Battery anomaly detection method, device, storage medium, and program product

Abstract

The present application relates to the technical field of battery testing, and provides a battery anomaly detection method, a device, a storage medium, and a program product. The method comprises: acquiring a battery parameter of a battery under test during charging / discharging; performing outlier detection on the basis of the battery parameter to determine whether there is a cell module that has an outlier parameter in said battery; and if there is a cell module that has an outlier parameter, determining the cell module having the outlier parameter as an anomalous cell module. In embodiments of the present application, outlier detection is performed on the basis of the battery parameter, so that by means of balance determination, it is found that there is an anomalous cell module in said battery, thereby improving the accuracy of battery anomaly detection.

Description

Battery anomaly detection methods, equipment, storage media and program products Technical Field

[0001] This application relates to the field of battery testing technology, and more specifically, to a battery anomaly detection method, device, storage medium, and program product. Background Technology

[0002] Currently, most battery anomaly detection methods employ threshold judgment, such as through the Energy Storage Management System (ESMS) module within a Battery Management System (BMS). This involves monitoring and recording the charging and discharging current and voltage of battery cells, modules, clusters, and / or stacks. When the collected data exceeds a preset threshold, the system will trigger an alarm or disable battery charging and discharging functions to handle the anomaly. However, this detection method has a relatively large margin of error. Summary of the Invention

[0003] The purpose of this application is to provide a battery anomaly detection method, device, storage medium, and program product to improve the accuracy of battery anomaly detection.

[0004] In a first aspect, embodiments of this application provide a battery anomaly detection method, including:

[0005] Obtain battery parameters of the battery under test during the charging and discharging process;

[0006] Outlier detection is performed based on battery parameters to determine whether there are any battery cell modules with outlier parameters in the battery under test.

[0007] If there are battery cell modules with outlier parameters, then the battery cell modules with outlier parameters will be identified as abnormal battery cell modules.

[0008] The battery parameters include cell voltage and / or cell temperature; outlier detection is performed based on these parameters to determine whether there are any cell modules with outlier parameters in the battery under test, including:

[0009] Obtain the first battery parameters of each cell in the battery under test at the end of charging, and obtain the second battery parameters of each cell in the battery under test at the end of discharging.

[0010] For each cell, a first outlier result is obtained based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the end of charging; a second outlier result is obtained based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the end of discharging.

[0011] Determine whether a cell is a parameter outlier based on the first outlier result and / or the second outlier result;

[0012] The first outlier result is obtained based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the end of charging, including:

[0013] An outlier detection function is used to perform outlier analysis on the first battery parameters and the first average battery parameters. If the cell parameters are determined to be outliers and the first battery parameter of the cell is greater than the first average battery parameter, then the first outlier result of the battery is determined to be a high-charge outlier. If the cell parameters are determined to be outliers and the first battery parameter of the cell is less than the first average battery parameter, then the first outlier result of the battery is determined to be a low-charge outlier.

[0014] The second outlier result is obtained based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the end of discharge, including:

[0015] Outlier detection functions are used to perform outlier analysis on the second battery parameters and the second average battery parameters. If the cell parameters are determined to be outliers and the second battery parameter of the cell is less than the second average battery parameter, then the first outlier result of the battery is determined to be a low-level outlier. If the cell parameters are determined to be outliers and the second battery parameter of the cell is greater than the second average battery parameter, then the first outlier result of the battery is determined to be a high-level outlier.

[0016] This application embodiment performs outlier detection using first battery parameters at the charging end and second battery parameters at the discharging end. Since the battery parameters at the charging end and the discharging end can reflect the battery performance and health status during the charging and discharging processes, outlier detection using the battery parameters at the charging end and the discharging module can improve the accuracy and reliability of anomaly detection, and help to promptly discover and handle potential battery faults.

[0017] In any embodiment, determining whether a cell is a parameter outlier based on a first outlier result and a second outlier result includes:

[0018] If the first outlier result is a high-level outlier and the second outlier result is a low-level outlier, then the battery is determined to be a cell with outlier parameters.

[0019] In this embodiment of the application, if a certain cell has a voltage and / or battery temperature that is significantly higher than other cells at the end of charging and significantly lower than other cells at the end of discharging, it indicates that the cell is abnormal. Therefore, abnormal cells can be detected more accurately through this feature.

[0020] In any embodiment, determining whether a cell is a parameter outlier based on a first outlier result and a second outlier result includes:

[0021] If the first outlier result is a charge-low outlier and the second outlier result is a discharge-low outlier, then the battery is determined to be a cell with parameter outliers.

[0022] In this embodiment of the application, if a certain cell has a voltage and / or battery temperature that is significantly lower than other cells at the end of charging and at the end of discharging, the voltage and / or battery temperature that is also significantly lower than other cells, then it is determined that the cell may have an abnormality such as insufficient power, and the cell is an abnormal cell.

[0023] In any embodiment, determining whether a cell is a parameter outlier based on a first outlier result and a second outlier result includes:

[0024] If the first outlier result is a low charge outlier or a high charge outlier, and / or the second outlier result is a low release outlier or a high release outlier, then the battery is determined to be a parameter outlier cell.

[0025] In this embodiment of the application, outlier cells can be identified through the first outlier result and / or the second outlier result, and these cells are identified as abnormal cells.

[0026] In any embodiment, battery parameters include battery module voltage and / or battery module temperature; outlier detection is performed based on battery parameters to determine whether there are any battery cell modules with outlier parameters in the battery under test, including:

[0027] Obtain the third battery parameters of each battery module in the battery under test at the charging end, and obtain the fourth battery parameters of each battery module in the battery under test at the discharging end.

[0028] For each battery module, a third outlier result is obtained based on the third battery parameters corresponding to the battery module and the third average battery parameters of the battery under test at the end of charging; a fourth outlier result is obtained based on the fourth battery parameters corresponding to the battery module at the end of discharging and the fourth average battery parameters of the battery under test at the end of discharging.

[0029] If at least one of the third and fourth outlier results represents an outlier in the battery module, then the battery cell module with outlier parameters is identified in the battery under test.

[0030] This application detects outliers in the voltage and / or temperature of battery modules. When the battery parameters of a battery module differ significantly from those of other battery modules, the battery module is identified as an abnormal cell module. Outlier detection can quickly and accurately identify abnormal battery modules.

[0031] In any embodiment, the battery parameters include cell voltage and / or cell temperature; after acquiring the battery parameters of the battery under test during the charging and discharging process, the method further includes:

[0032] Extract battery parameters between adjacent cells in the battery to be tested from the obtained battery parameters;

[0033] Calculate the first degree of difference in battery parameters between adjacent cells;

[0034] If the first difference is greater than the first preset difference threshold, the battery to be tested is determined to be abnormal.

[0035] In this embodiment of the application, under normal circumstances, the battery parameters of adjacent cells will not differ too much. If the difference is large, it indicates that the battery is abnormal. Therefore, the battery is abnormal by calculating the difference in voltage and / or battery temperature between adjacent cells.

[0036] In any embodiment, the battery parameters include battery stack voltage and battery stack current; after acquiring the battery parameters of the battery under test during the charging and discharging process, the method further includes:

[0037] If the battery stack current is less than the preset current threshold, the battery stack voltage shows an increasing trend, the battery stack voltage change rate is less than the preset change rate threshold, and the duration is greater than the preset duration, then the battery stack is determined to be abnormal.

[0038] This application embodiment, by monitoring the battery stack current and voltage, combined with the judgment of time duration, can more accurately detect whether the battery is abnormal.

[0039] In any embodiment, the battery parameters include the state of charge of the battery cluster; after acquiring the battery parameters of the battery under test during the charging and discharging process, the method further includes:

[0040] The second degree of difference is obtained by analyzing the difference in the state of charge of multiple battery clusters within the battery stack.

[0041] If the second difference degree is greater than the second preset difference degree threshold, then the battery cluster is determined to be abnormal.

[0042] This application embodiment analyzes the differences in the state of charge (SOC) of multiple battery clusters within a battery stack, which can quantify the SOC differences between each battery cluster. When the SOC of a certain battery cluster differs significantly from that of other battery clusters, it may mean that the battery cluster has an internal fault or performance degradation. This method of judgment based on the degree of difference is more accurate than judgment based on a single threshold, because the abnormality of the battery cluster may be manifested as a significant deviation in SOC, rather than just an abnormality in absolute value.

[0043] In any embodiment, after identifying a cell module with outlier parameters as an abnormal cell module, the method further includes:

[0044] The battery parameters are input into a pre-trained anomaly analysis model to obtain the cause of the anomaly output by the anomaly analysis model; the anomaly analysis model is generated based on a machine learning model, combined with SHAP theory and the information gain IG evaluation method.

[0045] This application's embodiments utilize machine learning models to obtain anomaly cause information. By training and learning from a large amount of battery parameter data, it can uncover the potential relationship between data features and battery anomalies, thereby achieving more accurate anomaly identification. In battery anomaly analysis scenarios, the SHAP method can help identify which battery parameters have the greatest impact on anomaly judgment, thus providing valuable insights and enhancing the model's transparency and credibility.

[0046] Secondly, embodiments of this application provide a battery anomaly detection device, comprising:

[0047] The parameter acquisition module is used to acquire the battery parameters of the battery under test during the charging and discharging process.

[0048] The detection module is used to perform outlier detection based on battery parameters to determine whether there are any outlier cell modules in the battery under test.

[0049] An anomaly determination module is used to identify battery cell modules with outlier parameters as abnormal battery cell modules.

[0050] Battery parameters include cell voltage and / or cell temperature; the detection module is specifically used for:

[0051] Obtain the first battery parameters of each cell in the battery under test at the end of charging, and obtain the second battery parameters of each cell in the battery under test at the end of discharging.

[0052] For each cell, a first outlier result is obtained based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the end of charging; a second outlier result is obtained based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the end of discharging.

[0053] Determine whether a cell is a parameter outlier based on the first outlier result and / or the second outlier result;

[0054] The first outlier result is obtained based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the end of charging, including:

[0055] An outlier detection function is used to perform outlier analysis on the first battery parameters and the first average battery parameters. If the cell parameters are determined to be outliers and the first battery parameter of the cell is greater than the first average battery parameter, then the first outlier result of the battery is determined to be a high-charge outlier. If the cell parameters are determined to be outliers and the first battery parameter of the cell is less than the first average battery parameter, then the first outlier result of the battery is determined to be a low-charge outlier.

[0056] The second outlier result is obtained based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the end of discharge, including:

[0057] Outlier detection functions are used to perform outlier analysis on the second battery parameters and the second average battery parameters. If the cell parameters are determined to be outliers and the second battery parameter of the cell is less than the second average battery parameter, then the first outlier result of the battery is determined to be a low-level outlier. If the cell parameters are determined to be outliers and the second battery parameter of the cell is greater than the second average battery parameter, then the first outlier result of the battery is determined to be a high-level outlier.

[0058] Thirdly, embodiments of this application provide an electronic device, including: a processor, a memory, and a bus, wherein the processor and the memory communicate with each other through the bus; the memory stores program instructions that can be executed by the processor, and the processor can execute the method of the first aspect by calling the program instructions.

[0059] Fourthly, embodiments of this application provide a non-transitory computer-readable storage medium, comprising:

[0060] The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the method of the first aspect.

[0061] Fifthly, embodiments of this application provide a computer program product, including computer program instructions, which, when read and executed by a processor, perform the method of the first aspect.

[0062] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0063] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 is a schematic flowchart of a battery anomaly detection method provided in an embodiment of this application;

[0065] Figure 2 is a schematic flowchart of another battery anomaly detection method provided in an embodiment of this application;

[0066] Figure 3 is a schematic diagram of a battery anomaly detection device provided in an embodiment of this application;

[0067] Figure 4 is a schematic diagram of the physical structure of the electronic device provided in the embodiment of this application. Detailed Implementation

[0068] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0069] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0070] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0071] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0072] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0073] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0074] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0075] Battery malfunctions refer to abnormal states or performance degradation that occur during battery charging, discharging, or storage. These malfunctions include, but are not limited to, the following:

[0076] Battery overheating: The battery temperature is too high during use or charging, possibly exceeding the normal operating temperature range.

[0077] Battery short circuit: Direct contact occurs between the positive and negative terminals inside the battery, resulting in excessive current, which may cause a fire or explosion.

[0078] Battery swelling or deformation: The battery casing expands or deforms due to increased internal pressure, which may be accompanied by leakage.

[0079] Battery charge drops too quickly: Under normal usage conditions, the battery charge decreases rapidly, far below the expected usage time.

[0080] Unable to charge: The battery cannot receive charging current, or the charging speed is extremely slow and it cannot be fully charged.

[0081] Battery aging: After prolonged use or multiple charge-discharge cycles, the performance of a battery gradually declines and its capacity decreases.

[0082] Battery malfunctions can lead to serious safety accidents such as fires and explosions. Timely anomaly detection allows for the discovery and resolution of problems before such incidents occur, ensuring safer and more stable battery operation. Existing anomaly detection methods set thresholds for key battery parameters, such as temperature, voltage, and current. When a cell's parameters exceed these thresholds, an anomaly is identified. However, this approach is not entirely accurate because the thresholds can be affected by factors such as battery aging and temperature fluctuations, which can cause changes in the thresholds and increase the risk of false positives.

[0083] To address the aforementioned technical problems, embodiments of this application provide a battery anomaly detection method, device, storage medium, and program product. The entity executing this method can be a battery management system or a battery cloud server, etc. If it is a battery cloud server, the server can communicate with the battery to obtain battery parameters during the charging and discharging process.

[0084] Furthermore, the battery can be a power battery or an energy storage battery. One battery structure may include multiple battery stacks, which are connected in series, parallel, or mixed connections. Each battery stack includes multiple battery clusters, which are connected in series, parallel, or mixed connections. Each battery cluster includes multiple battery modules connected in series, parallel, or mixed connections. Each battery module includes multiple cells connected in series, parallel, or mixed connections. Another battery structure may include multiple cells connected in series, parallel, or mixed connections. Yet another battery structure may include multiple battery stacks, each stack including multiple cells. The battery structure can also be other, and this application does not specifically limit it.

[0085] Figure 1 is a schematic flowchart of a battery anomaly detection method provided in an embodiment of this application. As shown in Figure 1, the method includes:

[0086] Step 101: Obtain the battery parameters of the battery under test during the charging and discharging process;

[0087] Step 102: Perform outlier detection based on battery parameters to determine whether there are any battery cell modules with outlier parameters in the battery under test;

[0088] Step 103: If there is a cell module with outlier parameters, then the cell module with outlier parameters is identified as an abnormal cell module.

[0089] In the specific implementation process, battery parameters can be collected by the battery management system from relevant parameters of the battery under test during the charging and discharging processes. These parameters reflect the battery's performance and health status. These battery parameters can be the voltage, current, and temperature of each individual cell within the battery under test, or the voltage, current, and temperature of the battery module, or even the voltage, current, and temperature of the battery cluster. Battery parameters can also include battery capacity, internal resistance, etc. Therefore, the specific parameters included in the battery parameters can be set according to the actual situation. It should be noted that before obtaining the battery parameters, a document configuration parsing template for the charge / discharge raw data can be exported from the host computer. This document configuration parsing template specifies the content included in the battery parameters. Then, the charge / discharge raw data document for the testing period is exported from the host computer, and the battery parameters are retrieved from the charge / discharge raw data document according to the document configuration parsing template.

[0090] When obtaining battery parameters, professional testing equipment can be used, such as battery management systems and data acquisition devices. These devices can accurately measure various parameters of the battery during the charging and discharging process and record them for subsequent analysis.

[0091] Outlier detection is used to identify points in the collected dataset that are significantly different from the majority of data points. After obtaining the battery parameters, preprocessing can be performed, including data cleaning, missing value imputation, and data standardization. This helps improve the accuracy and consistency of the data, laying the foundation for subsequent analysis.

[0092] After obtaining the battery parameters, outlier detection is performed based on these parameters to determine whether any cell modules with outlier parameters exist in the battery under test. It should be noted that a cell module can be a single cell, a battery module composed of multiple cells, or a battery cluster composed of multiple battery modules, etc. A cell module with outlier parameters refers to a cell module whose battery parameters differ significantly from those of other cell modules. Whether a significant difference exists can be determined using outlier detection algorithms, such as simple statistical analysis, the 3σ principle, box plot analysis, or machine learning algorithms. These algorithms analyze the battery parameters to identify outliers that are significantly different from the majority of data points. These outliers may represent cell modules with abnormal performance.

[0093] After outlier detection, if a cell module with outlier parameters is found in the battery, the cell module with outlier parameters is identified as an abnormal cell module.

[0094] It should be noted that if an abnormal cell module is found in the battery under test, the abnormality information will be displayed for staff to review, and it will be determined whether professional personnel are needed to analyze the abnormality details. If professional personnel are needed to analyze the abnormality, an analysis report will be generated by the professionals.

[0095] This application's embodiments identify anomalies through outlier detection, which improves detection accuracy compared to traditional threshold-based methods. For example, in temperature detection, if a normally functioning battery is in a high-temperature environment, the temperature of each cell will be relatively high overall during charging and discharging. If a temperature threshold is used, the battery might be considered abnormal. However, using the outlier detection method of this application, if the overall temperature of the battery cells is high but has not reached the temperature of thermal runaway, it can be considered normal.

[0096] This application's embodiments acquire battery parameters during the charging and discharging process of the battery under test, and perform outlier detection based on these parameters. This enables accurate identification of any battery cell modules with outlier parameters within the battery pack, allowing for appropriate handling measures. This is of great significance for ensuring the performance and safety of the battery pack.

[0097] The battery parameters include cell voltage and / or cell temperature; outlier detection is performed based on these parameters to determine whether there are any cell modules with outlier parameters in the battery under test, including:

[0098] Obtain the first battery parameters of each cell in the battery under test at the end of charging, and obtain the second battery parameters of each cell in the battery under test at the end of discharging.

[0099] For each cell, a first outlier result is obtained based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the end of charging; a second outlier result is obtained based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the end of discharging.

[0100] The battery cell is determined as a parameter outlier based on the first and second outlier results.

[0101] In practical implementation, battery parameters include cell voltage and / or cell temperature. Therefore, battery parameters can include only cell voltage, only cell temperature, or both. The following describes these three scenarios separately:

[0102] (1) Battery parameters only include cell voltage:

[0103] When obtaining the cell voltage of the battery under test, the cell voltage of the battery under test at the charging end (referred to as the first battery parameter in this application embodiment) and the cell voltage of the battery under test at the discharging end (referred to as the second battery parameter in this application embodiment) can be obtained.

[0104] For each cell in the battery under test, outlier detection is performed based on the cell voltage at the charging end of the cell and the average cell voltage at the charging end of the battery under test, to obtain the first outlier result for that cell. The first outlier result is used to characterize whether the cell voltage at the charging end is outlier.

[0105] Similarly, outlier detection is performed based on the cell voltage at the discharge end of the cell and the average cell voltage at the discharge end of the battery under test to obtain a second outlier result for the cell. The second outlier result is used to characterize whether the cell voltage at the discharge end is outlier.

[0106] After obtaining the first outlier result and the second outlier result, it can be determined whether the cell is a parameter outlier cell based on the first outlier result and / or the second outlier result.

[0107] It should be noted that the charging end refers to the stage when the battery is close to fully charged during the charging process. This can be determined by the battery's State of Charge (SOC) and voltage values ​​during charging. For example, when the SOC reaches 95%, it can be considered the charging end. Alternatively, when the battery voltage reaches 3.4V, it can also be considered the charging end. The SOC and voltage values ​​used to determine the charging end can be set according to actual conditions, and this application does not impose specific limitations on them.

[0108] During battery charging, charging continues after reaching the charging end point until the charging is stopped. Therefore, during the process from reaching the charging end point to the charging stop point, the cell voltage can be collected at multiple time points, and the average value can be taken as the cell voltage at the charging end point. Alternatively, the first cell voltage collected after reaching the charging end point can also be used as the cell voltage at the charging end point.

[0109] (2) Battery parameters only include cell temperature:

[0110] When obtaining the cell temperature of the battery under test, the cell temperature of the battery under test at the end of charging (referred to as the first battery parameter in this application embodiment) and the cell temperature of the battery under test at the end of discharging (referred to as the second battery parameter in this application embodiment) can be obtained.

[0111] For each cell in the battery under test, outlier detection is performed based on the cell temperature at the charging end of the cell and the average cell temperature at the charging end of the battery under test, to obtain the first outlier result for that cell. The first outlier result is used to characterize whether the cell temperature at the charging end is outlier.

[0112] Similarly, outlier detection is performed based on the cell temperature at the discharge end of the cell and the average cell temperature at the discharge end of the battery under test to obtain a second outlier result for the cell. The second outlier result is used to characterize whether the cell temperature at the discharge end is outlier.

[0113] After obtaining the first outlier result and the second outlier result, it can be determined whether the cell is a parameter outlier cell based on the first outlier result and / or the second outlier result.

[0114] It should be noted that the charging end refers to the stage when the battery is close to fully charged during the charging process. This can be determined by the battery's State of Charge (SOC) and voltage values ​​during charging. For example, when the SOC reaches 95%, it can be considered the charging end. Alternatively, when the battery voltage reaches 3.4V, it can also be considered the charging end. The SOC and voltage values ​​used to determine the charging end can be set according to actual conditions, and this application does not impose specific limitations on them.

[0115] During battery charging, charging continues after the charging terminus is reached, until the charging terminus is reached. Therefore, during the process from reaching the charging terminus to the charging terminus, the cell temperature can be collected at multiple time points, and the average value can be taken as the cell temperature at the charging terminus. Alternatively, the first cell temperature collected after reaching the charging terminus can also be used as the cell temperature at the charging terminus.

[0116] (3) Battery parameters include cell voltage and cell temperature:

[0117] For battery parameters including cell voltage and cell temperature, the above method can be used to perform outlier detection on cell voltage and cell temperature separately. This allows us to obtain the first and second outlier results for cell voltage, and the first and second outlier results for cell temperature.

[0118] When determining whether a battery cell is an outlier, the first and second outlier results for the cell voltage, as well as the first and second outlier results for the cell temperature, can be considered together. For example, if both the cell voltage and cell temperature are determined to be outliers, then the cell is considered an outlier; alternatively, if either the cell voltage or cell temperature is an outlier, then the cell is considered an outlier. A weighted average method can also be used for outlier determination.

[0119] This application embodiment performs outlier detection using first battery parameters at the charging end and second battery parameters at the discharging end. Since the battery parameters at the charging end and the discharging end can reflect the battery performance and health status during the charging and discharging processes, outlier detection using the battery parameters at the charging end and the discharging module can improve the accuracy and reliability of anomaly detection, and help to promptly discover and handle potential battery faults.

[0120] The first outlier result is obtained based on the first battery parameters corresponding to the battery cell and the first average battery parameters of the battery under test at the end of charging, including:

[0121] An outlier detection function is used to perform outlier analysis on the first battery parameters and the first average battery parameters. If the cell parameters are determined to be outliers and the first battery parameter of the cell is greater than the first average battery parameter, then the first outlier result of the battery is determined to be a high-charge outlier. If the cell parameters are determined to be outliers and the first battery parameter of the cell is less than the first average battery parameter, then the first outlier result of the battery is determined to be a low-charge outlier.

[0122] The second outlier result is obtained based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the end of discharge, including:

[0123] Outlier detection functions are used to perform outlier analysis on the second battery parameters and the second average battery parameters. If the cell parameters are determined to be outliers and the second battery parameter of the cell is less than the second average battery parameter, then the first outlier result of the battery is determined to be a low-level outlier. If the cell parameters are determined to be outliers and the second battery parameter of the cell is greater than the second average battery parameter, then the first outlier result of the battery is determined to be a high-level outlier.

[0124] In the specific implementation process, regarding outlier detection at the end of charging, taking cell voltage as an example, the cell voltage of an outlier cell may be significantly higher or significantly lower than that of other cells. Therefore, the first type of outlier result includes high-charge outliers and low-charge outliers. A high-charge outlier refers to a cell whose battery parameters are significantly higher than most other cells at the end of charging. A low-charge outlier refers to a cell whose battery parameters are significantly lower than most other cells at the end of charging.

[0125] Correspondingly, for outlier detection at the end of battery discharge, the second outlier result can include high-amplitude outliers and low-amplitude outliers. A high-amplitude outlier refers to a cell whose battery parameters are significantly higher than most other cells at the end of discharge. A charging outlier refers to a cell whose battery parameters are significantly lower than most other cells at the end of charging.

[0126] The criteria for determining outliers are as follows: an outlier detection function is used to perform outlier analysis on the first battery parameter and the first average battery parameter. If it is determined that the cell parameter is outlier, and the first battery parameter of the cell is greater than the first average battery parameter.

[0127] The criteria for determining outliers are as follows: an outlier detection function is used to perform outlier analysis on the first battery parameter and the first average battery parameter. If it is determined that the cell parameter is outlier, and the first battery parameter of the cell is less than the first average battery parameter.

[0128] The criteria for determining outliers are as follows: an outlier detection function is used to perform outlier analysis on the second battery parameters and the second average battery parameters. If it is determined that the cell parameters are outliers, and the second battery parameter of the cell is greater than the second average battery parameter.

[0129] The criteria for determining outliers are as follows: an outlier detection function is used to perform outlier analysis on the second battery parameters and the second average battery parameters. If it is determined that the cell parameters are outliers, and the second battery parameter of the cell is less than the second average battery parameter.

[0130] The outlier detection parameters are preset, for example, kab-|X i -ρ|=0. Where k is the scene coefficient, which varies depending on the anomaly detection scenario; this value can be preset. a is a severity constant, also preset according to different anomaly detection scenarios; a larger value indicates stricter detection. b is the outlier value. X i Let be the battery parameters of the i-th cell; ρ be the average parameters of the cell (which can be the first average battery parameter, the second average battery parameter, etc.). Outlier values ​​can be calculated using the above formula, and these outlier values ​​can be used to further determine whether a cell is an outlier.

[0131] In addition, outlier detection parameters can also be based on the 3σ principle. The standard deviation σ is calculated based on the first battery parameter and the first average battery parameter μ. Then, the standard parameter range is determined based on the first average battery parameter and the standard deviation σ, i.e. (μ-3σ, μ+3σ). If the first battery parameter is within the standard parameter range, it means that there is no outlier; otherwise, it means that the battery parameter of the cell is outlier.

[0132] It should be noted that other outlier detection methods can also be used, and this application does not specifically limit them.

[0133] The embodiments of this application use the identification of outliers during high charging, low charging, high discharge, and low discharge to provide a basis for subsequent abnormal detection of battery cell modules.

[0134] Based on the above embodiments, determining whether a cell is a parameter outlier cell according to the first outlier result and the second outlier result includes:

[0135] If the first outlier result is a high-level outlier and the second outlier result is a low-level outlier, then the battery is determined to be a cell with outlier parameters.

[0136] In practice, if a battery cell has a higher voltage and / or temperature than most other cells at the end of charging, but a lower voltage and / or temperature at the end of discharging, it may be due to low cell capacity, mixed cell types, or cell aging. Therefore, this cell is identified as an outlier in terms of parameters.

[0137] In this embodiment of the application, if a certain cell has a voltage and / or battery temperature that is significantly higher than other cells at the end of charging and significantly lower than other cells at the end of discharging, it indicates that the cell is abnormal. Therefore, abnormal cells can be detected more accurately through this feature.

[0138] Based on the above embodiments, determining whether a cell is a parameter outlier cell according to the first outlier result and the second outlier result includes:

[0139] If the first outlier result is a charge-low outlier and the second outlier result is a discharge-low outlier, then the battery is determined to be a cell with parameter outliers.

[0140] In practice, if a battery cell exhibits lower voltage and / or temperature than most other cells at both the charging and discharging ends, it may be due to insufficient charge (excessive self-discharge / internal micro-short circuit), mixed cell types, or aging of the cell. Therefore, this cell is identified as a parameter outlier.

[0141] In this embodiment of the application, if a certain cell has a voltage and / or battery temperature that is significantly lower than other cells at the end of charging and at the end of discharging, the voltage and / or battery temperature that is also significantly lower than other cells, then it is determined that the cell may have an abnormality such as insufficient power, and the cell is an abnormal cell.

[0142] Based on the above embodiments, determining whether a cell is a parameter outlier cell according to the first outlier result and the second outlier result includes:

[0143] If the first outlier result is a low charge outlier or a high charge outlier, and / or the second outlier result is a low release outlier or a high release outlier, then the battery is determined to be a parameter outlier cell.

[0144] In practical implementation, for single-cell outlier detection, a single cell can be identified as outlier if at least one of the following occurs: high-charge outlier, low-charge outlier, high-discharge outlier, and low-discharge outlier. The outlier detection rules are quite strict. For example, using kab-|X... i -ρ|=0. When making the judgment, k can be 1.25, a can be 1.5, or of course, other values.

[0145] In this embodiment of the application, outlier cells can be identified through the first outlier result and / or the second outlier result, and these cells are identified as abnormal cells.

[0146] Based on the above embodiments, battery parameters include battery module voltage and / or battery module temperature; outlier detection is performed based on battery parameters to determine whether there are any battery cell modules with outlier parameters in the battery under test, including:

[0147] Obtain the third battery parameters of each battery module in the battery under test at the charging end, and obtain the fourth battery parameters of each battery module in the battery under test at the discharging end.

[0148] For each battery module, a third outlier result is obtained based on the third battery parameters corresponding to the battery module and the third average battery parameters of the battery under test at the end of charging; a fourth outlier result is obtained based on the fourth battery parameters corresponding to the battery module at the end of discharging and the fourth average battery parameters of the battery under test at the end of discharging.

[0149] If at least one of the third and fourth outlier results represents an outlier in the battery module, then the battery cell module with outlier parameters is identified in the battery under test.

[0150] In practical implementation, anomaly detection within a battery cluster mainly involves lateral comparisons between battery modules. Therefore, battery parameters include battery module voltage and / or battery module temperature. A battery module comprises multiple cells, and the battery module voltage is the average voltage of all cells in the module. The battery module temperature is the average temperature of all cells in the module.

[0151] For a specific battery module, obtain the third battery parameters (battery module voltage and / or battery module temperature) at the end of charging, as well as the third average battery parameters corresponding to the battery cluster to which the battery module belongs at the end of charging. Use the third battery parameters and the third average battery parameters to perform outlier analysis on the battery module, obtaining the third outlier result. This third outlier result can indicate either a high-charge outlier or a low-charge outlier for the battery module.

[0152] Similarly, obtain the fourth battery parameters (battery module voltage and / or battery module temperature) of the battery module at the end of discharge, and the fourth average battery parameters of the battery cluster to which the battery module belongs at the end of discharge. Use the fourth battery parameters and the fourth average battery parameters to perform outlier analysis on the battery module, obtaining the fourth outlier result. This fourth outlier result can indicate whether the battery module is highly or lightly outliered.

[0153] It should be noted that the methods for obtaining the third and fourth outlier results can refer to the methods for obtaining the first and second outlier results in the above embodiments, and this application embodiment does not specifically limit them.

[0154] During battery charging, charging continues after reaching the charging endpoint until the charging cutoff point is reached. Therefore, for each battery module, the battery module voltage can be calculated at multiple time points during the charging process from the charging endpoint to the charging cutoff point, and the average value can be taken as the battery module voltage at the charging endpoint. Alternatively, the first battery module voltage calculated after reaching the charging endpoint can also be used as the battery module voltage at the charging endpoint. The method for obtaining the battery module temperature is similar and will not be elaborated here.

[0155] During battery discharge, once the discharge terminus is reached, the discharge continues until the discharge terminus is reached. Therefore, for each battery module, the battery module voltage can be calculated at multiple time points from the point of discharge terminus to the point of discharge terminus, and the average value can be taken as the battery module voltage at the end of the discharge terminus. Alternatively, the first battery module voltage calculated after reaching the end of the discharge terminus can also be used as the battery module voltage at the end of the discharge terminus. The method for obtaining the battery module temperature is similar and will not be elaborated here.

[0156] This application detects outliers in the voltage and / or temperature of battery modules. When the battery parameters of a battery module differ significantly from those of other battery modules, the battery module is identified as an abnormal cell module. Outlier detection can quickly and accurately identify abnormal battery modules.

[0157] Based on the above embodiments, the battery parameters include cell voltage and / or cell temperature; after obtaining the battery parameters of the battery under test during the charging and discharging process, the method further includes:

[0158] Extract battery parameters between adjacent cells in the battery to be tested from the obtained battery parameters;

[0159] Calculate the first degree of difference in battery parameters between adjacent cells;

[0160] If the first difference is greater than the first preset difference threshold, the battery to be tested is determined to be abnormal.

[0161] In practical implementation, the first degree of difference refers to the degree of difference in battery parameters between adjacent cells. This degree of difference can be calculated by weighing the absolute or relative differences in the battery parameters of adjacent cells. The absolute difference method directly calculates the absolute value of the difference between the parameters of adjacent cells, i.e., First degree of difference = |Battery parameters of cell A - Battery parameters of cell B|. The relative difference method refers to the ratio of the difference between two data points to their average value, usually expressed as a percentage, with the specific formula as follows: Where A represents the battery parameters of cell A, and B represents the battery parameters of cell B.

[0162] The first preset difference threshold is a pre-set value, the specific value of which can be set according to the normal operating range, design rules, and safety standards of the battery under test. It is designed to capture significant differences that may indicate internal abnormalities of the battery. If the first difference is greater than the first preset difference threshold, it indicates that the battery parameters (battery voltage / battery temperature) between two adjacent cells differ significantly, thus confirming that the battery under test is abnormal.

[0163] In this embodiment of the application, under normal circumstances, the battery parameters of adjacent cells will not differ too much. If the difference is large, it indicates that the battery is abnormal. Therefore, the battery is abnormal by calculating the difference in voltage and / or battery temperature between adjacent cells.

[0164] Based on the above embodiments, the battery parameters include battery stack voltage and battery stack current; after obtaining the battery parameters of the battery under test during the charging and discharging process, the method further includes:

[0165] If the battery stack current is less than the preset current threshold, the battery stack voltage shows an increasing trend, the battery stack voltage change rate is less than the preset change rate threshold, and the duration is greater than the preset duration, then the battery stack is determined to be abnormal.

[0166] Based on the above embodiments, a battery stack typically consists of multiple battery cells, which can be of the same or different types. In a series connection, the voltages of the cells are added together to obtain the total voltage of the battery stack; in a parallel connection, the currents of the cells are added together, but ideally, the voltage remains constant. The battery stack current refers to the total current flowing through the battery stack, which is generated by the charging and discharging process of the battery stack composed of multiple cells connected in series or parallel.

[0167] For abnormal scenarios involving prolonged low-current charging, the following conditions can be used to make a judgment based on the obtained battery stack voltage and current:

[0168] (1) Whether the battery stack current is less than the preset current threshold;

[0169] (2) Whether the voltage of the battery stack is increasing;

[0170] (3) Whether the rate of change of battery stack voltage is less than the preset rate of change threshold;

[0171] (4) Whether the duration of the phenomena described in (1)-(3) above is greater than the preset duration.

[0172] If all of (1)-(4) are judged as yes, it indicates that the battery stack is in an abnormal situation of continuous charging with a small current, which may be due to an abnormality in the management logic of the power conversion system (PCS).

[0173] The specific values ​​of the preset current threshold, preset rate of change threshold, and preset duration can be set according to the design requirements.

[0174] This application embodiment, by monitoring the battery stack current and voltage, combined with the judgment of time duration, can more accurately detect whether the battery is abnormal.

[0175] Based on the above embodiments, the battery parameters include the state of charge of the battery cluster; after obtaining the battery parameters of the battery under test during the charging and discharging process, the method further includes:

[0176] The second degree of difference is obtained by analyzing the difference in the state of charge of multiple battery clusters within the battery stack.

[0177] If the second difference degree is greater than the second preset difference degree threshold, then the battery cluster is determined to be abnormal.

[0178] In practical implementation, the state of charge (SOC) of a battery cluster refers to the percentage of its current remaining charge relative to its rated capacity. SOC = (Current charge of battery cluster - Lower limit of battery capacity) / (Upper limit of battery capacity - Lower limit of battery capacity) × 100%.

[0179] After obtaining the state of charge (SOC) of multiple battery clusters within a battery stack, analysis is performed based on the SOC inconsistency between the clusters. Specifically, the analysis focuses on the second degree of SOC difference between any two battery clusters. This second degree of difference can be calculated by subtracting the SOC values ​​of the two clusters. Furthermore, the calculated second degree of difference can be normalized to more intuitively represent the length of the SOC difference between the two clusters. Normalization is achieved by dividing the difference value by a baseline value (such as the rated capacity of the battery cluster or the SOC value at full charge) to obtain a degree of difference index between 0 and 1 (or an adjusted range depending on the specific situation). However, in this scenario, since SOC itself is a percentage value, and the rated capacities of the two battery clusters may be the same or similar, the difference value can be directly used as the degree of difference, or it can be divided by 100 to obtain a more intuitive percentage form.

[0180] After calculating the second difference degree, it can be determined whether the second difference degree is greater than a second preset difference degree threshold. If it is greater, it indicates that there are battery clusters with significant differences in state of charge within the battery stack. This may be due to differences in the degree of cell aging, leading to significant differences between different battery clusters.

[0181] This application embodiment analyzes the differences in the state of charge (SOC) of multiple battery clusters within a battery stack, which can quantify the SOC differences between each battery cluster. When the SOC of a certain battery cluster differs significantly from that of other battery clusters, it may mean that the battery cluster has an internal fault or performance degradation. This method of judgment based on the degree of difference is more accurate than judgment based on a single threshold, because the abnormality of the battery cluster may be manifested as a significant deviation in SOC, rather than just an abnormality in absolute value.

[0182] Based on the above embodiments, after identifying cell modules with outlier parameters as abnormal cell modules, the method further includes:

[0183] The battery parameters are input into a pre-trained anomaly analysis model to obtain the cause of the anomaly output by the anomaly analysis model; the anomaly analysis model is generated based on a machine learning model, combined with SHAP theory and the information gain IG evaluation method.

[0184] In the specific implementation process, the embodiments of this application rely on the machine learning scheme, based on the decision tree machine learning model, and fit the manufacturer outlier function of the corresponding scenario through machine learning. The function is implemented by forming a feature engineering, using SHAP theory combined with the information gain IG evaluation method, extracting and cleaning the original data documents labeled by business, summarizing the scenario performance characteristics of the same manufacturer and the same battery cell cathode material, and extracting and screening the feature subset that has the most influence on battery cell anomaly detection.

[0185] SHAP (SHapley Additive exPlanations) values ​​are a method based on cooperative game theory used to explain the contribution of each feature in a single predicted value. SHAP values ​​can provide a more granular assessment of feature importance and are suitable for complex machine learning models. To analyze the cause of battery failure, this application uses SHAP theory to infer the cause of the failure, providing effective guidance for subsequent battery safety maintenance.

[0186] The formula for calculating the SHAP value is as follows:

[0187] S k This represents the k-th subset, where a subset is selected from all features. i (f,x) represents the SHAP value of the i-th feature on a given model f and input instance x. The SHAP value indicates the marginal contribution to a particular prediction when only the i-th feature is considered. Σ represents the summation over all possible subsets S. k ∈{N / i} means that S is a subset selected from the set of all features [N] that do not contain feature i. N is the set of all features, and {N / i} represents the set of features remaining after removing the i-th feature.

[0188] 2 M-1 Let S represent the total number of all possible subsets S. Since there are M features, and each feature can be either added to or excluded from a subset, the total number of subsets is 2^M. M However, since cases containing feature i are excluded, the actual number of subsets is 2. M-1 S k This represents the number of elements in the k-th subset.

[0189] This part is the weighting factor, representing a value of size S across all possible subsets. k The probability that the k-th subset appears in a set of size M. It is derived from the combinatorial formula in combinatorics.

[0190] f x (S k ∪i) represents the prediction result of model f when only a subset S and the values ​​of feature i exist. In other words, this is the predicted output corresponding to a set of input vectors that only include the features in S and feature i. x (S kf represents the prediction result of model f when only the feature values ​​in a subset S are present. In other words, it is the predicted output corresponding to an input vector consisting only of features from S. x (S k ∪i)-f x (S k The denot represents the amount of change in the prediction result after adding feature i. It reflects the marginal contribution of feature i on subset S.

[0191] Information gain (IG) is an information theory-based method used to measure the reduction in uncertainty of a dataset after introducing a certain feature. The model f can be calculated using information gain, as shown in the following formula:

[0192] IG(Y|X)=H(Y)-H(Y|X)

[0193] Among them, (y i ) is the value of Y. i The probability is given by N, where N is the number of possible values ​​for Y.

[0194] Wherein, P(x i ) is the value of X. i The probability is given by P(Y|x), where M is the number of possible values ​​for X. i ) is in X = x i The probability of Y under given conditions.

[0195] In SHAP theory, f x (S k ∪i)-f x (S k The comparison focuses on the difference between the model output Y containing feature i and the model output Y without feature i. However, this method of judging difference based on distance has limited accuracy. Therefore, this embodiment considers the information gain of models containing and without feature i. Instead of simply using the difference between two output Y values ​​as the basis for judgment, it uses the difference after calculating entropy (information gain) for judgment. Simultaneously, it leverages the advantages of SHAP theory, namely, considering the contribution of feature i relative to each subset to the overall system to evaluate the contribution of that feature, ultimately completing the evaluation of the importance of all features.

[0196] During model training, cross-validation is used to ensure the model's stability on different datasets, while pruning techniques are employed to avoid overfitting.

[0197] Based on the fitting results, the obtained function is used to construct multiple decision tree combinations using the random forest ensemble learning method (to improve robustness).

[0198] Weight is a dictionary of weights for all models, w = {'Model 1': w1, 'Model 2': w2, ..., 'Model N': wn}.

[0199] It should be noted that the data used to train the model consists of battery parameters collected historically for known causes of anomalies.

[0200] Through the above process, an anomaly analysis model can be obtained for anomaly analysis, which can improve the accuracy of anomaly analysis in the embodiments of this application.

[0201] After obtaining the anomaly analysis model, if it is determined through the above embodiments that there is an abnormal cell module in the battery to be tested, the obtained battery parameters are input into the anomaly analysis model, and the anomaly analysis model outputs the cause of the anomaly of the battery to be tested.

[0202] This application's embodiments utilize machine learning models to obtain anomaly cause information. By training and learning from a large amount of battery parameter data, it can uncover the potential relationship between data features and battery anomalies, thereby achieving more accurate anomaly identification. In battery anomaly analysis scenarios, the SHAP method can help identify which battery parameters have the greatest impact on anomaly judgment, thus providing valuable insights and enhancing the model's transparency and credibility.

[0203] Figure 2 is a schematic flowchart of another battery anomaly detection method provided in an embodiment of this application. As shown in Figure 2, the method includes:

[0204] Step 201: Obtain battery parameters; battery parameters can be obtained through a BMS or other battery testing devices. These parameters can include the voltage and temperature of a single cell, the voltage and temperature of a battery module, the state of charge, voltage, and temperature of a battery cluster, or the voltage, current, and temperature of a battery stack.

[0205] Step 202: Obtain battery parameters at the charging end and discharging end; Step 201 can be battery parameters for the entire time period, and this step can extract the battery parameters at the charging end and the discharging end from Step 201.

[0206] Step 203: Data cleaning; clean the obtained battery parameters, such as removing outliers and filling in missing values.

[0207] Step 204: Individual cell voltage outlier analysis; Outlier analysis of individual cell voltages may include outlier analysis of cell voltages at the charging and discharging ends; difference analysis of cell voltages at the charging and discharging ends; and high-charge / low-discharge analysis of cell voltages at the charging and discharging ends. Specific analysis methods can be found in the above embodiments and will not be repeated here. Each analysis method yields a corresponding analysis result, that is, whether the battery under test includes individual cells with outlier parameters. Then, proceed to step 209.

[0208] Step 205: Individual cell temperature outlier analysis; Individual cell temperature outlier analysis may include: outlier analysis of cell temperature at the charging and discharging ends; difference detection of cell temperature at the charging and discharging ends; and high-charge / low-discharge temperature analysis of cell temperature at the charging and discharging ends. Specific analysis methods can be found in the above embodiments and will not be repeated here. Each analysis method yields a corresponding analysis result, that is, whether the battery under test includes individual cells with outlier parameters. Then, proceed to step 209.

[0209] Step 206: Module Outlier Analysis; Module outlier analysis may include: analyzing temperature outliers within the module at the charging and discharging ends, and analyzing voltage outliers within the module at the charging and discharging ends. Specific analysis methods can be found in the above embodiments and will not be repeated here. Each analysis method yields a corresponding analysis result, that is, it can determine whether the battery under test includes a battery module with outlier parameters. Then, proceed to step 209.

[0210] Step 207: Low-current continuous charging analysis; the analysis method for low-current continuous charging can be found in the above embodiments, and will not be repeated here. Then proceed to step 209.

[0211] Step 208: Perform outlier analysis on the SOC of clusters within the stack; determine the degree of difference in SOC between battery clusters within the battery stack, and perform outlier analysis based on the degree of difference.

[0212] Step 209: Record the outlier cell components; since there cannot be more than one abnormal cell, more than one abnormal battery module, or more than one abnormal battery cluster in the battery under test, all abnormal cell modules can be counted.

[0213] Step 210: Record all abnormal cell modules and abnormal scenarios; based on steps 203-206, all abnormal cell modules and the corresponding scenarios can be obtained.

[0214] Step 211: Summarize the error messages and display them on the front-end page.

[0215] This application embodiment can recognize the mainstream host computer original data formats (such as xlsx, db, csv, etc.) in the current market, and can be configured through custom import configuration templates to support the system in recognizing data such as cell voltage and temperature in original files from different manufacturers for diagnostic work.

[0216] Unlike mainstream solutions that rely on BMS systems for simple threshold judgments of battery cells, this solution uses independent equipment to analyze raw charge and discharge data from the power station's host computer. While export file formats, data storage locations, and naming conventions for the same field vary between manufacturers, this solution allows business personnel to customize the system's import value format and thus access raw charge and discharge data from different manufacturers through customizable import templates. Since most mainstream energy storage power station manufacturers can export raw charge and discharge data from their Energy Management Systems (EMS) host computers, this solution supports the analysis of data from mainstream power stations, and its value retrieval scheme is universal.

[0217] This solution can be integrated into an installation package and used on Windows systems. Business personnel can use the integrated software in this solution during factory testing, project implementation, and inspection to test the battery cells anytime, anywhere. The operation steps are simple, and the charging and discharging data can be visualized for abnormal data analysis by business personnel. This solution is easy to use.

[0218] Figure 3 is a schematic diagram of a battery anomaly detection device provided in an embodiment of this application. This device can be a module, program segment, or code on an electronic device. It should be understood that this device corresponds to the method embodiment in Figure 1 above and is capable of executing the various steps involved in the method embodiment in Figure 1. The specific functions of this device can be found in the description above; to avoid repetition, detailed descriptions are appropriately omitted here. The device includes: a parameter acquisition module 301, a detection module 302, and an anomaly determination module 303, wherein:

[0219] The parameter acquisition module 301 is used to acquire the battery parameters of the battery under test during the charging and discharging process;

[0220] The detection module 302 is used to perform outlier detection based on battery parameters to determine whether there are any outlier cell modules in the battery under test.

[0221] The anomaly determination module 303 is used to determine the battery cell module with outlier parameters as an abnormal battery cell module if there is one with outlier parameters.

[0222] The battery parameters include cell voltage and / or cell temperature; the detection module 302 is specifically used for:

[0223] Obtain the first battery parameters of each cell in the battery under test at the charging end, and obtain the second battery parameters of each cell in the battery under test at the discharging end;

[0224] For each battery cell, a first outlier result is obtained based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the end of charging; a second outlier result is obtained based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the end of discharging.

[0225] Determine whether the cell is a parameter outlier based on the first outlier result and / or the second outlier result;

[0226] The detection module 302 is specifically used for:

[0227] An outlier detection function is used to perform outlier analysis on the first battery parameters and the first average battery parameters. If the cell parameters are determined to be outliers and the first battery parameter of the cell is greater than the first average battery parameter, then the first outlier result of the battery is determined to be a high-charge outlier; if the cell parameters are determined to be outliers and the first battery parameter of the cell is less than the first average battery parameter, then the first outlier result of the battery is determined to be a low-charge outlier.

[0228] The step of obtaining the second outlier result based on the second battery parameters corresponding to the battery cell and the second average battery parameters of the battery under test at the end of discharge includes:

[0229] The outlier detection function is used to perform outlier analysis on the second battery parameters and the second average battery parameters. If the cell parameters are determined to be outliers, and the second battery parameter of the cell is less than the second average battery parameter, then the first outlier result of the battery is determined to be a low-level outlier; if the cell parameters are determined to be outliers, and the second battery parameter of the cell is greater than the second average battery parameter, then the first outlier result of the battery is determined to be a high-level outlier.

[0230] Based on the above embodiments, the detection module 302 is specifically used for:

[0231] If the first outlier result is a high-level outlier and the second outlier result is a low-level outlier, then the battery is determined to be a cell with outlier parameters.

[0232] Based on the above embodiments, the detection module 302 is specifically used for:

[0233] If the first outlier result is a low-charge outlier and the second outlier result is a low-release outlier, then the battery is determined to be a parameter outlier cell.

[0234] Based on the above embodiments, the detection module 302 is specifically used for:

[0235] If the first outlier result is a low-charge outlier or a high-charge outlier, or the second outlier result is a low-release outlier or a high-release outlier, then the battery is determined to be a parameter outlier cell.

[0236] Based on the above embodiments, the battery parameters include battery module voltage and / or battery module temperature; the detection module 302 is specifically used for:

[0237] Obtain the third battery parameters of each battery module in the battery under test at the charging end, and obtain the fourth battery parameters of each battery module in the battery under test at the discharging end.

[0238] For each battery module, a third outlier result is obtained based on the third battery parameter corresponding to the battery module and the third average battery parameter of the battery under test at the charging end; a fourth outlier result is obtained based on the fourth battery parameter corresponding to the battery module at the discharging end and the fourth average battery parameter of the battery under test at the discharging end.

[0239] If at least one of the third and fourth outlier results represents an outlier in the battery module, then it is determined that there is a cell module with outlier parameters in the battery under test.

[0240] Based on the above embodiments, the battery parameters include cell voltage and / or cell temperature; the detection module 302 is further used for:

[0241] Extract the battery parameters between adjacent cells in the battery to be tested from the obtained battery parameters;

[0242] Calculate the first degree of difference in battery parameters between adjacent cells;

[0243] If the first difference degree is greater than the first preset difference threshold, then the battery under test is determined to be abnormal.

[0244] Based on the above embodiments, the battery parameters include battery stack voltage and battery stack current; the detection module 302 is also used for:

[0245] If the current of the battery stack is less than a preset current threshold, the voltage of the battery stack shows an increasing trend, the rate of change of the voltage of the battery stack is less than a preset rate of change threshold, and the duration of the voltage change is greater than a preset duration, then the battery stack is determined to be abnormal.

[0246] Based on the above embodiments, the battery parameters include the state of charge of the battery cluster; the detection module 302 is further used for:

[0247] The second degree of difference is obtained by analyzing the difference in the state of charge of multiple battery clusters within the battery stack.

[0248] If the second difference degree is greater than the second preset difference degree threshold, then the battery cluster is determined to be abnormal.

[0249] Based on the above embodiments, the device further includes an anomaly analysis module, used for:

[0250] The battery parameters are input into a pre-trained anomaly analysis model to obtain the cause of the anomaly output by the anomaly analysis model; wherein, the anomaly analysis model is generated based on a machine learning model, combined with SHAP theory and the information gain IG evaluation method.

[0251] Figure 4 is a schematic diagram of the physical structure of the electronic device provided in the embodiment of this application. As shown in Figure 4, the electronic device includes: a processor 401, a memory 402, and a bus 403; wherein, the processor 401 and the memory 402 communicate with each other through the bus 403; the processor 401 is used to call program instructions in the memory 402 to execute the methods provided in the above-described method embodiments, such as: acquiring battery parameters of the battery under test during the charging and discharging process; performing outlier detection based on the battery parameters to determine whether there are any outlier cell modules in the battery under test; if there are outlier cell modules... If a cell module has outlier parameters, it is identified as an abnormal cell module. The battery parameters include cell voltage and / or cell temperature. The outlier detection based on the battery parameters to determine whether there are cell modules with outlier parameters in the battery under test includes: obtaining the first battery parameters of each cell in the battery under test at the charging end, and obtaining the second battery parameters of each cell in the battery under test at the discharging end; for each cell, obtaining a first outlier result based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the charging end; and obtaining the second battery parameters based on the second battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the discharging end. A second outlier result is obtained from two average battery parameters; the cell is determined to be an outlier cell based on the first outlier result and / or the second outlier result; obtaining the first outlier result based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the charging end includes: performing outlier analysis on the first battery parameters and the first average battery parameters using an outlier detection function; if the cell parameters are determined to be outlier, and the first battery parameters of the cell are greater than the first average battery parameters, then the first outlier result of the battery is determined to be a high-charge outlier; if the cell parameters are determined to be outlier, and the first battery parameters of the cell are less than the first average battery parameters, then the first outlier result of the battery is determined to be a high-charge outlier. If the battery parameters are equal, then the first outlier result of the battery is determined to be a low-charge outlier; the step of obtaining the second outlier result based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the discharge end includes: using the outlier detection function to perform outlier analysis on the second battery parameters and the second average battery parameters; if it is determined that the cell parameters are outliers, and the second battery parameters of the cell are less than the second average battery parameters, then the first outlier result of the battery is determined to be a low-discharge outlier; if it is determined that the cell parameters are outliers, and the second battery parameters of the cell are greater than the second average battery parameters, then the first outlier result of the battery is determined to be a high-discharge outlier.

[0252] Processor 401 can be an integrated circuit chip with signal processing capabilities. The processor 401 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor.

[0253] The memory 402 may include, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0254] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by the computer, the computer can execute the methods provided in the above-described method embodiments, such as: acquiring battery parameters of the battery under test during the charging and discharging process; performing outlier detection based on the battery parameters to determine whether there are any outlier cell modules in the battery under test; if there are outlier cell modules, identifying the outlier cell modules as abnormal cell modules; the battery parameters include cell voltage and / or electrical conductivity. Core temperature; the outlier detection based on the battery parameters to determine whether there are outlier cell modules in the battery under test includes: acquiring first battery parameters of each cell in the battery under test at the charging end, and acquiring second battery parameters of each cell in the battery under test at the discharging end; for each cell, obtaining a first outlier result based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the charging end; obtaining a second outlier result based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the discharging end; and obtaining a second outlier result based on the first outlier result and / or The second outlier result determines whether the cell is a parameter outlier; obtaining the first outlier result based on the first battery parameter corresponding to the cell and the first average battery parameter of the battery under test at the charging end includes: performing outlier analysis on the first battery parameter and the first average battery parameter using an outlier detection function; if it is determined that the cell parameter is outlier, and the first battery parameter of the cell is greater than the first average battery parameter, then the first outlier result of the battery is determined to be a high-charge outlier; if it is determined that the cell parameter is outlier, and the first battery parameter of the cell is less than the first average battery parameter, then the battery is determined to be an outlier. The first outlier result is a low-charge outlier; obtaining the second outlier result based on the second battery parameter corresponding to the cell and the second average battery parameter of the battery under test at the discharge end includes: using the outlier detection function to perform outlier analysis on the second battery parameter and the second average battery parameter; if it is determined that the cell parameter is outlier, and the second battery parameter of the cell is less than the second average battery parameter, then the first outlier result of the battery is determined to be a low-charge outlier; if it is determined that the cell parameter is outlier, and the second battery parameter of the cell is greater than the second average battery parameter, then the first outlier result of the battery is determined to be a high-charge outlier.

[0255] This embodiment provides a non-transitory computer-readable storage medium storing computer instructions that cause the computer to execute the methods provided in the above-described method embodiments. For example, the instructions include: acquiring battery parameters of a battery under test during charging and discharging; performing outlier detection based on the battery parameters to determine whether there are any outlier cell modules in the battery under test; if an outlier cell module is found, identifying it as an abnormal cell module; the battery parameters include cell voltage and / or cell temperature; and the outlier detection based on the battery parameters is described in the embodiment. To determine whether there are outlier cell modules in the battery under test, the method includes: acquiring first battery parameters of each cell in the battery under test at the charging end, and acquiring second battery parameters of each cell in the battery under test at the discharging end; for each cell, obtaining a first outlier result based on the first battery parameters corresponding to the cell and the first average battery parameters of the battery under test at the charging end; obtaining a second outlier result based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the discharging end; and determining the cell based on the first outlier result and / or the second outlier result. Whether the cell is an outlier; the step of obtaining the first outlier result based on the first battery parameter corresponding to the cell and the first average battery parameter of the battery under test at the charging end includes: performing outlier analysis on the first battery parameter and the first average battery parameter using an outlier detection function; if it is determined that the cell parameter is outlier, and the first battery parameter of the cell is greater than the first average battery parameter, then the first outlier result of the battery is determined to be a high-charge outlier; if it is determined that the cell parameter is outlier, and the first battery parameter of the cell is less than the first average battery parameter, then the first outlier result of the battery is determined to be... The step of obtaining a second outlier result based on the second battery parameters corresponding to the cell and the second average battery parameters of the battery under test at the discharge end includes: performing outlier analysis on the second battery parameters and the second average battery parameters using the outlier detection function; if it is determined that the cell parameters are outliers and the second battery parameters of the cell are less than the second average battery parameters, then the first outlier result of the battery is determined to be a low-level outlier; if it is determined that the cell parameters are outliers and the second battery parameters of the cell are greater than the second average battery parameters, then the first outlier result of the battery is determined to be a high-level outlier.

[0256] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0257] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0258] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0259] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0260] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A battery abnormality detection method characterized by comprising: The method comprises: obtaining battery parameters of a battery to be detected during charging and discharging; performing outlier detection based on the battery parameters to determine whether there is a parameter outlier battery cell module in the battery to be detected; if there is a parameter outlier battery cell module, determining the parameter outlier battery cell module as an abnormal battery cell module; the battery parameters include cell voltage and / or cell temperature; the outlier detection based on the battery parameters to determine whether there is a parameter outlier battery cell module in the battery to be detected comprises: obtaining first battery parameters of each battery cell in the battery to be detected at the end of charging, and obtaining second battery parameters of each battery cell in the battery to be detected at the end of discharging; for each battery cell, obtaining a first outlier result according to the first battery parameter corresponding to the battery cell and the first average battery parameter of the battery to be detected at the end of charging, and obtaining a second outlier result according to the second battery parameter corresponding to the battery cell and the second average battery parameter of the battery to be detected at the end of discharging; determining whether the battery cell is a parameter outlier battery cell according to the first outlier result and / or the second outlier result; the first outlier result obtained according to the first battery parameter corresponding to the battery cell and the first average battery parameter of the battery to be detected at the end of charging comprises: performing outlier analysis on the first battery parameter and the first average battery parameter by using an outlier detection function, if it is determined that the parameter of the battery cell is an outlier, and the first battery parameter of the battery cell is greater than the first average battery parameter, determining that the first outlier result of the battery is a charging high outlier; if it is determined that the parameter of the battery cell is an outlier, and the first battery parameters of the battery cell are less than the first average battery parameters, determining that the first outlier result of the battery is a charging low outlier; the second outlier result obtained according to the second battery parameter corresponding to the battery cell and the second average battery parameter of the second battery to be detected at the end of discharging comprises: performing outlier analysis on the second battery parameter and the second average battery parameter by using the outlier detection function, if it is determined that the parameter of the battery cell is an outlier, the second battery parameter of the battery cell is less than the second average battery parameter, and the second outlier result of the battery is a discharging low outlier; if it is determined that the parameter of the battery cell is an outlier, and the second battery parameter of the battery cell is greater than the second average battery parameter, determining that the second outlier result of the battery is a discharging high outlier; The outlier detection function is: k a b - | X i - p | = 0; Wherein, k is a scene coefficient, different abnormality detection scenes have different scene coefficients; a is a degree constant, which is also pre-set according to different abnormality detection scenes, the greater the value, the more strict the detection; b is an outlier; X i is a battery parameter of the i th battery cell; and p is the first average battery parameter or the second average battery parameter of the battery cell.

2. The method of claim 1, wherein, determining whether the battery cell is a parameter outlier battery cell according to the first outlier results and / or the second outlier results comprises: if the first outlier result is a charging high outlier, and the second outlier result is a discharging low outlier, determining that the battery cell is a parameter outlier battery cell.

3. The method of claim 1, wherein, determining whether the battery cell is a parameter outlier battery cell according to the first outlier results, and / or the second outlier results comprises: if the first outlier result is a charging low outlier, and the second outlier result is a discharging low outlier, determining that the battery cell as a parameter outlier battery cell.

4. The method of claim 1, wherein, determining whether the battery cell is a parameter outlier battery cell based on the first outlier result and / or the second outlier result comprises: If the first outlier result is a low-level outlier or a high-level outlier, or the second outlier result is a low-level outlier or a high-level outlier, then the cell is determined to be a cell with parameter outliers.

5. The method of claim 1, wherein, The battery parameters include battery module voltage and / or battery module temperature; the outlier detection based on the battery parameters to determine whether there are any outlier cell modules in the battery under test includes: Obtain the third battery parameters of each battery module in the battery under test at the charging end, and obtain the fourth battery parameters of each battery module in the battery under test at the discharging end. For each battery module, a third outlier result is obtained based on the third battery parameter corresponding to the battery module and the third average battery parameter of the battery under test at the charging end; a fourth outlier result is obtained based on the fourth battery parameter corresponding to the battery module at the discharging end and the fourth average battery parameter of the battery under test at the discharging end. If at least one of the third and fourth outlier results represents an outlier in the battery module, then it is determined that there is a cell module with outlier parameters in the battery under test.

6. The method of claim 1, wherein, The battery parameters include cell voltage and / or cell temperature; after acquiring the battery parameters of the battery under test during the charging and discharging process, the method further includes: Extract the battery parameters between adjacent cells in the battery to be tested from the obtained battery parameters; Calculate the first degree of difference in battery parameters between adjacent cells; If the first difference is greater than the first preset difference threshold, then the battery to be detected is determined to be abnormal.

7. The method of claim 1, wherein, The battery parameters include battery stack voltage and battery stack current; after acquiring the battery parameters of the battery under test during the charging and discharging process, the method further includes: If the current of the battery stack is less than a preset current threshold, the voltage of the battery stack shows an increasing trend, the rate of change of the voltage of the battery stack is less than a preset rate of change threshold, and the duration of the voltage change is greater than a preset duration, then the battery stack is determined to be abnormal.

8. The method of claim 1, wherein, The battery parameters include the state of charge of the battery cluster; after acquiring the battery parameters of the battery under test during the charging and discharging process, the method further includes: The second degree of difference is obtained by analyzing the difference in the state of charge of multiple battery clusters within the battery stack. If the second difference degree is greater than the second preset difference degree threshold, then the battery cluster is determined to be abnormal.

9. The method of claim 1, wherein, After identifying the cell module with outlier parameters as an abnormal cell module, the method further includes: The battery parameters are input into a pre-trained anomaly analysis model to obtain the cause of the anomaly output by the anomaly analysis model; wherein, the anomaly analysis model is generated based on a machine learning model, combined with SHAP theory and the information gain IG evaluation method.

10. An electronic device, comprising: include: Processor, memory, and bus, among which, The processor and the memory communicate with each other via the bus; The memory stores program instructions that can be executed by the processor, and the processor can execute the method as described in any one of claims 1-9 by calling the program instructions.

11. A non-transitory computer-readable storage medium, comprising: The non-transitory computer-readable storage medium stores computer instructions that, when executed by a computer, cause the computer to perform the method as described in any one of claims 1-9.

12. A computer program product, characterised in that, It includes computer program instructions, which, when read and executed by a processor, perform the method as described in any one of claims 1-9.

Images