Battery failure analysis method, apparatus, readable storage medium, and electronic device

Abstract

The present application belongs to the technical field of batteries, and particularly relates to a battery failure analysis method, an apparatus, a computer-readable storage medium and an electronic device. The method comprises: acquiring a battery failure case to be analyzed; on the basis of a preset battery failure case library and a preset battery failure fault tree, analyzing the battery failure case to obtain a battery failure factor set; and, according to the battery failure factor set, determining a battery failure analysis result. The present application can perform a comprehensive analysis on battery failure cases by taking into account a battery failure case library and a battery failure fault tree, so that more comprehensive battery failure factor sets can be obtained by means of the analysis, thereby effectively improving the accuracy of final results of the battery failure analysis.

Description

Battery failure analysis method, device, readable storage medium and electronic device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on November 27, 2023, with application number 202311597778.0 and application name “A battery failure analysis method, device, readable storage medium and electronic device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application belongs to the field of battery technology, and in particular relates to a battery failure analysis method, device, computer-readable storage medium, and electronic device. Background Art

[0003] With the rapid adoption of renewable energy and electric vehicles, demand for batteries such as lithium-ion batteries is growing dramatically. However, due to the complex manufacturing processes and physical and chemical reactions involved in their production, battery failure issues (such as lithium plating) have been a major factor limiting their performance and reliability.

[0004] Existing battery failure analysis methods rely on extensive production experience, combined with physical and chemical experiments, to identify and solve problems. Although useful analysis results can sometimes be obtained, the overall analysis is incomplete and the accuracy of the analysis results is low, making it unable to meet the challenges of large-scale production. Technical issues

[0005] In view of this, embodiments of the present application provide a battery failure analysis method, apparatus, computer-readable storage medium, and electronic device to address the problem of low accuracy of analysis results in existing battery failure analysis methods. Technical Solutions

[0006] A first aspect of an embodiment of the present application provides a battery failure analysis method, which may include:

[0007] Obtain battery failure cases to be analyzed;

[0008] Analyze battery failure cases based on a preset battery failure case library and a preset battery failure fault tree to obtain a battery failure factor set;

[0009] The battery failure analysis results are determined based on the battery failure factor set.

[0010] Through the above scheme, the battery failure case library and the battery failure fault tree can be combined to conduct a comprehensive analysis of the battery failure cases, so as to obtain a more comprehensive set of battery failure factors, effectively improving the accuracy of the final battery failure analysis results.

[0011] In a specific implementation of the first aspect, battery failure cases are analyzed based on a preset battery failure case library and a preset battery failure fault tree to obtain a battery failure factor set, which may include:

[0012] Analyze battery failure cases based on the battery failure case library to obtain a set of case library failure factors;

[0013] Analyze battery failure cases based on the battery failure fault tree and obtain the fault tree failure factor set;

[0014] The battery failure factor set is determined based on the case library failure factor set and the fault tree failure factor set.

[0015] Through the above scheme, a case library failure factor set can be obtained based on the analysis of the battery failure case library, and a fault tree failure factor set can be obtained based on the analysis of the battery failure fault tree. By comprehensively considering the two, a more comprehensive battery failure factor set can be obtained.

[0016] In a specific implementation of the first aspect, analyzing battery failure cases based on a battery failure case library to obtain a case library failure factor set may include:

[0017] Calculate the case similarity between the battery failure case and each historical case in the battery failure case database;

[0018] Selecting historical cases whose case similarity is greater than a preset similarity threshold from the battery failure case database as similar cases of the battery failure case;

[0019] Determine the failure factor set of the case library based on similar cases.

[0020] Through the above scheme, similar cases can be selected from the battery failure case library. The similarity between these similar cases and the battery failure cases is relatively large. The case library failure factor set determined based on these similar cases has a good reference significance for battery failure cases.

[0021] In a specific implementation of the first aspect, respectively calculating the case similarity between the battery failure case and each historical case in the battery failure case library may include:

[0022] Extract the first case features of battery failure cases;

[0023] Extracting the second case feature from the target historical case; wherein the target historical case is any historical case in the battery failure case library;

[0024] The case similarity between the battery failure case and the target historical case is calculated based on the first case feature and the second case feature.

[0025] In a specific implementation of the first aspect, calculating the case similarity between the battery failure case and the target historical case based on the first case feature and the second case feature may include:

[0026] Calculate the case feature distance between the first case feature and the second case feature;

[0027] The case similarity between the battery failure case and the target historical case is determined based on the case feature distance.

[0028] Through the above scheme, the similarity between cases is characterized by calculating the distance between case features, which can achieve an accurate measurement of case similarity.

[0029] In a specific implementation of the first aspect, calculating the case feature distance between the first case feature and the second case feature may include:

[0030] Calculate the sub-feature distances between the corresponding sub-features of the first case feature and the second case feature respectively;

[0031] The case feature distance is obtained by weighted summing up the sub-feature distances according to the preset sub-feature weights.

[0032] Through the above scheme, corresponding weights can be assigned to each sub-feature according to actual conditions, thereby strengthening more important sub-features and weakening unimportant sub-features, thereby improving the accuracy of the final result.

[0033] In a specific implementation of the first aspect, determining the case library failure factor set based on similar cases may include:

[0034] Obtain the root causes of failures in similar cases;

[0035] The root causes of failure are summarized to obtain the set of failure factors in the case library.

[0036] In a specific implementation of the first aspect, a battery failure case is analyzed based on a battery failure fault tree to obtain a set of fault tree failure factors, which may include:

[0037] Extract failure modes from battery failure cases;

[0038] Determine the target branch corresponding to the failure mode in the battery failure fault tree;

[0039] A fault tree analysis is performed on the battery failure case based on the target branch to obtain a set of fault tree failure factors.

[0040] Through the above scheme, the corresponding target branch can be determined in the battery failure fault tree according to the failure mode, and the fault tree analysis can be performed based on the target branch, which is more targeted, narrows the analysis scope, and improves the analysis efficiency.

[0041] In a specific implementation of the first aspect, determining the battery failure factor set based on the case library failure factor set and the fault tree failure factor set may include:

[0042] The case library failure factor set and the fault tree offline factor set are combined to obtain an offline factor set; wherein the fault tree offline factor set is the offline factor set in the fault tree failure factor set;

[0043] The offline factor set and the fault tree online factor set are combined to obtain a battery failure factor set; wherein the fault tree online factor set is an online factor set in the fault tree failure factor set.

[0044] In a specific implementation of the first aspect, determining a battery failure analysis result according to a battery failure factor set may include:

[0045] Construct a data table of battery failure cases according to the battery failure factor set;

[0046] Build a machine learning model based on the data table to obtain the constructed target model;

[0047] Determine the importance ranking of data features in the data table based on the target model;

[0048] The battery failure analysis results are determined based on the importance ranking of data features.

[0049] Through the above solution, machine learning is used to perform battery failure analysis, effectively improving the overall analysis efficiency.

[0050] In a specific implementation of the first aspect, before building a machine learning model according to the data table, the following steps may also be included:

[0051] Use the preset data feature selection method to select data features in the data table to obtain the selected data table.

[0052] Through the above scheme, the pre-selection of data features can eliminate parameters with poor classification and regression effects, reduce the dimension of the data, and improve the analysis efficiency.

[0053] In a specific implementation of the first aspect, before building a machine learning model according to the data table, the following steps may also be included:

[0054] Use the preset data cleaning method to clean the data in the data table to obtain the cleaned data table.

[0055] Through the above solution, the data table is cleaned in advance, which can remove a large amount of invalid data, avoid its interference with the analysis process, and effectively improve the accuracy of the final battery failure analysis results.

[0056] In a specific implementation of the first aspect, after determining the battery failure analysis result according to the battery failure factor set, the method may further include:

[0057] The battery failure case library and battery failure fault tree are updated according to the battery failure analysis results.

[0058] Through the above scheme, the battery failure case library and battery failure fault tree can be updated according to the analysis results of this time, thereby realizing a closed loop of the analysis process, continuously enriching the battery failure case library and battery failure fault tree, and providing a more complete foundation for subsequent battery failure case analysis.

[0059] A second aspect of an embodiment of the present application provides a battery failure analysis device, which may include:

[0060] A battery failure case acquisition module is used to acquire battery failure cases to be analyzed;

[0061] A battery failure analysis module is used to analyze battery failure cases based on a preset battery failure case library and a preset battery failure fault tree to obtain a set of battery failure factors;

[0062] The battery failure analysis result determination module is used to determine the battery failure analysis result based on the battery failure factor set.

[0063] In a specific implementation of the second aspect, the battery failure analysis module may include:

[0064] The battery failure case library analysis submodule is used to analyze battery failure cases based on the battery failure case library and obtain a set of case library failure factors;

[0065] The battery failure fault tree analysis submodule is used to analyze battery failure cases based on the battery failure fault tree and obtain a set of fault tree failure factors;

[0066] The battery failure factor set determination submodule is used to determine the battery failure factor set based on the case library failure factor set and the fault tree failure factor set.

[0067] In a specific implementation of the second aspect, the battery failure case library analysis submodule may include:

[0068] a case similarity calculation unit, configured to calculate case similarities between the battery failure case and each historical case in the battery failure case library;

[0069] A similar case selection unit is used to select historical cases whose case similarity is greater than a preset similarity threshold from the battery failure case library as similar cases to the battery failure case;

[0070] The case base failure factor set determination unit is used to determine the case base failure factor set based on similar cases.

[0071] In a specific implementation of the second aspect, the case similarity calculation unit may include:

[0072] A first case feature extraction subunit, configured to extract first case features from a battery failure case;

[0073] A second case feature extraction subunit is used to extract a second case feature from a target historical case; wherein the target historical case is any historical case in the battery failure case library;

[0074] The case similarity calculation subunit is used to calculate the case similarity between the battery failure case and the target historical case based on the first case feature and the second case feature.

[0075] In a specific implementation of the second aspect, the case similarity calculation subunit can be specifically used to: calculate the case feature distance between the first case feature and the second case feature; and determine the case similarity between the battery failure case and the target historical case based on the case feature distance.

[0076] In a specific implementation of the second aspect, the case similarity calculation subunit can be specifically used to: respectively calculate the sub-feature distances between each corresponding sub-feature of the first case feature and the second case feature; and perform weighted summation of each sub-feature distance according to a preset sub-feature weight to obtain the case feature distance.

[0077] In a specific implementation of the second aspect, the case library failure factor set determination unit may be specifically configured to: obtain failure root causes of similar cases; and summarize the failure root causes to obtain the case library failure factor set.

[0078] In a specific implementation of the second aspect, the battery failure fault tree analysis submodule can be specifically used to: extract the failure mode in the battery failure case; determine the target branch corresponding to the failure mode in the battery failure fault tree; perform fault tree analysis on the battery failure case based on the target branch to obtain a set of fault tree failure factors.

[0079] In a specific implementation of the second aspect, the battery failure factor set determination submodule can be specifically used to: combine the case library failure factor set and the fault tree offline factor set to obtain an offline factor set; wherein the fault tree offline factor set is the offline factor set in the fault tree failure factor set; combine the offline factor set and the fault tree online factor set to obtain a battery failure factor set; wherein the fault tree online factor set is the online factor set in the fault tree failure factor set.

[0080] In a specific implementation of the second aspect, the battery failure analysis result determination module may include:

[0081] The data table construction submodule is used to construct a data table of battery failure cases according to the battery failure factor set;

[0082] The target model construction submodule is used to construct a machine learning model based on the data table to obtain the constructed target model;

[0083] The data feature importance ranking submodule is used to determine the importance ranking of data features in the data table according to the target model;

[0084] The battery failure analysis result determination submodule is used to determine the battery failure analysis result according to the importance ranking of data features.

[0085] In a specific implementation of the second aspect, the battery failure analysis result determination module may further include:

[0086] The data feature selection submodule is used to select data features in the data table using a preset data feature selection method to obtain a selected data table.

[0087] In a specific implementation of the second aspect, the battery failure analysis result determination module may further include:

[0088] The data cleaning submodule is used to clean the data in the data table using a preset data cleaning method to obtain a cleaned data table.

[0089] In a specific implementation of the second aspect, the battery failure analysis device may further include:

[0090] The case library and fault tree updating module is used to update the battery failure case library and battery failure fault tree according to the battery failure analysis results.

[0091] A third aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above-mentioned battery failure analysis methods are implemented.

[0092] A fourth aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the above-mentioned battery failure analysis methods when executing the computer program.

[0093] A fifth aspect of an embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the steps of any one of the above-mentioned battery failure analysis methods. Beneficial effects

[0094] The embodiment of the present application obtains a battery failure case to be analyzed; analyzes the battery failure case based on a preset battery failure case library and a preset battery failure fault tree to obtain a battery failure factor set; and determines a battery failure analysis result based on the battery failure factor set. Through the embodiment of the present application, a comprehensive analysis of the battery failure case can be performed by combining the battery failure case library and the battery failure fault tree, thereby obtaining a more comprehensive battery failure factor set and effectively improving the accuracy of the final battery failure analysis result. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0096] FIG1 is a flow chart of an embodiment of a battery failure analysis method according to an embodiment of the present application;

[0097] FIG2 is a schematic flow chart of analyzing a battery failure case based on a preset battery failure case library and a preset battery failure fault tree;

[0098] FIG3 is a schematic flow chart of analyzing battery failure cases based on a battery failure case library;

[0099] FIG4 is a schematic flow chart of determining a battery failure analysis result based on a battery failure factor set;

[0100] FIG5 is a schematic diagram of an output result of an electronic device;

[0101] FIG6 is a structural diagram of an embodiment of a battery failure analysis device according to an embodiment of the present application;

[0102] FIG7 is a schematic block diagram of an electronic device in an embodiment of the present application. Modes for Carrying Out the Invention

[0103] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described below are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0104] It will be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0105] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0106] It should be further understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0107] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0108] In addition, in the description of the present application, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0109] With the rapid adoption of renewable energy and electric vehicles, demand for batteries such as lithium-ion batteries is growing dramatically. However, due to the complex manufacturing processes and physical and chemical reactions involved in their production, battery failure has always been a major factor limiting their performance and reliability.

[0110] Battery failure can include many aspects. Take battery lithium deposition as an example. When a lithium-ion battery is charging, lithium ions are deintercalated from the positive electrode and embedded in the negative electrode. However, when some abnormal conditions occur, such as insufficient space for lithium embedding in the negative electrode, too much resistance for lithium ions to embed in the negative electrode, or lithium ions are deintercalated from the positive electrode too quickly but cannot be embedded in the negative electrode in equal amounts, the lithium ions that cannot be embedded in the negative electrode can only gain electrons on the surface of the negative electrode, thereby forming a silvery-white metallic lithium element, which results in the phenomenon of battery lithium deposition.

[0111] Existing battery failure analysis methods rely on extensive production experience, combined with physical and chemical experiments, to identify and solve problems. Although useful analysis results can sometimes be obtained, the overall analysis is incomplete and the accuracy of the analysis results is low, making it unable to meet the challenges of large-scale production.

[0112] To address this issue, the embodiments of the present application can combine the battery failure case library and the battery failure fault tree to conduct a comprehensive analysis of battery failure cases, thereby obtaining a more comprehensive set of battery failure factors, effectively improving the accuracy of the final battery failure analysis results.

[0113] The execution entities of the embodiments of the present application may include but are not limited to electronic devices such as desktop computers, notebooks, PDAs, and servers.

[0114] Referring to FIG. 1 , an embodiment of a battery failure analysis method in an embodiment of the present application may include:

[0115] Step S101: Obtain a battery failure case to be analyzed.

[0116] In a specific implementation of an embodiment of the present application, a user may input a battery failure case to be analyzed into an input interface of an electronic device. The electronic device may obtain the battery failure case from the input interface and perform subsequent battery failure analysis on the battery failure case.

[0117] In another specific implementation of an embodiment of the present application, the user can store the battery failure case to be analyzed in a preset storage device, and the electronic device can obtain the stored battery failure case from the storage device through a pre-established data transmission link and perform subsequent battery failure analysis on it.

[0118] Among them, the data transmission link can be a data transmission link established based on at least one communication solution such as Wireless Local Area Networks (WLAN) (for example, Wireless Fidelity (WiFi)), Bluetooth, Global Navigation Satellite System (GNSS), Frequency Modulation (FM), Near Field Communication (NFC), Infrared (IR), Global System for Mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division-Synchronous Code Division Multiple Access (TD-SCDMA) and Long Term Evolution (LTE).

[0119] Battery failure cases may include but are not limited to failure descriptions and failure modes. Taking the failure case of battery lithium deposition as an example, the failure description may include but is not limited to failure nodes, failure rates, failure surfaces, failure locations, lithium deposition morphology, black spot morphology, failure levels and other descriptive dimensions; failure modes may include but are not limited to black spots, large-surface lithium deposition, corner lithium deposition and other different modes.

[0120] Step S102: Analyze the battery failure case based on a preset battery failure case library and a preset battery failure fault tree to obtain a battery failure factor set.

[0121] Fault Tree Analysis (FTA) is a logical deduction analysis tool that uses a directed logic tree depicting the causal relationships of an accident to analyze the phenomena, causes, and consequences of an accident, thereby identifying preventative measures. FTA is a key analytical method in systems safety engineering, capable of identifying and evaluating the hazards of various systems. It is suitable for both qualitative and quantitative analysis, and its simplicity and visualization demonstrate the systematic, accurate, and predictive nature of systems engineering approaches to safety research.

[0122] In the embodiment of the present application, a fault tree for performing FTA analysis on battery failure can be pre-constructed, which is recorded as a battery failure fault tree. The specific construction process of the fault tree can refer to any FTA method in the prior art, and the embodiment of the present application does not specifically limit this.

[0123] In an embodiment of the present application, a historical case library for analyzing battery failures can be pre-built and recorded as a battery failure case library. The battery failure case library can include historical cases for which battery failure analysis has been completed, and each historical case is pre-labeled with the corresponding failure root cause.

[0124] In order to improve the accuracy of battery failure analysis, the FTA analysis method can be combined with the case library analysis method to conduct a comprehensive analysis of battery failure cases, thereby obtaining a more comprehensive and complete set of battery failure factors.

[0125] In a specific implementation of the embodiment of the present application, step S102 may specifically include the process shown in FIG2 :

[0126] Step S1021: Analyze battery failure cases based on a battery failure case library to obtain a case library failure factor set.

[0127] In a specific implementation of the embodiment of the present application, similar cases of battery failure cases can be selected from the battery failure case library based on the similarity between the cases, and the case library failure factor set can be determined based on the similar cases. Step S1021 can specifically include the process shown in Figure 3:

[0128] Step S1021a: Calculate the case similarity between the battery failure case and each historical case in the battery failure case library.

[0129] Taking any historical case in the battery failure case library as an example, it is recorded as the target historical case. In a specific implementation method of an embodiment of the present application, the failure description in the battery failure case can be extracted and used as the first case feature, and each description dimension in the failure description is used as one of its sub-features; similarly, the failure description in the target historical case can be extracted and used as the second case feature, and each description dimension in the failure description is used as one of its sub-features.

[0130] After obtaining the first case feature and the second case feature, the case similarity between the battery failure case and the target historical case may be calculated based on the first case feature and the second case feature.

[0131] In a specific implementation of the embodiment of the present application, the case feature distance between the first case feature and the second case feature may be calculated first.

[0132] Specifically, the sub-feature distances between the corresponding sub-features of the first case feature and the second case feature may be calculated respectively, and the sub-feature distances may be weighted and summed according to preset sub-feature weights to obtain the case feature distance.

[0133] Among them, for nominal sub-features, one-hot encoding can be performed on them first, and then the cosine distance calculation is performed on the encoded data to obtain the corresponding sub-feature distance.

[0134] For numerical sub-features, the Absolute Percentage Error (APE) can be calculated to obtain the corresponding sub-feature distance.

[0135] It should be noted that the above distance calculation method is only an example. In practical applications, any distance calculation method in the prior art can be adopted according to specific circumstances, and the embodiments of the present application do not make specific limitations on this.

[0136] Different sub-features can be pre-assigned corresponding weights based on actual circumstances, with more important sub-features given larger weights and less important sub-features given smaller weights. After obtaining the distances for each sub-feature, they can be weighted and summed according to these pre-assigned weights to obtain the case feature distance. This approach can strengthen more important sub-features and weaken less important ones, thereby improving the accuracy of the final result.

[0137] After obtaining the case feature distance, the case similarity between the battery failure case and the target historical case can be determined based on the case feature distance.

[0138] Among them, case similarity is negatively correlated with case feature distance, that is, the greater the case feature distance between the battery failure case and the target historical case, the smaller the case similarity between the battery failure case and the target historical case; conversely, the smaller the case feature distance between the battery failure case and the target historical case, the greater the case similarity between the battery failure case and the target historical case.

[0139] In a specific implementation of an embodiment of the present application, the case feature distance can be normalized to the interval range of [0,1], and then the difference between 1 and the case feature distance is calculated and used as the case similarity between the battery failure case and the target historical case.

[0140] In another specific implementation of the embodiment of the present application, the inverse of the case feature distance may be calculated and used as the case similarity between the battery failure case and the target historical case.

[0141] By calculating the distance between case features to characterize the similarity between cases, an accurate measurement of case similarity can be achieved.

[0142] Step S1021b: selecting historical cases whose case similarity is greater than a preset similarity threshold from the battery failure case library as similar cases to the battery failure case.

[0143] The specific value of the similarity threshold can be set according to actual conditions. For example, the similarity threshold can be set to 0.8, 0.85, 0.9, 0.95 or other values, which is not specifically limited in the embodiment of the present application.

[0144] Step S1021c: Determine a set of failure factors of the case library based on similar cases.

[0145] Each historical case in the battery failure case library is pre-labeled with the corresponding root cause of failure. After selecting similar cases of battery failure from the battery failure case library, the root causes of failure of similar cases can be obtained and summarized to obtain the case library failure factor set.

[0146] Through the process shown in FIG3 , similar cases can be selected from the battery failure case library. The similarity between these similar cases and the battery failure cases is relatively large. The case library failure factor set determined based on these similar cases has a good reference significance for the battery failure cases.

[0147] In a specific implementation of the embodiment of the present application, the frequency of occurrence of the root causes of failures of similar cases can also be counted, and the root causes of failures can be sorted in descending order of frequency in the failure factor set of the case library, that is, the higher the frequency of occurrence of the root cause of failure, the higher the ranking, and the lower the frequency of occurrence of the root cause of failure, the lower the ranking, so as to improve the efficiency of subsequent analysis.

[0148] Step S1022: Analyze the battery failure case based on the battery failure fault tree to obtain a set of fault tree failure factors.

[0149] In practical applications, any FTA method in the prior art can be used to analyze battery failure cases according to specific circumstances, and this is not specifically limited here.

[0150] In a specific implementation of an embodiment of the present application, the battery failure fault tree may include branches corresponding to each failure mode. For example, the battery failure fault tree may include but is not limited to branches corresponding to black spot failure modes, branches corresponding to large-surface lithium deposition failure modes, branches corresponding to corner lithium deposition failure modes, etc.

[0151] When analyzing battery failure cases based on a battery failure fault tree, the failure mode can be extracted from the case and the branch corresponding to the failure mode can be identified in the battery failure fault tree, which is recorded as the target branch. Subsequent fault tree analysis of the battery failure case based on the target branch is no longer necessary based on the entire battery failure fault tree. This yields a set of fault tree failure factors. This approach is more targeted, narrows the analysis scope, and effectively improves analysis efficiency.

[0152] Step S1023: Determine a battery failure factor set based on the case library failure factor set and the fault tree failure factor set.

[0153] Since there are many failure factors that lead to battery failure, possibly more than hundreds, only the more important failure factors will be included in the preset database. For easy distinction, the failure factors included in the database can be recorded as online factors, and the failure factors not included in the database can be recorded as offline factors.

[0154] The failure factors in the case library failure factor set are all offline factors, while the failure factors in the fault tree failure factor set include both online and offline factors. For ease of distinction, the offline factor set in the fault tree failure factor set can be referred to as the fault tree offline factor set, and the online factor set in the fault tree failure factor set can be referred to as the fault tree online factor set.

[0155] For the set of factors on the fault tree line, the analysis index of each failure factor can be calculated separately, where the analysis index may include but is not limited to distribution difference, equipment concentration, film roll concentration, time concentration and other indicators.

[0156] By combining the case library failure factor set with the fault tree offline factor set, we can obtain the offline factor set. Similar to the online factors, we can calculate analysis indicators for each failure factor in the offline factor set. These analysis indicators may include, but are not limited to, distribution variability, equipment concentration, film roll concentration, and time concentration.

[0157] After the offline factor set and the fault tree online factor set are determined, the offline factor set and the fault tree online factor set may be combined to obtain a battery failure factor set.

[0158] Through the process shown in Figure 2, a case library failure factor set can be obtained based on the analysis of the battery failure case library, and a fault tree failure factor set can be obtained based on the analysis of the battery failure fault tree. By comprehensively considering the two, a more comprehensive battery failure factor set can be obtained.

[0159] Step S103: Determine a battery failure analysis result according to the battery failure factor set.

[0160] In a specific implementation of the embodiment of the present application, a machine learning approach can be used to perform battery failure analysis to improve overall analysis efficiency. Step S103 can specifically include the process shown in Figure 4:

[0161] Step S1031: Construct a data table of battery failure cases according to the battery failure factor set.

[0162] For all the data in the battery failure case, the online and offline factors in the battery failure factor set can be combined according to certain rules to construct a data table of battery failure cases. Specific rules can be set according to actual conditions, for example, they may include but are not limited to rules for matching battery cell barcodes, matching core rolls (JR), matching film rolls, etc.

[0163] In a specific implementation of the embodiment of the present application, after the data table is constructed, a preset data cleaning method may be used to clean the data in the data table, thereby obtaining a cleaned data table.

[0164] The specific data cleaning method can be configured based on the actual situation and is not specifically limited in the present embodiment. For example, it may include but is not limited to: removing parameters with no differences in the data table, removing parameters with missing data exceeding a set threshold in the data table, removing rows or columns containing missing values ​​(i.e., dropna), and other cleaning operations.

[0165] By pre-cleaning the data table, a large amount of invalid data can be cleaned out, avoiding its interference with the analysis process and effectively improving the accuracy of the final battery failure analysis results.

[0166] In a specific implementation of the embodiment of the present application, a preset data feature selection method may be used to select data features in a data table, thereby obtaining a selected data table.

[0167] The specific data feature selection method can be set according to the actual situation, and the present embodiment does not specifically limit this. For example, it can include but is not limited to: recursive feature elimination method, Select from model and other feature selection methods.

[0168] By using data feature selection in advance, parameters with poor classification and regression effects can be eliminated, the dimension of the data can be reduced, and the analysis efficiency can be improved.

[0169] Step S1032: construct a machine learning model based on the data table to obtain a constructed target model.

[0170] After obtaining the data table, the data in the data table can be input into the initial machine learning model for classification or regression modeling to obtain the final target model.

[0171] The specific machine learning model to be used can be set according to the actual situation, and the present embodiment does not specifically limit this. For example, it can include but is not limited to: decision tree, random forest, XGBoost and other models.

[0172] Step S1033: Determine the importance ranking of the data features in the data table according to the target model.

[0173] After obtaining the target model, the target model can be used to rank the importance of each feature (ie, failure factor) in the data table to determine its impact on the final result.

[0174] Specifically, for decision trees, the importance of features can be evaluated based on the number of node splits or information gain in the decision tree; for random forests, the out-of-bag (OOB) error can be used to evaluate the importance of features; for XGBoost, the average number of feature splits on each weak learner or the loss reduction brought by the feature to the model can be used to evaluate the importance of features.

[0175] Step S1034: Determine the battery failure analysis result according to the order of importance of the data features.

[0176] In a specific implementation method of an embodiment of the present application, after determining the importance ranking of data features, the electronic device can output the importance ranking of data features through a preset human-computer interaction interface. In addition, it can also be displayed in combination with indicators such as distribution differences, equipment concentration, film roll concentration, and time concentration.

[0177] Based on the output results of the electronic equipment, users can verify and correct them through manual inspection to obtain the final battery failure analysis results and propose corresponding solutions.

[0178] FIG5 is a schematic diagram of the output results of the electronic device. As shown in the figure, the importance of data features is ranked as follows: failure factor A, failure factor B, failure factor C, failure factor D, failure factor E, failure factor F, ... After the user verifies through manual inspection, the failure factor B can be determined as the final battery failure analysis result, and the battery failure analysis result can be input into the electronic device through the human-computer interaction interface.

[0179] In a specific implementation of the embodiment of the present application, after obtaining the final battery failure analysis result, the electronic device may also update the battery failure case library and the battery failure fault tree according to the battery failure analysis result.

[0180] Specifically, the current battery failure case can be added as a new historical case to the battery failure case library, and its corresponding root cause of failure can be marked according to the battery failure analysis results; the missing failure factors in the battery failure fault tree can also be fed back and completed according to the battery failure analysis results, thereby realizing a closed loop of the analysis process, continuously enriching the battery failure case library and battery failure fault tree, and providing a more complete foundation for subsequent battery failure case analysis.

[0181] In summary, the embodiments of the present application obtain battery failure cases to be analyzed; analyze the battery failure cases based on a preset battery failure case library and a preset battery failure fault tree to obtain a set of battery failure factors; and determine the battery failure analysis results based on the set of battery failure factors. Through the embodiments of the present application, the battery failure cases can be comprehensively analyzed in combination with the battery failure case library and the battery failure fault tree, thereby obtaining a more comprehensive set of battery failure factors and effectively improving the accuracy of the final battery failure analysis results.

[0182] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0183] Corresponding to the battery failure analysis method described in the above embodiment, FIG6 shows a structural diagram of an embodiment of a battery failure analysis device provided in an embodiment of the present application.

[0184] In this embodiment, a battery failure analysis device may include:

[0185] A battery failure case acquisition module 601 is used to acquire battery failure cases to be analyzed;

[0186] A battery failure analysis module 602 is configured to analyze battery failure cases based on a preset battery failure case library and a preset battery failure fault tree to obtain a battery failure factor set;

[0187] The battery failure analysis result determination module 603 is configured to determine the battery failure analysis result according to the battery failure factor set.

[0188] In a specific implementation of the embodiment of the present application, the battery failure analysis module may include:

[0189] The battery failure case library analysis submodule is used to analyze battery failure cases based on the battery failure case library and obtain a set of case library failure factors;

[0190] The battery failure fault tree analysis submodule is used to analyze battery failure cases based on the battery failure fault tree and obtain a set of fault tree failure factors;

[0191] The battery failure factor set determination submodule is used to determine the battery failure factor set based on the case library failure factor set and the fault tree failure factor set.

[0192] In a specific implementation of the embodiment of the present application, the battery failure case library analysis submodule may include:

[0193] a case similarity calculation unit, configured to calculate case similarities between the battery failure case and each historical case in the battery failure case library;

[0194] A similar case selection unit is used to select historical cases whose case similarity is greater than a preset similarity threshold from the battery failure case library as similar cases to the battery failure case;

[0195] The case base failure factor set determination unit is used to determine the case base failure factor set based on similar cases.

[0196] In a specific implementation of the embodiment of the present application, the case similarity calculation unit may include:

[0197] A first case feature extraction subunit, configured to extract first case features from a battery failure case;

[0198] A second case feature extraction subunit is used to extract a second case feature from a target historical case; wherein the target historical case is any historical case in the battery failure case library;

[0199] The case similarity calculation subunit is used to calculate the case similarity between the battery failure case and the target historical case based on the first case feature and the second case feature.

[0200] In a specific implementation of an embodiment of the present application, the case similarity calculation subunit can be specifically used to: calculate the case feature distance between the first case feature and the second case feature; and determine the case similarity between the battery failure case and the target historical case based on the case feature distance.

[0201] In a specific implementation of an embodiment of the present application, the case similarity calculation subunit can be specifically used to: respectively calculate the sub-feature distances between each corresponding sub-feature of the first case feature and the second case feature; and perform weighted summation of each sub-feature distance according to a preset sub-feature weight to obtain the case feature distance.

[0202] In a specific implementation of the embodiment of the present application, the case library failure factor set determination unit may be specifically configured to: obtain failure root causes of similar cases; and summarize the failure root causes to obtain the case library failure factor set.

[0203] In a specific implementation of an embodiment of the present application, the battery failure fault tree analysis submodule can be specifically used to: extract the failure mode in the battery failure case; determine the target branch corresponding to the failure mode in the battery failure fault tree; perform fault tree analysis on the battery failure case based on the target branch to obtain a set of fault tree failure factors.

[0204] In a specific implementation of an embodiment of the present application, the battery failure factor set determination submodule can be specifically used to: combine the case library failure factor set and the fault tree offline factor set to obtain an offline factor set; wherein, the fault tree offline factor set is the offline factor set in the fault tree failure factor set; combine the offline factor set and the fault tree online factor set to obtain a battery failure factor set; wherein, the fault tree online factor set is the online factor set in the fault tree failure factor set.

[0205] In a specific implementation of the embodiment of the present application, the battery failure analysis result determination module may include:

[0206] The data table construction submodule is used to construct a data table of battery failure cases according to the battery failure factor set;

[0207] The target model construction submodule is used to construct a machine learning model based on the data table to obtain the constructed target model;

[0208] The data feature importance ranking submodule is used to determine the importance ranking of data features in the data table according to the target model;

[0209] The battery failure analysis result determination submodule is used to determine the battery failure analysis result according to the importance ranking of data features.

[0210] In a specific implementation of the embodiment of the present application, the battery failure analysis result determination module may further include:

[0211] The data feature selection submodule is used to select data features in the data table using a preset data feature selection method to obtain a selected data table.

[0212] In a specific implementation of the embodiment of the present application, the battery failure analysis result determination module may further include:

[0213] The data cleaning submodule is used to clean the data in the data table using a preset data cleaning method to obtain a cleaned data table.

[0214] In a specific implementation of the embodiment of the present application, the battery failure analysis device may further include:

[0215] The case library and fault tree updating module is used to update the battery failure case library and battery failure fault tree according to the battery failure analysis results.

[0216] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0217] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0218] FIG7 shows a schematic block diagram of an electronic device provided in an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0219] As shown in FIG7 , the electronic device 7 of this embodiment includes: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70. When the processor 70 executes the computer program 72, it implements the steps in the aforementioned battery failure analysis method embodiments, such as steps S101 to S103 shown in FIG1 . Alternatively, when the processor 70 executes the computer program 72, it implements the functions of the modules / units in the aforementioned device embodiments, such as the functions of modules 601 to 603 shown in FIG6 .

[0220] Exemplarily, the computer program 72 may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to implement the present application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 72 in the electronic device 7.

[0221] The electronic device 7 may be a computing device such as a desktop computer, a notebook, a PDA, or a server. Those skilled in the art will appreciate that FIG. 7 is merely an example of the electronic device 7 and does not limit the electronic device 7 . The electronic device 7 may include more or fewer components than shown, or may combine certain components or different components. For example, the electronic device 7 may also include input and output devices, network access devices, a bus, and the like.

[0222] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0223] The memory 71 may be an internal storage unit of the electronic device 7, such as a hard disk or memory of the electronic device 7. The memory 71 may also be an external storage device of the electronic device 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 7. Furthermore, the memory 71 may include both an internal storage unit of the electronic device 7 and an external storage device. The memory 71 is used to store the computer program and other programs and data required by the electronic device 7. The memory 71 may also be used to temporarily store data that has been output or is about to be output.

[0224] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0225] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0226] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0227] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0228] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0229] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0230] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0231] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A battery failure analysis method, wherein: include: Obtain battery failure cases to be analyzed; Analyze the battery failure case based on a preset battery failure case library and a preset battery failure fault tree to obtain a battery failure factor set; A battery failure analysis result is determined according to the battery failure factor set.

2. The battery failure analysis method according to claim 1, wherein: The battery failure case is analyzed based on a preset battery failure case library and a preset battery failure fault tree to obtain a battery failure factor set, including: Analyze the battery failure case based on the battery failure case library to obtain a case library failure factor set; Analyze the battery failure case based on the battery failure fault tree to obtain a fault tree failure factor set; The battery failure factor set is determined according to the case library failure factor set and the fault tree failure factor set.

3. The battery failure analysis method according to claim 2, wherein: The battery failure case is analyzed based on the battery failure case library to obtain a case library failure factor set, including: respectively calculating case similarities between the battery failure case and each historical case in the battery failure case library; Selecting historical cases whose case similarity is greater than a preset similarity threshold from the battery failure case library as similar cases to the battery failure case; The case library failure factor set is determined according to the similar cases.

4. The battery failure analysis method according to claim 3, wherein: The respectively calculating the case similarity between the battery failure case and each historical case in the battery failure case library includes: Extracting a first case feature from the battery failure case; Extracting a second case feature in a target historical case; wherein the target historical case is any historical case in the battery failure case library; The case similarity between the battery failure case and the target historical case is calculated according to the first case feature and the second case feature.

5. The battery failure analysis method according to claim 4, wherein: The calculating, according to the first case feature and the second case feature, the case similarity between the battery failure case and the target historical case includes: calculating a case feature distance between the first case feature and the second case feature; Determine the case similarity between the battery failure case and the target historical case based on the case feature distance Spend.

6. The battery failure analysis method according to claim 5, wherein: The calculating the case feature distance between the first case feature and the second case feature includes: respectively calculating the sub-feature distances between the respective corresponding sub-features of the first case feature and the second case feature; The case feature distance is obtained by performing weighted summation on each sub-feature distance according to a preset sub-feature weight.

7. The battery failure analysis method according to any one of claims 3 to 6, wherein: The step of determining the case library failure factor set according to the similar cases includes: Obtain the root causes of failures of the similar cases; The failure root causes are summarized to obtain the case library failure factor set.

8. The battery failure analysis method according to any one of claims 2 to 7, wherein: The battery failure case is analyzed based on the battery failure fault tree to obtain a set of fault tree failure factors, including: Extracting failure modes from the battery failure cases; Determining a target branch corresponding to the failure mode in the battery failure fault tree; A fault tree analysis is performed on the battery failure case based on the target branch to obtain the fault tree failure factor set.

9. The battery failure analysis method according to any one of claims 2 to 8, wherein: The step of determining the battery failure factor set according to the case library failure factor set and the fault tree failure factor set includes: The case base failure factor set and the fault tree offline factor set are combined to obtain an offline factor set; wherein the fault tree offline factor set is an offline factor set in the fault tree failure factor set; The offline factor set and the fault tree online factor set are combined to obtain the battery failure factor set; wherein the fault tree online factor set is an online factor set in the fault tree failure factor set.

10. The battery failure analysis method according to any one of claims 1 to 9, wherein: The determining of the battery failure analysis result according to the battery failure factor set includes: Constructing a data table of the battery failure cases according to the battery failure factor set; Construct a machine learning model according to the data table to obtain a constructed target model; Determine the importance ranking of the data features in the data table according to the target model; The battery failure analysis result is determined according to the importance ranking of the data features.

11. The battery failure analysis method according to claim 10, wherein: Before building a machine learning model based on the data table, it also includes: Use the preset data feature selection method to select data features in the data table, and obtain the selected data features. Data sheet.

12. The battery failure analysis method according to claim 10 or 11, wherein: Before building a machine learning model based on the data table, it also includes: Use a preset data cleaning method to clean the data in the data table to obtain the cleaned data table.

13. The battery failure analysis method according to any one of claims 1 to 12, wherein: After determining the battery failure analysis result according to the battery failure factor set, the method further includes: The battery failure case library and the battery failure fault tree are updated according to the battery failure analysis result.

14. A battery failure analysis device, wherein: include: A battery failure case acquisition module is used to acquire battery failure cases to be analyzed; A battery failure analysis module is used to analyze battery failure cases based on a preset battery failure case library and a preset battery failure fault tree to obtain a battery failure factor set; The battery failure analysis result determination module is used to determine the battery failure analysis result according to the battery failure factor set.

15. A computer-readable storage medium storing a computer program, wherein: When the computer program is executed by a processor, the steps of the battery failure analysis method according to any one of claims 1 to 13 are implemented.

16. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the battery failure analysis method according to any one of claims 1 to 13 are implemented.

Images