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

Abstract

The invention belongs to the technical field of batteries, and particularly relates to a battery failure analysis method and device, a computer readable storage medium and electronic equipment. The method comprises the following steps: acquiring a battery failure case to be analyzed; analyzing 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 determining a battery failure analysis result according to the battery failure factor set. According to the battery failure analysis method and device, the battery failure cases can be comprehensively analyzed in combination with the battery failure case library and the battery failure fault tree, so that a more comprehensive battery failure factor set can be obtained through analysis, and the accuracy of a final battery failure analysis result is effectively improved.

Description

Technical Field

[0001] This application belongs to the technical field of batteries, and particularly relates to a battery failure analysis method, device, computer-readable storage medium, and electronic device. Background Art

[0002] With the rapid popularization of renewable energy and electric vehicles, the demand for batteries such as lithium-ion batteries is increasing sharply. However, due to the complex manufacturing processes and physical and chemical reactions in their production, the failure problems of batteries (such as lithium plating in batteries) have always been the main factors restricting their performance and reliability.

[0003] In the existing battery failure analysis methods, a large amount of production experience is required, combined with physical and chemical experiments to identify and solve problems. Although sometimes some useful analysis results can be obtained, overall the analysis is not comprehensive, and the accuracy of the analysis results is relatively low, unable to cope with the challenges in large-scale production. Summary of the Invention

[0004] In view of this, the embodiments of this application provide a battery failure analysis method, device, computer-readable storage medium, and electronic device to solve the problem of relatively low accuracy of the analysis results in the existing battery failure analysis methods.

[0005] The first aspect of the embodiments of this application provides a battery failure analysis method, which may include:

[0006] Obtain a battery failure case to be analyzed;

[0007] Analyze the battery failure case based on a preset battery failure case library and a preset battery failure fault tree to obtain a set of battery failure factors;

[0008] Determine the battery failure analysis result according to the set of battery failure factors.

[0009] Through the above solution, the battery failure case can be comprehensively analyzed by combining the battery failure case library and the battery failure fault tree, so that a more comprehensive set of battery failure factors can be analyzed, effectively improving the accuracy of the final battery failure analysis result.

[0010] In a specific implementation manner of the first aspect, analyzing the battery failure case based on a preset battery failure case library and a preset battery failure fault tree to obtain a set of battery failure factors may include:

[0011] Analyze the battery failure case based on the battery failure case library to obtain a set of case library failure factors;

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

[0013] Determine the battery failure factor set according to the case base failure factor set and the fault tree failure factor set of the battery.

[0014] Through the above solution, the case base failure factor set can be obtained based on the analysis of the battery failure case base, the fault tree failure factor set can be obtained based on the analysis of the battery failure fault tree, and by comprehensively considering these two, a more comprehensive battery failure factor set can be obtained.

[0015] In a specific implementation manner of the first aspect, analyzing the battery failure cases based on the battery failure case base to obtain the case base failure factor set may include:

[0016] Calculate the case similarity between the battery failure case and each historical case in the battery failure case base respectively;

[0017] Select the historical cases with case similarity greater than the preset similarity threshold from the battery failure case base as the similar cases of the battery failure case;

[0018] Determine the case base failure factor set according to the similar cases.

[0019] Through the above solution, similar cases can be selected from the battery failure case base. These similar cases have a relatively large similarity with the battery failure case, and the case base failure factor set determined according to these similar cases has good reference significance for the battery failure case.

[0020] In a specific implementation manner of the first aspect, calculating the case similarity between the battery failure case and each historical case in the battery failure case base respectively may include:

[0021] Extract the first case feature in the battery failure case;

[0022] Extract the second case feature in the target historical case; where the target historical case is any historical case in the battery failure case base;

[0023] Calculate the case similarity between the battery failure case and the target historical case according to the first case feature and the second case feature.

[0024] In a specific implementation manner of the first aspect, calculating the case similarity between the battery failure case and the target historical case according to the first case feature and the second case feature may include:

[0025] Calculate the case feature distance between the first case feature and the second case feature;

[0026] Determine the case similarity between the battery failure case and the target historical case according to the case feature distance.

[0027] Through the above solution, by calculating the distance between case features to characterize the similarity between cases, an accurate measurement of case similarity can be achieved.

[0028] In a specific implementation manner of the first aspect, calculating the case feature distance between the first case feature and the second case feature may include:

[0029] Calculating the sub-feature distances between the respective corresponding sub-features of the first case feature and the second case feature respectively;

[0030] Performing weighted summation on each sub-feature distance according to the preset sub-feature weights to obtain the case feature distance.

[0031] Through the above solution, corresponding weights can be assigned to each sub-feature according to the actual situation, strengthening the more important sub-features and weakening the unimportant sub-features, thereby improving the accuracy of the final result.

[0032] In a specific implementation manner of the first aspect, determining the case library failure factor set according to similar cases may include:

[0033] Obtaining the failure root cause of the similar cases;

[0034] Summarizing the failure root causes to obtain the case library failure factor set.

[0035] In a specific implementation manner of the first aspect, analyzing battery failure cases based on the battery failure fault tree to obtain the fault tree failure factor set may include:

[0036] Extracting the failure mode in the battery failure case;

[0037] Determining the target branch corresponding to the failure mode in the battery failure fault tree;

[0038] Performing fault tree analysis on the battery failure case based on the target branch to obtain the fault tree failure factor set.

[0039] Through the above solution, the corresponding target branch can be determined in the battery failure fault tree according to the failure mode, and fault tree analysis is performed based on the target branch, which has stronger pertinence, narrows the analysis scope, and improves the analysis efficiency.

[0040] In a specific implementation manner of the first aspect, determining the battery failure factor set according to the case library failure factor set and the fault tree failure factor set may include:

[0041] Combining the case library failure factor set and the off-line factor set of the fault tree to obtain the off-line factor set; wherein, the off-line factor set of the fault tree is the off-line factor set in the fault tree failure factor set;

[0042] Combine the offline factor set and the online factor set of the fault tree to obtain a battery failure factor set; among them, the online factor set of the fault tree is the online factor set in the fault tree failure factor set.

[0043] In a specific implementation manner of the first aspect, determining the battery failure analysis result according to the battery failure factor set may include:

[0044] Construct a data table of battery failure cases according to the battery failure factor set;

[0045] Construct a machine learning model according to the data table to obtain the constructed target model;

[0046] Determine the importance ranking of data features in the data table according to the target model;

[0047] Determine the battery failure analysis result according to the importance ranking of data features.

[0048] Through the above solution, the battery failure analysis is carried out by means of machine learning, effectively improving the overall analysis efficiency.

[0049] In a specific implementation manner of the first aspect, before constructing the machine learning model according to the data table, it may further include:

[0050] Use a preset data feature selection method to select data features in the data table to obtain a data table after selection.

[0051] Through the above solution, pre-using data feature selection can eliminate parameters with poor classification and regression effects, reduce the dimension of data, and improve the analysis efficiency.

[0052] In a specific implementation manner of the first aspect, before constructing the machine learning model according to the data table, it may further include:

[0053] Use a preset data cleaning method to clean the data in the data table to obtain a data table after cleaning.

[0054] Through the above solution, pre-cleaning the data table can clean a large amount of invalid data, avoid its interference with the analysis process, and effectively improve the accuracy of the final battery failure analysis result.

[0055] In a specific implementation manner of the first aspect, after determining the battery failure analysis result according to the battery failure factor set, it may further include:

[0056] Update the battery failure case library and the battery failure fault tree according to the battery failure analysis result.

[0057] Through the above solution, the battery failure case library and the battery failure fault tree can be updated according to the analysis results of this time, thus realizing the closed-loop of the analysis process, continuously enriching the battery failure case library and the battery failure fault tree, and providing a more complete basis for subsequent battery failure case analysis.

[0058] The second aspect of the embodiments of the present application provides a battery failure analysis device, which may include:

[0059] A battery failure case acquisition module, configured to acquire a battery failure case to be analyzed;

[0060] A battery failure analysis module, configured to analyze the battery failure case based on a preset battery failure case library and a preset battery failure fault tree to obtain a set of battery failure factors;

[0061] A battery failure analysis result determination module, configured to determine a battery failure analysis result according to the set of battery failure factors.

[0062] In a specific implementation manner of the second aspect, the battery failure analysis module may include:

[0063] A battery failure case library analysis sub-module, configured to analyze the battery failure case based on the battery failure case library to obtain a set of case library failure factors;

[0064] A battery failure fault tree analysis sub-module, configured to analyze the battery failure case based on the battery failure fault tree to obtain a set of fault tree failure factors;

[0065] A battery failure factor set determination sub-module, configured to determine a set of battery failure factors according to the set of case library failure factors and the set of fault tree failure factors.

[0066] In a specific implementation manner of the second aspect, the battery failure case library analysis sub-module may include:

[0067] A case similarity calculation unit, configured to calculate the case similarity between the battery failure case and each historical case in the battery failure case library respectively;

[0068] A similar case selection unit, configured to select a historical case with a case similarity greater than a preset similarity threshold from the battery failure case library as a similar case of the battery failure case;

[0069] A case library failure factor set determination unit, configured to determine a set of case library failure factors according to the similar cases.

[0070] In a specific implementation manner of the second aspect, the case similarity calculation unit may include:

[0071] The first case feature extraction subunit is used to extract the first case features in the battery failure cases;

[0072] The second case feature extraction subunit is used to extract the second case features in the target historical cases; wherein, the target historical case is any historical case in the battery failure case library;

[0073] The case similarity calculation subunit is used to calculate the case similarity between the battery failure case and the target historical case according to the first case features and the second case features.

[0074] In a specific implementation manner of the second aspect, the case similarity calculation subunit can specifically be used to: calculate the case feature distance between the first case features and the second case features; determine the case similarity between the battery failure case and the target historical case according to the case feature distance.

[0075] In a specific implementation manner of the second aspect, the case similarity calculation subunit can specifically be used to: respectively calculate the sub-feature distances between the corresponding sub-features of the first case features and the second case features; perform weighted summation on each sub-feature distance according to the preset sub-feature weights to obtain the case feature distance.

[0076] In a specific implementation manner of the second aspect, the case library failure factor set determination unit can specifically be used to: obtain the failure root causes of the similar cases; summarize the failure root causes to obtain the case library failure factor set.

[0077] In a specific implementation manner of the second aspect, the battery failure fault tree analysis sub-module can specifically be used to: extract the failure modes in the battery failure cases; determine the target branches corresponding to the failure modes in the battery failure fault tree; perform fault tree analysis on the battery failure cases based on the target branches to obtain the fault tree failure factor set.

[0078] In a specific implementation manner of the second aspect, the battery failure factor set determination sub-module can specifically be used to: combine the case library failure factor set and the fault tree offline factor set to obtain the 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 the battery failure factor set; wherein, the fault tree online factor set is the online factor set in the fault tree failure factor set.

[0079] In a specific implementation manner of the second aspect, the battery failure analysis result determination module can include:

[0080] The data table construction sub-module is used to construct the data table of the battery failure cases according to the battery failure factor set;

[0081] A target model construction sub-module, configured to construct a machine learning model based on a data table to obtain a constructed target model;

[0082] A data feature importance ranking sub-module, configured to determine the importance ranking of data features in the data table according to the target model;

[0083] A battery failure analysis result determination sub-module, configured to determine the battery failure analysis result according to the importance ranking of data features.

[0084] In a specific implementation manner of the second aspect, the battery failure analysis result determination module may further include:

[0085] A data feature selection sub-module, configured to perform data feature selection in the data table using a preset data feature selection method to obtain a data table after selection.

[0086] In a specific implementation manner of the second aspect, the battery failure analysis result determination module may further include:

[0087] A data cleaning sub-module, configured to perform data cleaning in the data table using a preset data cleaning method to obtain a data table after cleaning.

[0088] In a specific implementation manner of the second aspect, the battery failure analysis device may further include:

[0089] A case library and fault tree update module, configured to update the battery failure case library and the battery failure fault tree according to the battery failure analysis result.

[0090] The third aspect of the embodiments of the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above battery failure analysis methods are implemented.

[0091] The fourth aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the above battery failure analysis methods are implemented.

[0092] The fifth aspect of the embodiments of the present application provides a computer program product, which when running on an electronic device causes the electronic device to execute the steps of any one of the above battery failure analysis methods.

[0093] The beneficial effects of the second aspect to the fifth aspect can be referred to the specific description in the first aspect, and will not be elaborated here. Description of the Drawings

[0094] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0095] Figure 1 It is a flowchart of an embodiment of a battery failure analysis method in an embodiment of the present application;

[0096] Figure 2 It is a schematic flowchart for analyzing battery failure cases based on a preset battery failure case library and a preset battery failure fault tree;

[0097] Figure 3 It is a schematic flowchart for analyzing battery failure cases based on a battery failure case library;

[0098] Figure 4 It is a schematic flowchart for determining the battery failure analysis result according to the battery failure factor set;

[0099] Figure 5 It is a schematic diagram of the output result of an electronic device;

[0100] Figure 6 It is a structural diagram of an embodiment of a battery failure analysis device in an embodiment of the present application;

[0101] Figure 7 It is a schematic block diagram of an electronic device in an embodiment of the present application. Detailed implementation manners

[0102] To make the invention purposes, features, and advantages of the present application more obvious and understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the embodiments described below are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0103] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0104] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0105] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0106] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may 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.

[0107] 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.

[0108] With the rapid popularization of renewable energy and electric vehicles, the demand for batteries such as lithium-ion batteries is growing dramatically. However, due to the complex manufacturing process and physical and chemical reactions in its production process, battery failure has always been the main factor restricting its performance and reliability.

[0109] Battery failure can include many aspects, such as battery lithium deposition. 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 battery lithium deposition.

[0110] Existing battery failure analysis methods rely on a lot of production experience and physical and chemical experiments to identify and solve problems. Although some useful analysis results can sometimes be obtained, the analysis is not comprehensive overall, the accuracy of the analysis results is low, and it cannot meet the challenges of large-scale production.

[0111] To address this issue, the embodiments of the present application can comprehensively analyze battery failure cases by combining a battery failure case library and a 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.

[0112] The execution subject of the embodiments of the present application may include, but is not limited to, electronic devices such as desktop computers, notebooks, palmtop computers, and servers.

[0113] Please refer to Figure 1 , an embodiment of a battery failure analysis method in the embodiments of the present application may include:

[0114] Step S101, obtain a battery failure case to be analyzed.

[0115] In a specific implementation manner of the embodiments of the present application, the user can input the battery failure case to be analyzed into the input interface in the electronic device, and the electronic device can obtain the battery failure case from the input interface and perform subsequent battery failure analysis on it.

[0116] In another specific implementation manner of the embodiments 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.

[0117] 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).

[0118] The battery failure cases can include but are not limited to failure descriptions and failure modes. Taking the failure case of battery lithium plating as an example, the failure description can include but are not limited to description dimensions such as failure nodes, failure rates, failure surfaces, failure locations, lithium plating morphology, black spot morphology, and failure levels; the failure modes can include but are not limited to different modes such as black spots, large-area lithium plating, and corner lithium plating.

[0119] Step S102: 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.

[0120] Fault Tree Analysis (FTA) is a logical deductive analysis tool that uses a directed logic tree depicting accident causal relationships to analyze the phenomena, causes, and consequences of accidents, thereby finding measures to prevent accidents. FTA is one of the important analysis methods in system safety engineering. It can identify and evaluate the hazards of various systems, be applicable to both qualitative and quantitative analyses, and has the characteristics of simplicity and visualization, reflecting the systematicness, accuracy, and predictability of studying safety issues using system engineering methods.

[0121] In an embodiment of the present application, a fault tree for FTA analysis of battery failure can be pre-constructed and denoted as a battery failure fault tree. Among them, the specific construction process of the fault tree can refer to any one of the FTA methods in the prior art, and the embodiments of the present application do not make specific limitations thereon.

[0122] In an embodiment of the present application, a historical case library for analyzing battery failure can be pre-constructed and denoted as a battery failure case library. Among them, the battery failure case library may include historical cases of various completed battery failure analyses, and each historical case is pre-annotated with the corresponding root cause of failure.

[0123] In order to improve the accuracy of battery failure analysis, the FTA analysis method and the case library analysis method can be combined to comprehensively analyze battery failure cases, so as to obtain a more comprehensive and complete set of battery failure factors.

[0124] In a specific implementation manner of the embodiment of the present application, step S102 may specifically include as Figure 2 shown in the following process:

[0125] Step S1021: Analyze the battery failure case based on the battery failure case library to obtain a set of case library failure factors.

[0126] In a specific implementation manner of the embodiment of the present application, similar cases of the battery failure case can be selected from the battery failure case library based on the similarity between cases, and the set of case library failure factors can be determined according to the similar cases. Step S1021 may specifically include as Figure 3 shown in the following process:

[0127] Step S1021a: Calculate the case similarity between the battery failure case and each historical case in the battery failure case library respectively.

[0128] Taking any one historical case in the battery failure case library as an example, denoted as the target historical case, in a specific implementation manner of the embodiment of the present application, the failure description in the battery failure case can be extracted as the first case feature, and each description dimension in the failure description is used as one of the sub-features; similarly, the failure description in the target historical case can be extracted as the second case feature, and each description dimension in the failure description is used as one of the sub-features.

[0129] After obtaining the first case feature and the second case feature, the case similarity between the battery failure case and the target historical case can be calculated according to the first case feature and the second case feature.

[0130] In a specific implementation manner of the embodiment of the present application, the case feature distance between the first case feature and the second case feature can be calculated first.

[0131] Specifically, the sub-feature distances between the corresponding sub-features of the first case feature and the second case feature can be calculated respectively, and the sub-feature distances are weighted and summed according to the preset sub-feature weights to obtain the case feature distance.

[0132] Among them, for nominal sub-features, they can be One-Hot encoded first, and then the cosine distance is calculated for the encoded data to obtain the corresponding sub-feature distance.

[0133] For numerical sub-features, the Absolute Percentage Error (APE) can be calculated for them to obtain the corresponding sub-feature distance.

[0134] It should be noted that the above distance calculation methods are only examples. In actual applications, any distance calculation method in the prior art can be adopted according to specific situations, and the embodiment of the present application does not make specific limitations on this.

[0135] For different sub-features, corresponding weights can be assigned to them in advance according to the actual situation. Larger weights are assigned to more important sub-features, and smaller weights are assigned to unimportant sub-features. After obtaining the sub-feature distances, these preset sub-feature weights can be used to perform weighted summation on the sub-feature distances to obtain the case feature distance. In this way, more important sub-features can be strengthened, and unimportant sub-features can be weakened, thereby improving the accuracy of the final result.

[0136] After obtaining the case feature distance, the case similarity between the battery failure case and the target historical case can be determined according to the case feature distance.

[0137] Among them, the case similarity is negatively correlated with the case feature distance, that is, the larger 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. On the contrary, the smaller the case feature distance between the battery failure case and the target historical case, the larger the case similarity between the battery failure case and the target historical case.

[0138] In a specific implementation manner of the 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.

[0139] In another specific implementation of the embodiment of the present application, the inverse of the case feature distance can be calculated and used as the case similarity between the battery failure case and the target historical case.

[0140] By calculating the distance between case features to characterize the similarity between cases, an accurate measurement of case similarity can be achieved.

[0141] 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.

[0142] Among them, 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 embodiments of the present application.

[0143] Step S1021c: determine a set of failure factors of the case library based on similar cases.

[0144] 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 cases from the battery failure case library, the root causes of failure of similar cases can be obtained and summarized to obtain a set of failure factors in the case library.

[0145] pass Figure 3 The process shown can select similar cases 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.

[0146] In a specific implementation of the embodiment of the present application, the occurrence frequency of the root causes of failures of similar cases can also be counted, and the root causes of failures can be sorted in the case library failure factor set in descending order of occurrence frequency, that is, the higher the occurrence frequency of the root cause of failure, the higher its ranking, and the lower the occurrence frequency of the root cause of failure, the lower its ranking, so as to improve the efficiency of subsequent analysis.

[0147] Step S1022: Analyze the battery failure case based on the battery failure fault tree to obtain a set of fault tree failure factors.

[0148] In practical applications, any FTA method in the prior art can be used to analyze battery failure cases according to specific circumstances, and no specific limitation is made here.

[0149] In a specific implementation manner of the embodiment of the present application, the battery failure fault tree may include branches respectively corresponding to each failure mode. For example, the battery failure fault tree may include, but is not limited to, branches corresponding to the black spot failure mode, branches corresponding to the large area lithium plating failure mode, branches corresponding to the corner lithium plating failure mode, etc.

[0150] When analyzing a battery failure case based on the battery failure fault tree, the failure mode in the battery failure case can be extracted, and the branch corresponding to the failure mode can be determined in the battery failure fault tree and denoted as the target branch. Subsequently, it is not necessary to analyze the battery failure case based on the entire battery failure fault tree, but only to perform fault tree analysis on the battery failure case based on the target branch, thereby obtaining a set of fault tree failure factors. Such a method has stronger pertinence, narrows the analysis scope, and effectively improves the analysis efficiency.

[0151] Step S1023: Determine the battery failure factor set according to the case library failure factor set and the fault tree failure factor set.

[0152] Since there are many failure factors that cause battery failure, possibly more than hundreds, only the relatively important failure factors will be included in the preset database. For the sake of easy distinction, the failure factors already included in the database can be denoted as online factors here, and the failure factors not included in the database can be denoted as offline factors.

[0153] 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 factors and offline factors. For the sake of easy distinction, the offline factor set in the fault tree failure factor set can be denoted as the fault tree offline factor set here, and the online factor set in the fault tree failure factor set can be denoted as the fault tree online factor set.

[0154] For the fault tree online factor set, the analysis indexes of each failure factor therein can be calculated respectively. Among them, the analysis indexes can include, but are not limited to, indexes such as distribution difference, equipment concentration, film roll concentration, time concentration, etc.

[0155] By combining the case library failure factor set and the fault tree offline factor set, an offline factor set can be obtained. Similar to the online factors, the analysis indexes of each failure factor in the offline factor set can be calculated respectively. Among them, the analysis indexes can include, but are not limited to, indexes such as distribution difference, equipment concentration, film roll concentration, time concentration, etc.

[0156] After determining the offline factor set and the fault tree online factor set, the offline factor set and the fault tree online factor set can be combined to obtain the battery failure factor set.

[0157] Through Figure 2The process shown can obtain the set of case base failure factors based on the analysis of the battery failure case base, obtain the set of fault tree failure factors based on the analysis of the battery failure fault tree, and obtain a more comprehensive set of battery failure factors by comprehensively considering the two.

[0158] Step S103: Determine the battery failure analysis result according to the set of battery failure factors.

[0159] In a specific implementation manner of the embodiment of the present application, machine learning can be used for battery failure analysis to improve the overall analysis efficiency. Step S103 may specifically include the process as Figure 4 shown:

[0160] Step S1031: Construct a data table of battery failure cases according to the set of battery failure factors.

[0161] For all the data in the battery failure cases, the online factors and offline factors in the set of battery failure factors can be combined according to certain rules to construct a data table of battery failure cases. Among them, the specific rules can be set according to the actual situation. For example, it may include but is not limited to the rules of cell barcode matching, JR (Jelly Roll) matching, film roll matching, etc.

[0162] In a specific implementation manner of the embodiment of the present application, after constructing the data table, a preset data cleaning method can also be used to clean the data in the data table to obtain a cleaned data table.

[0163] The specific data cleaning method can be set according to the actual situation, and the embodiment of the present application does not make specific limitations in this regard. For example, it may include but is not limited to cleaning operations such as removing parameters without differences in the data table, removing parameters with data missing exceeding a set threshold, and removing rows or columns containing missing values (i.e., dropna).

[0164] By pre-cleaning the data table, a large amount of invalid data can be cleaned, avoiding interference with the analysis process and effectively improving the accuracy of the final battery failure analysis result.

[0165] In a specific implementation manner of the embodiment of the present application, a preset data feature selection method can also be used to select data features in the data table to obtain a data table after feature selection.

[0166] The specific data feature selection method can be set according to the actual situation, and the embodiment of the present application does not make specific limitations in this regard. For example, it may include but is not limited to feature selection methods such as recursive feature elimination method, Selectfrommodel, etc.

[0167] By pre-selecting data features, parameters with poor classification and regression effects can be eliminated, reducing the dimensionality of the data and thus improving the analysis efficiency.

[0168] Step S1032: Construct a machine learning model based on the data table to obtain the constructed target model.

[0169] 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, thereby obtaining the final target model.

[0170] Specifically, which machine learning model to adopt can be set according to the actual situation, and the embodiments of the present application do not make specific limitations in this regard. For example, it may include but is not limited to: decision tree, random forest, XGBoost and other models.

[0171] Step S1033: Determine the importance ranking of data features in the data table according to the target model.

[0172] After obtaining the target model, the importance of each feature (i.e., failure factor) in the data table can be ranked using the target model to determine its influence on the final result.

[0173] Specifically, for a decision tree, the importance of a feature can be evaluated according to the number of node splits or information gain of the feature in the decision tree; for a random forest, the Out-of-Bag (OOB) error can be used to evaluate the importance of a feature; for XGBoost, the average number of splits of a feature on each weak learner or the reduction in loss brought by the feature to the model can be used to evaluate the importance of a feature.

[0174] Step S1034: Determine the battery failure analysis result according to the importance ranking of data features.

[0175] In a specific implementation manner of the embodiments of the present application, after the electronic device determines the importance ranking of data features, it 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 difference, device concentration, film roll concentration, and time concentration.

[0176] The user can verify based on the output result of the electronic device through manual inspection, correct to obtain the final battery failure analysis result, and propose corresponding solutions.

[0177] Figure 5The figure shows a schematic diagram of the output result of the electronic device. As shown in the figure, the data feature importance ranking is: failure factor A, failure factor B, failure factor C, failure factor D, failure factor E, failure factor F, …… After the user verifies it 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 man-machine interaction interface.

[0178] In a specific implementation manner of the embodiment of the present application, after the electronic device obtains the final battery failure analysis result, it can also update the battery failure case library and the battery failure fault tree according to the battery failure analysis result.

[0179] Specifically, the current battery failure case can be added to the battery failure case library as a new historical case, and its corresponding failure root cause can be marked according to the battery failure analysis result; the missing failure factors in the battery failure fault tree can also be fed back and complemented according to the battery failure analysis result, thus realizing the closed-loop of the analysis process, continuously enriching the battery failure case library and the battery failure fault tree, and providing a more complete basis for subsequent battery failure case analysis.

[0180] In summary, the embodiment of the present application obtains the battery failure case to be analyzed; analyzes the battery failure case based on the preset battery failure case library and the preset battery failure fault tree to obtain the battery failure factor set; determines the battery failure analysis result according to the battery failure factor set. Through the embodiment of the present application, the battery failure case can be comprehensively analyzed in combination with the battery failure case library and the battery failure fault tree, so that a more comprehensive battery failure factor set can be analyzed, and the accuracy of the final battery failure analysis result can be effectively improved.

[0181] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

[0182] Corresponding to the battery failure analysis method described in the above embodiment, Figure 6 The figure shows a structural diagram of an embodiment of a battery failure analysis device provided by the embodiment of the present application.

[0183] In this embodiment, a battery failure analysis device may include:

[0184] A battery failure case acquisition module 601, configured to acquire a battery failure case to be analyzed;

[0185] A battery failure analysis module 602, configured to 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;

[0186] The battery failure analysis result determination module 603 is configured to determine the battery failure analysis result according to the battery failure factor set.

[0187] In a specific implementation manner of the embodiment of the present application, the battery failure analysis module may include:

[0188] The battery failure case library analysis sub-module is configured to analyze the battery failure cases based on the battery failure case library to obtain the case library failure factor set;

[0189] The battery failure fault tree analysis sub-module is configured to analyze the battery failure cases based on the battery failure fault tree to obtain the fault tree failure factor set;

[0190] The battery failure factor set determination sub-module is configured to determine the battery failure factor set according to the case library failure factor set and the fault tree failure factor set.

[0191] In a specific implementation manner of the embodiment of the present application, the battery failure case library analysis sub-module may include:

[0192] The case similarity calculation unit is configured to calculate the case similarity between the battery failure case and each historical case in the battery failure case library respectively;

[0193] The similar case selection unit is configured to select the historical cases with the case similarity greater than the preset similarity threshold from the battery failure case library as the similar cases of the battery failure case;

[0194] The case library failure factor set determination unit is configured to determine the case library failure factor set according to the similar cases.

[0195] In a specific implementation manner of the embodiment of the present application, the case similarity calculation unit may include:

[0196] The first case feature extraction sub-unit is configured to extract the first case feature in the battery failure case;

[0197] The second case feature extraction sub-unit is configured to extract the second case feature in the target historical case; wherein, the target historical case is any historical case in the battery failure case library;

[0198] The case similarity calculation sub-unit is configured to calculate the case similarity between the battery failure case and the target historical case according to the first case feature and the second case feature.

[0199] In a specific implementation manner of the embodiment of the present application, the case similarity calculation sub-unit may specifically be used to: calculate the 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 according to the case feature distance.

[0200] In a specific implementation manner of the embodiment of the present application, the case similarity calculation sub-unit may specifically be used to: calculate the sub-feature distances between the respective corresponding sub-features of the first case feature and the second case feature; perform weighted summation on the respective sub-feature distances according to the preset sub-feature weights to obtain the case feature distance.

[0201] In a specific implementation manner of the embodiment of the present application, the case library failure factor set determination unit may specifically be used to: obtain the failure root causes of the similar cases; summarize the failure root causes to obtain the case library failure factor set.

[0202] In a specific implementation manner of the embodiment of the present application, the battery failure fault tree analysis sub-module may specifically be used to: extract the failure modes in the battery failure cases; determine the target branches corresponding to the failure modes in the battery failure fault tree; perform fault tree analysis on the battery failure cases based on the target branches to obtain the fault tree failure factor set.

[0203] In a specific implementation manner of the embodiment of the present application, the battery failure factor set determination sub-module may specifically be used to: combine the case library failure factor set and the fault tree offline factor set to obtain the offline factor set; where 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 the battery failure factor set; where the fault tree online factor set is the online factor set in the fault tree failure factor set.

[0204] In a specific implementation manner of the embodiment of the present application, the battery failure analysis result determination module may include:

[0205] A data table construction sub-module, configured to construct a data table of the battery failure cases according to the battery failure factor set;

[0206] A target model construction sub-module, configured to construct a machine learning model according to the data table to obtain the constructed target model;

[0207] A data feature importance ranking sub-module, configured to determine the data feature importance ranking in the data table according to the target model;

[0208] A battery failure analysis result determination sub-module, configured to determine the battery failure analysis result according to the data feature importance ranking.

[0209] In a specific implementation manner of the embodiment of the present application, the battery failure analysis result determination module may further include:

[0210] A data feature selection sub-module, configured to perform data feature selection in a data table using a preset data feature selection method to obtain a selected data table.

[0211] In a specific implementation manner of the embodiment of the present application, the battery failure analysis result determination module may further include:

[0212] A data cleaning sub-module, configured to perform data cleaning in a data table using a preset data cleaning method to obtain a cleaned data table.

[0213] In a specific implementation manner of the embodiment of the present application, the battery failure analysis device may further include:

[0214] A case library and fault tree update module, configured to update the battery failure case library and the battery failure fault tree according to the battery failure analysis result.

[0215] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices, modules, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0216] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0217] Figure 7 The schematic block diagram of an electronic device provided by the embodiment of the present application is shown. For the convenience of description, only the parts related to the embodiment of the present application are shown.

[0218] As Figure 7 shown, 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, the steps in the above-mentioned various battery failure analysis method embodiments are implemented, such as Figure 1 the steps S101 to S103 shown. Alternatively, when the processor 70 executes the computer program 72, the functions of the various modules / units in the above-mentioned device embodiments are implemented, such as Figure 6 the functions of the modules 601 to 603 shown.

[0219] Exemplarily, the computer program 72 can be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 72 in the electronic device 7.

[0220] The electronic device 7 can be a computing device such as a desktop computer, a notebook, a palm computer, a server, etc. Those skilled in the art can understand that Figure 7 merely examples of the electronic device 7, which do not constitute a limitation to the electronic device 7, may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the electronic device 7 may further include input / output devices, network access devices, a bus, etc.

[0221] The processor 70 can be a central processing unit (CPU), or can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0222] The memory 71 can be an internal storage unit of the electronic device 7, such as the hard disk or memory of the electronic device 7. The memory 71 can also be an external storage device of the electronic device 7, such as a plug-in hard disk equipped on the electronic device 7, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 71 can also include both the internal storage unit and the external storage device of the electronic device 7. The memory 71 is used to store the computer program and other programs and data required by the electronic device 7. The memory 71 can also be used to temporarily store the data that has been output or will be output.

[0223] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0224] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0225] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0226] In the embodiments provided in this application, it should be understood that the disclosed device / electronic device and method can be implemented in other ways. For example, the device / electronic device embodiments described above are only illustrative. For example, the division of the module or unit is only a logical function division. In actual implementation, there can be other division methods. For example, 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 displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0227] The unit described as a separate component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0228] In addition, in each embodiment of the present application, each functional unit can be integrated into a 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 a software functional unit.

[0229] 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 such an understanding, all or part of the processes in the above-mentioned embodiment methods of the present application can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable storage medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included 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, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0230] The above-mentioned 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 foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for analyzing battery failure, characterized in that, it includes: Obtaining a battery failure case to be analyzed; Analyzing the battery failure case based on a preset battery failure case library and a preset battery failure fault tree to obtain a set of battery failure factors; Determining a battery failure analysis result according to the set of battery failure factors.

2. The method for analyzing battery failure according to claim 1, characterized in that, The analyzing the battery failure case based on a preset battery failure case library and a preset battery failure fault tree to obtain a set of battery failure factors includes: Analyzing the battery failure case based on the battery failure case library to obtain a set of case library failure factors; Analyzing the battery failure case based on the battery failure fault tree to obtain a set of fault tree failure factors; Determining the set of battery failure factors according to the set of case library failure factors and the set of fault tree failure factors.

3. The method for analyzing battery failure according to claim 2, characterized in that, The analyzing the battery failure case based on the battery failure case library to obtain a set of case library failure factors includes: Calculating the case similarity between the battery failure case and each historical case in the battery failure case library respectively; Selecting, from the battery failure case library, a historical case with a case similarity greater than a preset similarity threshold as a similar case of the battery failure case; Determining the set of case library failure factors according to the similar cases.

4. The method for analyzing battery failure according to claim 3, characterized in that, The calculating the case similarity between the battery failure case and each historical case in the battery failure case library respectively includes: Extracting first case features in the battery failure case; Extracting second case features in a target historical case; wherein, the target historical case is any historical case in the battery failure case library; Calculating the case similarity between the battery failure case and the target historical case according to the first case features and the second case features.

5. The method for analyzing battery failure according to claim 4, characterized in that, The calculating the case similarity between the battery failure case and the target historical case according to the first case features and the second case features includes: Calculating the case feature distance between the first case features and the second case features; Determining the case similarity between the battery failure case and the target historical case according to the case feature distance.

6. The method for analyzing battery failure according to claim 5, characterized in that, The calculating the case feature distance between the first case features and the second case features includes: Calculating the sub-feature distance between each corresponding sub-feature of the first case features and the second case features respectively; Performing weighted summation on each sub-feature distance according to a preset sub-feature weight to obtain the case feature distance.

7. The method for analyzing battery failure according to any one of claims 3 to 6, characterized in that, Determining the set of case base failure factors according to the similar cases includes: Obtaining the root cause of failure of the similar cases; Summarizing the root causes of failure to obtain the set of case base failure factors.

8. The battery failure analysis method according to any one of claims 2 to 7, wherein, Analyzing the battery failure cases based on the battery failure fault tree to obtain a set of fault tree failure factors, including: Extracting the failure modes in the battery failure cases; Determining the target branches corresponding to the failure modes in the battery failure fault tree; Performing fault tree analysis on the battery failure cases based on the target branches to obtain the set of fault tree failure factors.

9. The battery failure analysis method according to any one of claims 2 to 8, wherein, Determining the set of battery failure factors according to the set of case base failure factors and the set of fault tree failure factors includes: Combining the set of case base failure factors and the set of offline factors of the fault tree to obtain a set of offline factors; wherein, the set of offline factors of the fault tree is the set of offline factors in the set of fault tree failure factors; Combining the set of offline factors and the set of online factors of the fault tree to obtain the set of battery failure factors; wherein, the set of online factors of the fault tree is the set of online factors in the set of fault tree failure factors.

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

11. The battery failure analysis method according to claim 10, wherein, Before constructing the machine learning model according to the data table, it further includes: Performing data feature selection in the data table using a preset data feature selection method to obtain the data table after selection.

12. The battery failure analysis method according to claim 10 or 11, wherein, Before constructing the machine learning model according to the data table, it further includes: Performing data cleaning in the data table using a preset data cleaning method to obtain the data table after cleaning.

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 set of battery failure factors, it further includes: Updating the battery failure case base and the battery failure fault tree according to the battery failure analysis result.

14. A battery failure analysis device, wherein, It includes: A battery failure case acquisition module for acquiring battery failure cases to be analyzed; A battery failure analysis module, configured to analyze battery failure cases based on a preset battery failure case library and a preset battery failure fault tree, so as to obtain a set of battery failure factors; A battery failure analysis result determination module, configured to determine a battery failure analysis result according to the set of battery failure factors.

15. A computer-readable storage medium storing a computer program, characterized in that, 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, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, the steps of the battery failure analysis method according to any one of claims 1 to 13 are implemented.

Images