtaining the self-discharge rate increase rate of each second battery cell except the first battery cell in all target battery cells, screening out a third battery cell which is of a first risk level again based on the self-discharge rate increase rate, obtaining multidimensional response parameters of each fourth battery cell except the third battery cell in all second battery cells when the second charge and discharge operation is carried out, and obtaining the risk level of each fourth battery cell by combining a risk assessment model. The application can realize nondestructive and accurate security risk grading evaluation of the battery after slight thermal abuse.

Inventors

SUN ZHENYU
MA XIAN
XU ZHONGLING
LIANG CHANGQING
DUAN PINGHUI
YU WENJUN

Assignees

欣旺达动力科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260129

Claims (12)

1. A risk assessment method for assessing the risk of a battery cell, the method comprising: The method comprises the steps of respectively obtaining the health state variable quantity of each target battery cell through first charge and discharge operation, and screening out first battery cells with a first risk level from all the target battery cells based on the health state variable quantity, wherein the target battery cells are battery cells except for valve-opening battery cells; Acquiring the self-discharge rate increase rate of each second battery cell except the first battery cell in all the target battery cells, and screening out a third battery cell which is the first risk level again based on the self-discharge rate increase rate; And acquiring multidimensional response parameters of all fourth battery cells except the third battery cell in the second battery cell when the second charge and discharge operation is executed, and combining a risk assessment model to obtain the risk grade of each fourth battery cell, wherein the risk of the first risk grade is highest.
2. The risk assessment method according to claim 1, wherein the acquiring the state of health variation of each target battery cell through the first charge-discharge operation, and screening the first battery cell of the first risk level from all the target battery cells based on the state of health variation, includes: Respectively executing first charge and discharge operations on each target battery cell so as to respectively determine the change amount of the health state corresponding to each target battery cell according to the change of the capacity of each target battery cell after the first charge and discharge operations; And taking the target battery cell with the health state variation larger than or equal to a first judgment threshold value as the first battery cell of the first risk level.
3. The risk assessment method according to claim 2, wherein before the first charge and discharge operations are performed on the respective target battery cells, further comprising obtaining an initial nominal capacity of the respective target battery cells; The step of respectively executing a first charge and discharge operation on each target battery cell to determine the corresponding change amount of the health state according to the capacity change of each target battery cell after the first charge and discharge operation includes: Respectively executing the first charge and discharge operation for each target battery cell at least twice, and obtaining an average battery cell capacity according to the battery cell capacity after each first charge and discharge operation; And acquiring a battery cell health state based on the initial nominal capacity and the average battery cell capacity of the target battery cell, and determining the health state change amount according to the battery cell health state.
4. The risk assessment method according to claim 1, wherein the acquiring the self-discharge rate increase rate of each of the second battery cells other than the first battery cell among all the target battery cells, and the re-screening the third battery cell that is the first risk level based on the self-discharge rate increase rate, comprises: Performing a second charge-discharge operation and a standing operation on each second battery cell to obtain the self-discharge rate increase rate of the self-discharge rate of each second battery cell relative to the initial self-discharge rate; And taking the battery cell with the self-discharge rate increase rate being greater than or equal to a second judgment threshold as the third battery cell of the first risk level.
5. The risk assessment method according to claim 4, wherein the obtaining the self-discharge rate increase rate of the self-discharge rate of each of the second battery cells relative to an initial self-discharge rate includes: Obtaining the standing voltage of each second battery cell at the starting time and the ending time within a preset time before the standing operation is ended, and calculating the self-discharge rate of each second battery cell based on the obtained standing voltage at the starting time and the obtained standing voltage at the ending time; And determining the self-discharge rate increase rate of each second battery cell based on the current self-discharge rate of each second battery cell, the initial self-discharge rate when leaving the factory and an adjustment coefficient.
6. The risk assessment method according to claim 4, wherein the charging operation in the second charging and discharging operation is a constant-current constant-voltage charging operation, the constant-current constant-voltage charging operation including a constant-current charging stage and a constant-voltage charging stage; The step of obtaining multidimensional response parameters of each fourth battery cell except the third battery cell in all the second battery cells when the second charge and discharge operation is executed, and combining a risk assessment model to obtain risk levels of each fourth battery cell, including: Extracting a voltage standard deviation of each fourth battery cell in the constant-current charging stage, a duration of the constant-voltage charging stage, a temperature change characteristic in the charging operation of the second charging and discharging operation, and a voltage change amount obtained after the standing operation as the multidimensional response parameters; inputting the multidimensional response parameters into the risk assessment model to obtain risk scores of the fourth battery cells; And performing risk ranking on each fourth battery cell based on the risk scores, and determining the risk level of each fourth battery cell based on ranking results, wherein the risk level of each fourth battery cell comprises a second risk level and a third risk level, and the risk of the second risk level is higher than that of the third risk level.
7. The risk assessment method according to claim 6, wherein the constructing of the risk assessment model includes: Acquiring a plurality of training sample battery monomers with known risk states, executing the second charge-discharge operation, and acquiring the corresponding multidimensional response parameters as input features, wherein the known risk states are used as classification labels; Modeling a training data set formed by the input features and the classification labels by adopting a random forest algorithm, and screening the input features with importance scores higher than a preset importance threshold value as key features by an arrangement importance method; And normalizing the importance scores of the key features to obtain weight coefficients corresponding to the key features in the risk scores so as to obtain a risk assessment model consisting of the key features and the corresponding weight coefficients.
8. The risk assessment method according to claim 1, wherein the target battery cell is a battery cell that extends outward from the valve-opening battery cell within a preset threshold range.
9. The risk assessment method according to claim 5, wherein the adjustment coefficient is dynamically adjusted according to the cumulative number of cycles, the degree of capacity fade, and the ambient temperature of each of the second battery cells.
10. A risk assessment apparatus for assessing the risk of a battery cell, the apparatus comprising: The primary screening module is used for respectively acquiring the health state variable quantity of each target battery cell through first charge and discharge operation, and screening out first battery cells with a first risk level from all the target battery cells based on the health state variable quantity, wherein the target battery cells are battery cells except for valve-opening battery cells; The re-screening module is used for acquiring the self-discharge rate increase rate of each second battery cell except the first battery cell in all the target battery cells, and screening out a third battery cell which is the first risk level again based on the self-discharge rate increase rate; the risk determination module is used for obtaining multidimensional response parameters of all fourth battery cells except the third battery cell in the second battery cell when the second charge and discharge operation is executed, and combining a risk assessment model to obtain the risk grade of each fourth battery cell, wherein the risk of the first risk grade is highest.
11. A terminal device, characterized in that it comprises a processor and a memory, the memory storing a computer program, the processor being adapted to execute the computer program to implement the risk assessment method of any one of claims 1-9.
12. A computer-readable storage medium, characterized in that it stores a computer program which, when executed on a processor, implements the risk assessment method according to any one of claims 1-9.

Description

Risk assessment method, risk assessment device, risk assessment terminal and storage medium Technical Field The present application relates to the field of battery management technologies, and in particular, to a risk assessment method, a risk assessment device, a risk assessment terminal, and a risk assessment storage medium. Background With the rapid development of new energy automobiles and energy storage systems, lithium ion batteries have become the mainstream energy storage devices because of their advantages of high energy density, long cycle life, light weight, and the like. However, during use of the battery, slight thermal abuse events such as valve opening, micro-shorting, etc. may occur due to overcharging, shorting, mechanical damage, or localized heat accumulation, etc. Such events, although not causing severe thermal runaway, may lead to irreversible electrochemical degradation inside the individual cells, thereby affecting the safety and reliability of the overall module. In the prior art, the evaluation of the safety state of the battery is mostly dependent on-line monitoring parameters such as voltage, temperature, internal resistance and the like in the running process, or a health state model is established based on historical charge and discharge data to conduct trend prediction. However, when a battery is subjected to slight thermal abuse, macroscopic performance parameters such as capacity and voltage curves may not change significantly, making it difficult for conventional methods to identify potential risks in time. Disclosure of Invention In view of the above, the embodiments of the present application provide a risk assessment method, apparatus, terminal and storage medium, so as to implement lossless and accurate security risk classification assessment on a battery after the battery is subjected to slight thermal abuse. In a first aspect, an embodiment of the present application provides a risk assessment method for assessing a battery cell, the method including: The method comprises the steps of respectively obtaining the health state variable quantity of each target battery cell through first charge and discharge operation, and screening out first battery cells with a first risk level from all the target battery cells based on the health state variable quantity, wherein the target battery cells are battery cells except for valve-opening battery cells; Acquiring the self-discharge rate increase rate of each second battery cell except the first battery cell in all the target battery cells, and screening out a third battery cell which is the first risk level again based on the self-discharge rate increase rate; And acquiring multidimensional response parameters of all fourth battery cells except the third battery cell in the second battery cell when the second charge and discharge operation is executed, and combining a risk assessment model to obtain the risk grade of each fourth battery cell, wherein the risk of the first risk grade is highest. In an optional embodiment, the obtaining, through a first charge-discharge operation, a change amount of a health state of each target battery cell, and screening the first battery cell that is the first risk level from all the target battery cells based on the change amount of the health state, includes: Respectively executing first charge and discharge operations on each target battery cell so as to respectively determine the change amount of the health state corresponding to each target battery cell according to the change of the capacity of each target battery cell after the first charge and discharge operations; And taking the target battery cell with the health state variation larger than or equal to a first judgment threshold value as the first battery cell of the first risk level. In an alternative embodiment, before the first charge and discharge operations are performed on the target battery cells, the method further includes obtaining an initial nominal capacity of each target battery cell; The step of performing the first charge and discharge operation on each of the target battery cells to determine the corresponding change amount of the health state according to the change in capacity of each of the target battery cells after the first charge and discharge operation, includes: Respectively executing the first charge and discharge operation for each target battery cell at least twice, and obtaining an average battery cell capacity according to the battery cell capacity after each first charge and discharge operation; And acquiring a battery cell health state based on the initial nominal capacity and the average battery cell capacity of the target battery cell, and determining the health state change amount according to the battery cell health state. In an optional embodiment, the obtaining the self-discharge rate increase rate of each of the second battery cells except the first battery cell in all the target battery cells, an