Battery failure analysis method and device, equipment, storage medium and program product

Abstract

The invention relates to a battery failure analysis method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a failure mode and a first failure characteristic of a target battery; wherein the failure characteristics are used for representing observable failure phenomena; determining a target failure analysis tree according to the failure mode, and performing factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set; wherein the failure factor set comprises at least one first failure factor, the failure analysis tree is constructed in advance based on a plurality of second failure factors and a plurality of second failure features, and the failure factors are used for representing failure causes; performing data acquisition according to the failure factor set to obtain production process data; and performing statistical processing on the production process data, and determining a failure reason of the target battery. By adopting the method, the failure analysis speed can be increased, and the failure reason positioning efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of battery failure analysis, and in particular to a battery failure analysis method, device, equipment, storage medium and program product. Background Art

[0002] Battery production is a complex and delicate process, involving stirring, coating, slitting, winding / stacking, formation, assembly and other processes. The production process, equipment status, personnel quality, product design, raw material quality, storage conditions, etc. determine the quality of the final product. Battery failure is mainly divided into two categories: performance failure and safety failure; among them, performance failure refers to the failure of battery performance to meet the requirements and indicators, mainly including capacity attenuation or diving, short cycle life, etc.; safety failure refers to the failure of the battery due to improper use and the risk of failure, mainly including lithium precipitation, leakage, swelling, etc. The battery production cycle is long, and abnormalities or combinations in each link may lead to product quality problems. Failure analysis is to find the root cause of the failure of defective products, so as to solve the problem and avoid the problem from happening again.

[0003] At present, most of the analysis methods for battery failure are aimed at specific failure phenomena, relying on personal experience to decide whether to disassemble the battery, collect certain process data for data analysis, and locate the cause of failure. However, the above methods are prone to problems such as slow failure analysis speed and low efficiency in locating failure causes due to lack of experience. Summary of the invention

[0004] Based on the above problems, the present application provides a battery failure analysis method, device, equipment, storage medium and program product, which can improve the failure analysis speed and improve the efficiency of locating the cause of failure.

[0005] In a first aspect, the present application provides a battery failure analysis method, the method comprising: obtaining a failure mode and a first failure feature of a target battery; wherein the failure feature is used to characterize an observable failure phenomenon; determining a target failure analysis tree according to the failure mode, and performing factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set; wherein the failure factor set includes at least one first failure factor, the failure analysis tree is pre-constructed based on multiple second failure factors and multiple second failure features, and the failure factor is used to characterize the cause of the failure; data is collected according to the failure factor set to obtain production process data; and statistical processing is performed on the production process data to determine the cause of the failure of the target battery.

[0006] In the technical solution of the embodiment of the present application, a set of failure factors, that is, the failure causes to be investigated, can be quickly and accurately obtained based on the failure phenomenon and failure analysis tree of the target battery. Data collection and statistical analysis are automatically performed based on the failure causes to be investigated without relying on personal experience. Therefore, the failure analysis speed can be improved, as well as the efficiency of locating the failure causes.

[0007] In some embodiments, the failure analysis tree includes a root node and multiple child nodes; the root node represents the failure mode, the child nodes include a failure factor node and a failure feature node, and the failure feature node is provided with a second failure feature; factor matching processing is performed in the target failure analysis tree according to the first failure feature to obtain a failure factor set, including: selecting a failure factor node from the child nodes of the root node of the target failure analysis tree as the target node; in the case where the child nodes of the target node contain a failure feature node, matching the first failure feature with each second failure feature corresponding to the target node to obtain a matching result; determining a troubleshooting node according to the matching result, and reselecting the target node; after traversing each child node of the target failure analysis tree, determining the failure factor set according to the determined troubleshooting node. In the technical solution of the embodiment of the present application, traversing each child node of the target failure analysis tree can quickly and accurately recommend the cause to be troubleshooted, does not rely on personal experience, can improve the accuracy of the analysis of the failure cause, and automatic search can also improve the speed of the analysis of the failure cause.

[0008] In some embodiments, determining the investigation node according to the matching result, and reselecting the target node include: when the matching result meets the preset matching condition, determining the target node as the investigation node, if the investigation node has child nodes, reselecting a failure factor node from the child nodes of the investigation node as the target node, and executing the steps after selecting the target node, if the investigation node has no child nodes, returning to the parent node of the investigation node to reselect the target node; when the matching result does not meet the preset matching condition, if the target node has a node of the same level, reselecting a failure factor node from the node of the same level as the target node, and executing the steps after selecting the target node; if the target node has no node of the same level, returning to the parent node of the target node to reselect the target node. In the technical solution of the embodiment of the present application, each child node of the target failure analysis tree is traversed, and according to whether the matching result meets the preset matching condition, the cause to be investigated can be quickly and accurately recommended, which does not rely on personal experience, can improve the accuracy of the analysis of the failure cause, and the automatic search can also improve the speed of the analysis of the failure cause.

[0009] In some embodiments, the method further includes: in the case where the child nodes of the target node do not contain a failure characteristic node, determining the target node as a check node; if the target node has a peer node, reselecting a failure factor node from the peer nodes of the target node as the target node, and executing the steps after selecting the target node; if the target node has no peer node, returning to the parent node of the target node to reselect the target node. In the technical solution of the embodiment of the present application, each child node of the target failure analysis tree is traversed, and the cause to be checked can be quickly and accurately recommended based on whether it contains a failure characteristic node, which does not rely on personal experience, can improve the accuracy of the analysis of the failure cause, and the automatic search can also improve the speed of the analysis of the failure cause.

[0010] In some embodiments, matching the first failure feature with each second failure feature corresponding to the target node to obtain a matching result includes: obtaining the weight of each second failure feature corresponding to the target node; matching the first failure feature with each second failure feature corresponding to the target node to obtain the probability of each second failure feature; calculating the probability of the target node according to the weight and probability of each second failure feature, and determining the probability of the target node as the matching result. In the technical solution of the embodiment of the present application, the probability of each second failure feature is determined according to the first failure feature, the cause of the failure can be accurately matched, and items to be checked can be recommended, which provides a basis for subsequent data collection, can improve the efficiency of failure analysis, and improve the efficiency of locating the cause of failure.

[0011] In some embodiments, statistical processing is performed on production process data to determine the failure cause of the target battery, including: calculating the defect rate of each first failure factor in the failure factor set according to the production process data; statistically processing the defect rates of multiple first failure factors to obtain the failure cause of the target battery. In the technical solution of the embodiment of the present application, automatic data statistics can improve the efficiency of data analysis, thereby improving the efficiency of failure analysis.

[0012] In some embodiments, statistical processing is performed on the defect rates of multiple first failure factors to obtain the failure cause of the target battery, including: selecting m first failure factors in order of defect rates from high to low; m is a positive integer; when the defect rates of the selected m first failure factors meet the concentration condition, the m first failure factors are determined as the failure cause of the target battery. In the technical solution of the embodiment of the present application, the failure factors with concentration in the production process data are located according to the element concentration calculation method, which can improve the efficiency and accuracy of locating the failure cause.

[0013] In some embodiments, the method further includes: obtaining the on-site verification result of the failure cause of the target battery; if the on-site verification result is not passed, excluding the verified failure cause, and returning to the step of performing statistical processing on the production process data. In the technical solution of the embodiment of the present application, the real failure cause of the target battery can be further determined through on-site verification, and the failure analysis tree can be improved to provide a more accurate basis for subsequent failure analysis.

[0014] In a second aspect, the present application also provides a battery failure analysis device, the device comprising:

[0015] A feature acquisition module, used to acquire the failure mode and the first failure feature of the target battery;

[0016] A cause analysis module, used to determine a target failure analysis tree according to the failure mode, and perform factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set; wherein the failure factor set includes at least one first failure factor, and the failure analysis tree is pre-constructed based on a plurality of second failure factors and a plurality of second failure features; the first failure feature and the second failure feature are used to characterize the failure phenomenon, and the first failure factor and the second failure factor are used to characterize the failure cause;

[0017] A data acquisition module is used to collect data according to the failure factor set to obtain production process data;

[0018] The cause determination module is used to perform statistical processing on the production process data to determine the failure cause of the target battery.

[0019] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any one of the methods in the first aspect when executing the computer program.

[0020] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method of any one of the first aspects is implemented.

[0021] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements any one of the methods in the first aspect when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the optional embodiments below. The accompanying drawings are only used for the purpose of illustrating the optional embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0023] Figure 1 This is a schematic diagram of an application environment of a battery failure analysis method according to an embodiment of the present application;

[0024] Figure 2 is a flow chart of a battery failure analysis method according to an embodiment of the present application;

[0025] Figure 3 is a schematic diagram of a failure analysis tree of an embodiment of the present application;

[0026] Figure 4 This is one of the flowcharts of the factor matching processing steps of an embodiment of the present application;

[0027] Figure 5 This is the second flow chart of the factor matching processing step of an embodiment of the present application;

[0028] Figure 6 This is the third flowchart of the factor matching processing step of an embodiment of the present application;

[0029] Figure 7 is a schematic diagram of a troubleshooting factor recommendation process according to an embodiment of the present application;

[0030] Figure 8 It is a flowchart of the failure feature matching processing steps of an embodiment of the present application;

[0031] Fig. 9 It is a flowchart of the steps of statistical processing of production process data in one embodiment of the present application;

[0032] Fig.10 It is a flowchart of the defect rate statistical processing steps of an embodiment of the present application;

[0033] Fig.11 A flow chart of the on-site verification processing steps of an embodiment of the present application;

[0034] Fig.12 is a structural block diagram of a battery failure analysis device according to an embodiment of the present application;

[0035] Fig.13 is a structural block diagram of a battery failure analysis device according to another embodiment of the present application;

[0036] Fig.14 It is a diagram of the internal structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0037] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0039] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0040] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0041] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0042] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0043] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0044] Battery production is a complex and delicate process, involving mixing, coating, slitting, winding / stacking, formation, assembly and other processes. The production process, equipment status, personnel quality, product design, raw material quality, storage conditions and other factors determine the quality of the final product. Battery production has a long cycle, and abnormalities or combinations in each link may lead to product quality problems. Failure analysis is to find the root cause of failure from defective products, so as to solve the problem and prevent it from happening again.

[0045] At present, most of the analysis methods for battery failure are aimed at specific failure phenomena, relying on personal experience to decide whether to disassemble the battery, collect certain process data for data analysis, and locate the cause of failure. For example, for battery swelling, personal experience is used to decide to disassemble the battery, and formation data and assembly data are collected, so as to locate the cause of failure based on the results of battery disassembly, formation data and assembly data; or, for lithium analysis, personal experience is used to decide to disassemble the battery, and coating data and formation data are collected, so as to locate the cause of failure based on the results of battery disassembly, coating data and formation data. It can be seen that the above method relies too much on personal experience. If there is insufficient experience, it will lead to problems such as slow failure analysis speed and low efficiency in locating failure causes.

[0046] In response to the above problems, an embodiment of the present application provides a battery failure analysis method, which obtains the failure mode and the first failure feature of the target battery; determines the target failure analysis tree according to the failure mode, and performs factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set; performs data collection according to the failure factor set to obtain production process data; and performs statistical processing on the production process data to determine the failure cause of the target battery. In the technical solution of the embodiment of the present application, a failure factor set, i.e., the failure cause to be investigated, can be obtained quickly and accurately according to the failure phenomenon of the target battery and the failure analysis tree, and data collection and statistical analysis are automatically performed according to the failure cause to be investigated, which does not rely on personal experience, thereby improving the failure analysis speed and the efficiency of locating the failure cause.

[0047] The battery failure analysis method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. The application environment includes a terminal 102 and a server 104, wherein the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on a cloud or other network server. The terminal 102 can obtain the failure mode and the first failure feature of the target battery; determine the target failure analysis tree according to the failure mode, and determine the failure cause of the target battery according to the first failure feature and the target failure analysis tree. After obtaining the failure mode and the first failure feature of the target battery, the terminal 102 can also send the failure mode and the first failure feature to the server 104, and the server determines the target failure analysis tree according to the failure mode, and determines the failure cause of the target battery according to the first failure feature and the target failure analysis tree. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0048] According to some embodiments of the present application, referring to Figure 2 , a battery failure analysis method is provided, which is applied to Figure 1 Taking the terminal in as an example, the following steps may be included:

[0049] Step 201, obtaining a failure mode and a first failure feature of a target battery.

[0050] Among them, failure modes are used to characterize the general classification of failure causes, including poor K value, lithium precipitation, battery cell bulging, etc. Failure characteristics are used to characterize observable failure phenomena, including appearance damage, excessive element composition, abnormal monitoring indicators, etc. Failure characteristics can be obtained through observation, disassembly, experiments, etc. In addition, failure characteristics can be obtained multiple times. For example, observable failure characteristics are extracted first, and then extracted after disassembly and experiments. The first failure feature is used to characterize the failure phenomenon of the target battery.

[0051] The terminal can provide a failure analysis program. After the failure analysis program is started, the terminal displays a failure analysis interface. The failure analysis interface may include a failure mode input area and a failure feature input area. The staff can enter the failure mode of the target battery in the failure mode input area and enter the first failure feature of the target battery in the failure feature input area. Alternatively, the staff selects the failure mode of the target battery based on the failure mode input area and selects the first failure feature of the target battery based on the failure feature input area. The terminal can obtain the failure mode and the first failure feature of the target battery based on the input operation or selection operation of the staff.

[0052] In other embodiments, the terminal displays a failure analysis interface in the form of a web page, and obtains the failure mode and the first failure feature of the target battery based on the failure analysis interface.

[0053] It should be noted that the manner in which the terminal obtains the failure mode and the first failure feature is not limited to the above example, and in practical applications, other manners may also be used.

[0054] Step 202 : determining a target failure analysis tree according to the failure mode, and performing factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set.

[0055] Among them, the failure factor is used to characterize the failure cause, and the failure cause is hierarchical. For example, the failure cause includes the first-level cause and the second-level cause. The second-level cause is the specific cause of the first-level cause. The higher the cause level, the more accurate it is. There are many kinds of failure causes, such as equipment abnormality, operation abnormality, raw material abnormality, design structure, etc.

[0056] The failure factor set includes at least one first failure factor, that is, the failure factor set includes a failure cause of at least one target battery.

[0057] The failure analysis tree is pre-constructed based on multiple second failure factors and multiple second failure features, that is, the failure analysis tree includes multiple levels of failure causes and failure phenomena corresponding to each failure cause. For example, the failure analysis tree includes failure factors A and B, where failure factor A corresponds to failure features t1 and t2, and the sub-factors of failure factor A include A-1, A-2, and A-3, and failure factor A-1 corresponds to failure feature t1; failure factor B corresponds to failure features t1, t4, and t5, and the sub-factors of failure factor B include B-1, B-2, and B-3.

[0058] After obtaining the failure mode of the target battery, the terminal searches for the target failure analysis tree corresponding to the failure mode of the target battery from the pre-created multiple failure analysis trees according to the correspondence between the failure analysis tree and the failure mode. For example, failure analysis tree 1 corresponding to poor K value, failure analysis tree 2 corresponding to lithium deposition, and failure analysis tree 3 corresponding to cell swelling are pre-established. If the failure mode of the target battery is poor K value, then according to the correspondence between the failure analysis tree and the failure mode, it can be determined that the target failure analysis tree corresponding to the target battery is failure analysis tree 1.

[0059] After determining the target failure analysis tree corresponding to the target battery, the first failure feature of the target battery is matched with the second failure features corresponding to each second failure factor in the target failure analysis tree to obtain a failure factor set. For example, the first failure feature of the target battery includes t1 and t4, and the second failure features t1 and t4 are found in the target failure analysis tree. According to the second failure feature t1, it is determined that the failure factor set includes failure factor A-1, and according to the second failure feature t4, it is determined that the failure factor set includes failure factor B.

[0060] Step 203: collect data according to the failure factor set to obtain production process data.

[0061] Among them, production process data includes data on equipment, raw materials, processes, workstations, etc. that the product passes through. Production process data can be divided into structured data and unstructured data. Structured data is standard data generated by various software systems, including MES systems, ERP systems, Scada systems, etc. Unstructured data includes process files, experimental files, etc.

[0062] The terminal can create an analysis task based on the failure factor set, and the analysis task includes data collection parameters defined by each first failure factor in the failure factor set. The analysis task is automatically started, or the analysis task is started based on a start operation input by a staff member, and the terminal performs data collection based on the analysis task to obtain production process data.

[0063] For example, the terminal obtains data from the MES system according to the analysis task, and obtains process files, experimental files, etc. from the preset folder.

[0064] In some embodiments, when determining the failure factor set, the terminal can obtain the failure matching degree between each first failure factor and the second failure factor in the target failure analysis tree. When performing data collection, data collection is performed for each first failure factor in order from high to low failure matching degrees. It can be understood that by performing data collection in the above order, data collection can be performed preferentially on failure causes with high failure matching degrees, so as to preferentially perform statistical analysis on these data, thereby improving the failure analysis speed and efficiency, improving product quality, and reducing production costs.

[0065] Step 204, statistically process the production process data to determine the failure cause of the target battery.

[0066] Statistical processing is performed on the production process data of each first failure factor to obtain the probability corresponding to each first failure factor; and the failure cause of the target battery is determined according to the probability corresponding to each first failure factor.

[0067] For example, by statistically processing the production process data, it is found that the probability corresponding to the first failure factor A-1 is a%, and the probability corresponding to the first failure factor B is b%. Since a%>b%, A-1 is determined as the failure cause of the target battery.

[0068] In the above embodiment, the failure mode and the first failure feature of the target battery are obtained; the target failure analysis tree is determined according to the failure mode, and factor matching processing is performed in the target failure analysis tree according to the first failure feature to obtain a failure factor set; data is collected according to the failure factor set to obtain production process data; the production process data is statistically processed to determine the failure cause of the target battery. In the technical solution of the embodiment of the present application, the failure factor set, that is, the failure cause to be investigated, can be quickly and accurately obtained according to the failure phenomenon of the target battery and the target failure analysis tree, and data collection and statistical analysis are automatically performed according to the failure cause to be investigated, which does not rely on personal experience, thereby improving the failure analysis speed and the efficiency of locating the failure cause.

[0069] According to some embodiments of the present application, referring to Figure 3 The failure analysis tree includes a root node and multiple child nodes; the root node represents the failure mode, the child nodes include a failure factor node and a failure feature node, and the failure feature node is provided with the second failure feature.

[0070] The terminal displays the failure analysis interface, which also includes an analysis tree configuration area. The staff can input the failure mode, multiple failure causes, and the failure phenomenon corresponding to each failure cause based on the analysis tree configuration area. The terminal obtains the content input by the staff, creates a failure analysis tree based on the content input by the staff, and configures the failure analysis tree.

[0071] For example, the terminal configures the failure mode input by the staff as the root node of the failure analysis tree, configures the failure cause as the failure factor node, and configures the failure phenomenon as the failure feature node.

[0072] It can be understood that different failure analysis trees can be created for different failure modes.

[0073] Reference Figure 4 In the above embodiment, “performing factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set” may include the following steps:

[0074] Step 301 : Select a failure factor node from the child nodes of the root node of the target failure analysis tree as a target node.

[0075] Reference Figure 3The child nodes of the root node include failure factor nodes A, B, C, and D, and one of the failure factor nodes is used as the target node. For example, failure factor node A is used as the target node, or failure factor node B is used as the target node.

[0076] Step 302: When the child node of the target node contains a failure feature node, the first failure feature is matched with each second failure feature corresponding to the target node to obtain a matching result.

[0077] Assuming that failure factor node A is the target node, and the child nodes of failure factor node A contain failure feature nodes, the first failure feature of the target battery is matched with the second failure features t1 and t2 corresponding to failure factor node A to obtain a matching result.

[0078] Assuming that the failure factor node B is the target node, and the child nodes of the failure factor node B contain failure feature nodes, the first failure feature of the target battery is matched with the second failure features t1, t4, and t5 corresponding to the failure factor node B to obtain a matching result.

[0079] The matching of other failure factor nodes will not be described in detail here.

[0080] Step 303, determine the check node according to the matching result, and reselect the target node.

[0081] When the matching result meets the preset matching conditions, the target node is determined as the troubleshooting node. If the troubleshooting node has child nodes, a failure factor node is reselected from the child nodes of the troubleshooting node as the target node, and the steps after selecting the target node are executed. If the troubleshooting node has no child nodes, the parent node of the troubleshooting node is returned to reselect the target node.

[0082] When the matching result does not meet the preset matching conditions, if the target node has a sibling node, a failure factor node is reselected from the sibling nodes of the target node as the target node, and the steps after selecting the target node are executed. If the target node has no sibling node, the parent node of the target node is returned to reselect the target node.

[0083] Step 304: after traversing all child nodes of the target failure analysis tree, determine a failure factor set according to the determined troubleshooting nodes.

[0084] Each child node of the target failure analysis tree is traversed according to the above steps. After the traversal is completed, at least one determined investigation node can be obtained. The investigation node corresponds to the failure factor node one by one. The failure factor set can be obtained by summarizing the investigation nodes.

[0085] In the aggregation process, the failure factor nodes can be screened. For example, failure factor nodes A and A-1 are both screening nodes. Since failure factor node A-1 is a child node of failure factor node A, failure factor node A can be eliminated and failure factor node A-1 can be aggregated into the failure factor set.

[0086] In the above embodiment, a failure factor node is selected from the child nodes of the root node of the target failure analysis tree as the target node; when the child nodes of the target node contain failure feature nodes, the first failure feature is matched with each second failure feature corresponding to the target node to obtain a matching result; when the matching result meets the preset matching condition, the target node is determined as a troubleshooting node, if the troubleshooting node has child nodes, a failure factor node is reselected from the child nodes of the troubleshooting node as the target node, and the steps after selecting the target node are executed, if the troubleshooting node has no child nodes, the parent node of the troubleshooting node is returned to reselect the target node; after the traversal of each child node of the target failure analysis tree is completed, the failure factor set is determined according to the determined troubleshooting nodes. In the technical solution of the embodiment of the present application, the child nodes of the target failure analysis tree are traversed, and the causes to be troubleshooted can be quickly and accurately recommended, which does not rely on personal experience, can improve the accuracy of the analysis of the failure causes, and the automatic search can also improve the speed of the analysis of the failure causes.

[0087] According to some embodiments of the present application, referring to Figure 5 In the above embodiment, “determining the screening node according to the matching result and reselecting the target node” may include the following steps:

[0088] Step 3031, when the matching result meets the preset matching conditions, the target node is determined as the screening node. If the screening node has child nodes, a failure factor node is reselected from the child nodes of the screening node as the target node, and the steps after selecting the target node are executed. If the screening node has no child nodes, the parent node of the screening node is returned to reselect the target node.

[0089] The matching result may include a failure matching degree, which is expressed as a percentage or a decimal, for example, a failure matching degree of 0.8 or a failure matching degree of 80%.

[0090] The preset matching condition may include that the failure matching degree is greater than or equal to a preset matching degree threshold. For example, the preset matching degree threshold is 0.8, and the first failure feature of the target battery is matched with the second failure features t1 and t2 corresponding to the failure factor node A, and the failure matching degree is 0.8. The failure matching degree is equal to the preset matching degree threshold, indicating that the matching result meets the preset matching condition, and the failure factor node A is determined as the troubleshooting node.

[0091] It should be noted that the preset matching degree threshold can be modified according to different scenarios and failure modes to meet different requirements.

[0092] If the troubleshooting node is failure factor node A, and A has child nodes, then select a failure factor node from the child nodes A-1, A-2, and A-3 of failure factor node A as the target node, for example, select failure factor node A-1 as the target node. The child nodes of failure factor node A-1 contain failure feature nodes, and the first failure feature of the target battery is matched with the second failure feature corresponding to failure factor node A-1 to obtain a matching result.

[0093] If the node under investigation has no child nodes, the parent node of the node under investigation is returned. For example, if the failure factor node A-2 is a node under investigation and the child nodes of the failure factor node A-2 have no failure feature nodes, its parent node A is returned. Since the parent node A is not the root node, a failure factor node is reselected from the same-level nodes B, C, and D of the parent node A as the target node. If the parent node is the root node after returning, the traversal is determined to be complete.

[0094] Step 3032, when the matching result does not meet the preset matching conditions, if the target node has a sibling node, then reselect an invalidation factor node from the sibling nodes of the target node as the target node, and execute the steps after selecting the target node. If the target node has no sibling node, then return to the parent node of the target node to reselect the target node.

[0095] If the failure matching degree is less than the preset matching threshold, it indicates that the matching result does not meet the preset matching condition. In this case, if the target node has a peer node, a node with failure factor is reselected from the peer nodes of the target node as the target node.

[0096] For example, taking failure factor node A as the target node, if the matching result between the first failure feature of the target battery and the second failure feature of failure factor node A does not meet the preset matching condition, then reselect a failure factor node as the target node from the peer nodes B, C, and D of failure factor node A. For another example, taking failure factor node A-1 as the target node, if the matching result between the first failure feature of the target battery and the second failure feature of failure factor node A-1 does not meet the preset matching condition, then reselect a failure factor node as the target node from the peer nodes A-2 and A-3 of failure factor node A-1.

[0097] After reselecting the target node, determine whether the child nodes of the target node contain a failure feature node. If the child nodes of the target node contain a failure feature node, match the first failure feature with each second failure feature corresponding to the target node to obtain a matching result.

[0098] If the target node has no sibling nodes, the parent node of the target node is returned; if the parent node is the root node, the traversal is determined to be complete; if the parent node is not the root node, a failure factor node is reselected from the sibling nodes of the parent node as the target node.

[0099] In the above embodiment, when the matching result meets the preset matching condition, the target node is determined as the investigation node. If the investigation node has child nodes, a failure factor node is reselected from the child nodes of the investigation node as the target node, and the steps after selecting the target node are executed. If the investigation node has no child nodes, the parent node of the investigation node is returned to reselect the target node. In the case that the matching result does not meet the preset matching condition, if the target node has a node at the same level, a failure factor node is reselected from the node at the same level of the target node as the target node, and the steps after selecting the target node are executed; if the target node has no node at the same level, the parent node of the target node is returned to reselect the target node. In the technical scheme of the embodiment of the present application, each child node of the target failure analysis tree is traversed, and according to whether the matching result meets the preset matching condition, the cause to be investigated can be quickly and accurately recommended, which does not rely on personal experience, can improve the accuracy of the analysis of the failure cause, and the automatic search can also improve the speed of the analysis of the failure cause.

[0100] According to some embodiments of the present application, referring to Figure 6 , and may also include the following steps:

[0101] Step 305: When the child nodes of the target node do not contain a failed characteristic node, the target node is determined as a check node.

[0102] If the target node's child node contains a failure feature node, the first failure feature of the target battery can be matched with the second failure feature in the failure feature node to obtain a matching result. If the target node's child node does not contain a failure feature node, the target node is directly determined as a troubleshooting node.

[0103] Reference Figure 3 , assuming that the failure factor node A-1 is the target node, and the child node of the failure factor node A-1 contains a failure feature node, the first failure feature of the target battery is matched with the second failure feature in the failure feature node to obtain a matching result. Assuming that the failure factor node A-2 is the target node, and the child node of the failure factor node A-2 does not contain a failure feature node, the failure factor node A-2 is determined as a check node.

[0104] Step 306: If the target node has a sibling node, a failure factor node is reselected from the sibling nodes of the target node as the target node, and the steps after selecting the target node are executed; if the target node has no sibling node, the target node's parent node is returned to reselect the target node.

[0105] Reference Figure 3 After determining the failure factor node A-2 as the node to be checked, select a failure factor node from the same level nodes of the failure factor node A-2 as the target node. For example, reselect the failure factor node A-3 as the target node. The failure factor node A-3 does not contain a failure feature node, and the failure factor node A-3 is determined as the node to be checked. Since the failure factor node A-3 has no same level nodes, the parent node A of the failure factor node is returned, and the target node is reselected from the same level nodes B, C, and D of the parent node A.

[0106] Similarly, you can traverse each child node in the target failure analysis tree, refer to Figure 7 , showing the screening factor recommendation process.

[0107] In the above embodiment, when the child nodes of the target node do not contain a failure characteristic node, the target node is determined as a check node; if the target node has a peer node, a failure factor node is reselected from the peer nodes of the target node as the target node, and the steps after selecting the target node are performed; if the target node has no peer node, the parent node of the target node is returned to reselect the target node. In the technical solution of the embodiment of the present application, each child node of the target failure analysis tree is traversed, and the cause to be checked can be quickly and accurately recommended based on whether it contains a failure characteristic node, which does not rely on personal experience, can improve the accuracy of the analysis of the failure cause, and the automatic search can also improve the speed of the analysis of the failure cause.

[0108] According to some embodiments of the present application, referring to Figure 8 In the above embodiment, “matching the first failure feature with each second failure feature corresponding to the target node to obtain a matching result” may include the following steps:

[0109] Step 401: Obtain the weights of each second failure feature corresponding to the target node.

[0110] When configuring the failure analysis tree, the weight of each second failure feature in the failure analysis tree may be configured. After selecting a target node, the weight of each second failure feature corresponding to the target node is obtained from the target failure analysis tree.

[0111] Reference Figure 3 , taking the failure factor node A as the target node, the weight of the second failure feature t1 corresponding to the failure factor node A is W1, and the weight of the second failure feature t2 is W2.

[0112] Step 402: Match the first failure feature with each second failure feature corresponding to the target node to obtain the probability of each second failure feature.

[0113] Assuming that the first failure feature includes t1, the first failure feature t1 is matched with each second failure feature corresponding to the target node, and the probability of the second failure feature t1 is 1. Assuming that the first failure feature does not include t1, the first failure feature is matched with each second failure feature corresponding to the target node, and the probability of the second failure feature t1 is 0. Similarly, the probability of each second failure feature can be determined based on the first failure feature.

[0114] Step 403: Calculate the probability of the target node according to the weight and probability of each second failure feature, and determine the probability of the target node as a matching result.

[0115] The probability of the target node can be calculated using formula (1):

[0116] Z=(a1*W1+a2*W2+…+an*Wn) / SumW--------------(1)

[0117] Among them, a1 is the probability of the second failure feature t1, W1 is the weight of the second failure feature t1, and so on, an is the probability of the second failure feature tn, Wn is the weight of the second failure feature tn, and SumW is the sum of the weights.

[0118] After determining the weights and probabilities of the second failure features corresponding to the target node, the weights and probabilities of the second failure features are substituted into the above formula for calculation, and the probability of the target node can be obtained, and the probability of the target node is used as the matching result.

[0119] In the above embodiment, the weights of the second failure features corresponding to the target node are obtained; the first failure feature is matched with the second failure features corresponding to the target node to obtain the probability of each second failure feature; the probability of the target node is calculated according to the weight and probability of each second failure feature, and the probability of the target node is determined as the matching result. In the technical solution of the embodiment of the present application, the probability of each second failure feature is determined according to the first failure feature, the cause of the failure can be accurately matched, and the items to be checked are recommended, which provides a basis for subsequent data collection, can improve the efficiency of failure analysis, and improve the efficiency of locating the cause of failure.

[0120] According to some embodiments of the present application, referring to Fig. 9 In the above embodiment, “performing statistical processing on the production process data to determine the failure cause of the target battery” may include the following steps:

[0121] Step 501: Calculate the defect rate of each first failure factor in the failure factor set according to the production process data.

[0122] The defect rate refers to the ratio of the number of products that do not meet the specified standards or have defects to the total number of samples in a certain number of products, usually expressed as a percentage. The defect rate is calculated using formula (2):

[0123] Defective rate = defective quantity / (qualified quantity + defective quantity)*100%-----------(2)

[0124] For each first failure factor in the failure factor set, the terminal obtains the production process data corresponding to the first failure factor, determines the defective quantity and the qualified quantity according to the production process data, and calculates the defective rate of the first failure factor using formula (2).

[0125] For example, the failure factor set includes first failure factors x1, x2, ..., xn, and the defect rates y1, y2, ..., yn of the first failure factors are calculated respectively.

[0126] Step 502 , statistically process the defect rates of multiple first failure factors to obtain the failure cause of the target battery.

[0127] By statistically processing the defect rates of multiple first failure factors, the first failure factor with the highest defect rate can be determined as the failure cause of the target battery; or m first failure factors with relatively high defect rates can be determined as the failure cause of the target battery.

[0128] In some embodiments, data charts may be drawn after statistical processing, wherein the chart styles include bar charts, line charts, box plots, and the like.

[0129] In the above embodiment, the defect rate of each first failure factor in the failure factor set is calculated based on the production process data; the defect rates of multiple first failure factors are statistically processed to obtain the failure cause of the target battery. In the technical solution of the embodiment of the present application, automatic data statistics can improve the efficiency of data analysis, thereby improving the efficiency of failure analysis.

[0130] According to some embodiments of the present application, referring to Fig.10 In the above embodiment, “performing statistical processing on the defect rates of multiple first failure factors to obtain the failure cause of the target battery” may include the following steps:

[0131] Step 601, selecting m first failure factors in descending order of defective rate; m is a positive integer.

[0132] Arrange multiple first failure factors in order of defective rate from low to high to obtain a data set of failure factors and defective rates {x1:y1, x2:y2…xn:yn}, where x is the first failure factor, y is the defective rate corresponding to the first failure factor, y1 is the lowest, and yn is the highest.

[0133] Assuming m is 1, the first failure factor with the highest defective rate is selected; assuming m is 2, the first failure factors with the highest and second highest defective rates are selected.

[0134] Step 602: When the defect rates of the selected m first failure factors satisfy the concentration condition, the m first failure factors are determined as the failure causes of the target battery.

[0135] The concentration condition includes that the sum of defect rates of m first failure factors is greater than the sum of defect rates of all other first failure factors.

[0136] After selecting m first failure factors, determine whether the sum of the defective rates of the m first failure factors is greater than the sum of the defective rates of all other first failure factors; if so, determine that the defective rates of the m first failure factors meet the concentration condition. If not, determine that the defective rates of the m first failure factors do not meet the concentration condition, and reselect the first failure factors.

[0137] For example, the first failure factor xn with the highest defective rate is selected. If yn>(y1+y2+…yn-1), it is determined that the defective rate of the first failure factor xn meets the concentration condition, the first failure factor xn has concentration, and the first failure factor xn is determined as the failure cause of the target battery. If yn≤(y1+y2+…yn-1), it is determined that the defective rate of the first failure factor xn does not meet the concentration condition. In this case, the first failure factors xn and xn-1 with the highest and second highest defective rates are selected. If (yn+yn-1)>(y1+y2+…yn-2), it is determined that the defective rates of the first failure factors xn and xn-1 meet the concentration condition, the first failure factors xn and xn-1 have concentration, and the first failure factors xn and xn-1 are determined as the failure causes of the target battery. Similarly, if the defective rates of the first failure factors xn and xn-1 do not meet the concentration condition, xn, xn-1, and xn-2 with higher defective rates are selected. If (yn+yn-1+yn-2)>(y1+y2+…yn-3), it is determined that the defective rates of the first failure factors xn, xn-1 and xn-2 meet the concentration condition, the first failure factors xn, xn-1 and xn-2 are concentrated, and the first failure factors xn, xn-1 and xn-2 are determined as the failure causes of the target battery.

[0138] In the above embodiment, m first failure factors are selected in descending order of defective rate; when the defective rates of the selected m first failure factors meet the concentration condition, the m first failure factors are determined as the failure causes of the target battery. In the technical solution of the embodiment of the present application, the failure factors with concentration in the production process data are located according to the element concentration calculation method, which can improve the efficiency and accuracy of locating the failure causes.

[0139] According to some embodiments of the present application, referring to Fig.11 After determining the failure cause of the target battery, the embodiment of the present application may further include the following steps:

[0140] Step 701, obtaining the on-site verification result of the failure cause of the target battery.

[0141] The staff of the battery production line can conduct on-site verification based on the failure cause of the target battery. For example, if the failure mode of the target battery is a poor K value and the failure cause of the target battery is determined to be F1, the staff can conduct on-site verification by disassembling the target battery and conducting simulation experiments based on the failure cause F1 to confirm whether the actual failure cause of the target battery is failure cause F1.

[0142] After the on-site verification, the staff can input the on-site verification results in the terminal. For example, the terminal displays the failure analysis interface, which includes a verification result input area; the terminal obtains the on-site verification results according to the input content of the staff in the verification result input area.

[0143] Step 702: If the on-site verification result is not passed, the verified failure cause is eliminated, and the process returns to the step of performing statistical processing on the production process data.

[0144] If the on-site verification result is failed, the verified failure causes will be excluded, the production process data of other failure causes will be statistically processed, the failure cause of the target battery will be recalculated, and on-site verification will be carried out again.

[0145] If the on-site verification result is passed, the failure analysis process ends.

[0146] In some embodiments, the terminal may also adjust parameters in the failure analysis tree according to the field verification results, for example, adjusting the failure factor node and / or failure feature node of the failure analysis tree, and adjusting the weight of the second failure feature in the failure analysis tree.

[0147] It should be noted that the adjustment of the failure analysis tree is not limited to the above examples and can be determined according to actual conditions.

[0148] In the above embodiment, the on-site verification result of the failure cause of the target battery is obtained; if the on-site verification result is not passed, the verified failure cause is excluded, and the step of performing statistical processing on the production process data is returned. In the technical solution of the embodiment of the present application, the real failure cause of the target battery can be further determined through on-site verification, the failure analysis tree can be improved, and a more accurate basis can be provided for subsequent failure analysis.

[0149] According to some embodiments of the present application, a battery failure analysis method is provided. Figure 1 Taking the terminal in as an example, the following steps may be included:

[0150] Step 1: Obtain the failure mode and first failure feature of the target battery.

[0151] Among them, failure characteristics are used to characterize observable failure phenomena.

[0152] Step 2: Determine the target failure analysis tree according to the failure mode.

[0153] The failure factor set includes at least one first failure factor, the failure analysis tree is pre-constructed based on a plurality of second failure factors and a plurality of second failure features, and the failure factor is used to characterize the failure cause.

[0154] The failure analysis tree includes a root node and multiple child nodes; the root node represents the failure mode, the child nodes include a failure factor node and a failure feature node, and the failure feature node is provided with the second failure feature.

[0155] Step 3: Select a failure factor node from the child nodes of the root node of the target failure analysis tree as the target node.

[0156] Depending on whether the child nodes of the target node contain invalid feature nodes, execute step 4 or step 7.

[0157] Step 4: When the child node of the target node contains a failure feature node, the first failure feature is matched with each second failure feature corresponding to the target node to obtain a matching result.

[0158] Among them, matching the first failure feature with each second failure feature corresponding to the target node to obtain the matching result includes: obtaining the weights of each second failure feature corresponding to the target node; matching the first failure feature with each second failure feature corresponding to the target node to obtain the probability of each second failure feature; calculating the probability of the target node according to the weights and probabilities of each second failure feature, and determining the probability of the target node as the matching result.

[0159] After obtaining the matching result, step 5 or step 6 is executed according to whether the matching result meets the preset matching condition.

[0160] Step 5, when the matching result meets the preset matching conditions, the target node is determined as the investigation node. If the investigation node has child nodes, a failure factor node is reselected from the child nodes of the investigation node as the target node, and the steps after selecting the target node are executed. If the investigation node has no child nodes, the parent node of the investigation node is returned to reselect the target node.

[0161] Step 6. When the matching result does not meet the preset matching conditions, if the target node has a sibling node, a failure factor node is reselected from the sibling nodes of the target node as the target node, and the steps after selecting the target node are executed. If the target node has no sibling node, the parent node of the target node is returned to reselect the target node.

[0162] Step 7, when the child nodes of the target node do not contain failure feature nodes, the target node is determined as a check node. If the target node has sibling nodes, a failure factor node is reselected from the sibling nodes of the target node as the target node, and the steps after selecting the target node are executed. If the target node has no sibling nodes, the parent node of the target node is returned to reselect the target node.

[0163] Step 8: After traversing all child nodes of the target failure analysis tree, determine the failure factor set according to the determined troubleshooting nodes.

[0164] Step 9: collect data based on the failure factor set to obtain production process data.

[0165] Step 10: Calculate the defect rate of each first failure factor in the failure factor set according to the production process data.

[0166] Step 11, selecting m first failure factors in descending order of defective rate; m is a positive integer;

[0167] Step 12: When the defect rates of the selected m first failure factors satisfy the concentration condition, the m first failure factors are determined as the failure causes of the target battery.

[0168] Step 13, obtaining an on-site verification result of the failure cause of the target battery;

[0169] Step 14: If the on-site verification result is not passed, the verified failure cause is eliminated and the process returns to the step of performing statistical processing on the production process data.

[0170] In the above embodiment, a failure factor set, i.e., the failure cause to be investigated, can be obtained quickly and accurately based on the failure phenomenon of the target battery and the target failure analysis tree. Data collection and statistical analysis are automatically performed based on the failure cause to be investigated without relying on personal experience. Therefore, the failure analysis speed can be improved, as well as the efficiency of locating the failure cause.

[0171] It should be understood that, although the various steps in the above flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowchart may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0172] Based on the same inventive concept, the embodiment of the present application also provides a battery failure analysis device for implementing the battery failure analysis method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more battery failure analysis device embodiments provided below can refer to the limitations of the battery failure analysis method above, and will not be repeated here.

[0173] According to some embodiments of the present application, referring to Fig.12 , provides a battery failure analysis device, the device comprising:

[0174] A feature acquisition module 801 is used to acquire a failure mode and a first failure feature of a target battery;

[0175] The cause analysis module 802 is used to determine a target failure analysis tree according to the failure mode, and perform factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set; wherein the failure factor set includes at least one first failure factor, and the failure analysis tree is pre-constructed based on multiple second failure factors and multiple second failure features; the first failure feature and the second failure feature are used to characterize the failure phenomenon, and the first failure factor and the second failure factor are used to characterize the failure cause;

[0176] The data collection module 803 is used to collect data according to the failure factor set to obtain production process data;

[0177] The cause determination module 804 is used to perform statistical processing on the production process data to determine the failure cause of the target battery.

[0178] In some embodiments, the failure analysis tree includes a root node and multiple child nodes; the root node represents the failure mode, and the child nodes include a failure factor node and a failure feature node, and the failure feature node is provided with a second failure feature; the cause analysis module 802 is specifically used to select a failure factor node from the child nodes of the root node of the target failure analysis tree as the target node; when the child nodes of the target node contain a failure feature node, the first failure feature is matched with each second failure feature corresponding to the target node to obtain a matching result; when the matching result meets the preset matching condition, the target node is determined as a troubleshooting node, if the troubleshooting node has child nodes, a failure factor node is reselected from the child nodes of the troubleshooting node as the target node, and the steps after selecting the target node are executed, if the troubleshooting node has no child nodes, the parent node of the troubleshooting node is returned to reselect the target node; after traversing each child node of the target failure analysis tree, a failure factor set is determined according to the determined troubleshooting node.

[0179] In some embodiments, the cause analysis module 802 is also used to, when the matching result does not meet the preset matching conditions, if the target node has a sibling node, reselect an invalidation factor node from the sibling nodes of the target node as the target node, and execute the steps after selecting the target node; if the target node has no sibling node, return to the parent node of the target node to reselect the target node.

[0180] In some embodiments, the cause analysis module 802 is also used to determine the target node as a troubleshooting node when the child nodes of the target node do not contain a failure feature node; if the target node has a sibling node, then reselect a failure factor node from the sibling nodes of the target node as the target node, and execute the steps after selecting the target node; if the target node has no sibling nodes, then return to the parent node of the target node to reselect the target node.

[0181] In some embodiments, the cause analysis module 802 is specifically used to obtain the weights of each second failure feature corresponding to the target node; match the first failure feature with each second failure feature corresponding to the target node to obtain the probability of each second failure feature; calculate the probability of the target node based on the weights and probabilities of each second failure feature, and determine the probability of the target node as the matching result.

[0182] In some embodiments, the cause determination module 804 is specifically used to calculate the defect rate of each first failure factor in the failure factor set according to the production process data; perform statistical processing on the defect rates of multiple first failure factors to obtain the failure cause of the target battery.

[0183] In some embodiments, the cause determination module 804 is specifically used to select m first failure factors in order of defective rate from high to low; m is a positive integer; when the defective rates of the selected m first failure factors meet the concentration condition, the m first failure factors are determined as the failure causes of the target battery.

[0184] In some embodiments, reference Fig.13 , the device further comprises:

[0185] A verification result acquisition module 805 is used to obtain an on-site verification result of the failure cause of the target battery;

[0186] The re-statistics module 806 is used to eliminate the verified failure causes if the on-site verification result is not passed, and return to the step of performing statistical processing on the production process data.

[0187] Each module in the above-mentioned battery failure analysis device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in an electronic device in the form of hardware, or can be stored in a memory in an electronic device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0188] According to some embodiments of the present application, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.14 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a battery failure analysis method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0189] Those skilled in the art will understand that Fig.14 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0190] According to some embodiments of the present application, there is also provided a non-transitory computer-readable storage medium including instructions, such as a memory including instructions, and the above instructions can be executed by a processor of an electronic device to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0191] According to some embodiments of the present application, a computer program product is also provided, and when the computer program is executed by a processor, the above method can be implemented. The computer program product includes one or more computer instructions. When these computer instructions are loaded and executed on a computer, part or all of the above method can be implemented in whole or in part according to the process or function described in the embodiment of the present application.

[0192] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0193] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0194] The above-described embodiments only express several implementation methods of the present application, which is convenient for understanding the technical solutions of the present application in detail, but cannot be understood as limiting the scope of protection of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. It should be understood that the technical solutions obtained by those skilled in the art through logical analysis, reasoning or limited experiments on the basis of the technical solutions provided in the present application are all within the protection scope of the attached claims described in the present application. Therefore, the protection scope of the patent of this application shall be based on the contents of the attached claims, and the description and drawings can be used to explain the contents of the claims.

Claims

1. A battery failure analysis method, characterized in that: The method comprises: Obtaining a failure mode and a first failure feature of a target battery; wherein the failure feature is used to characterize an observable failure phenomenon; Determine a target failure analysis tree according to the failure mode, and perform factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set; wherein the failure factor set includes at least one first failure factor, the failure analysis tree is pre-constructed based on a plurality of second failure factors and a plurality of second failure features, and the failure factor is used to characterize the failure cause; Collect data according to the failure factor set to obtain production process data; Statistical processing is performed on the production process data to determine the failure cause of the target battery.

2. The method according to claim 1, characterized in that The failure analysis tree includes a root node and a plurality of child nodes; the root node represents the failure mode, the child nodes include a failure factor node and a failure feature node, and the failure feature node is provided with the second failure feature; The performing factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set includes: Select a failure factor node from the child nodes of the root node of the target failure analysis tree as a target node; In the case where the child node of the target node contains the failure feature node, matching the first failure feature with each second failure feature corresponding to the target node to obtain a matching result; Determine the check node according to the matching result, and reselect the target node; After all child nodes of the target failure analysis tree are traversed, the failure factor set is determined according to the determined troubleshooting nodes.

3. The method according to claim 2, characterized in that The determining the check node according to the matching result and reselecting the target node include: In the case where the matching result meets the preset matching condition, the target node is determined as the screening node. If the screening node has child nodes, a failure factor node is reselected from the child nodes of the screening node as the target node, and the steps after selecting the target node are performed. If the screening node has no child nodes, the parent node of the screening node is returned to reselect the target node. In the case where the matching result does not meet the preset matching condition, if the target node has a peer node, reselect an invalidation factor node from the peer nodes of the target node as the target node, and execute the steps after selecting the target node; If the target node has no sibling node, the parent node of the target node is returned to reselect the target node.

4. The method according to claim 2, characterized in that: The method further comprises: In the case that the child nodes of the target node do not contain a failure characteristic node, determining the target node as the check node; If the target node has a peer node, reselect a failure factor node from the peer nodes of the target node as the target node, and execute the steps after selecting the target node; If the target node has no sibling node, the parent node of the target node is returned to reselect the target node.

5. The method according to any one of claims 2 to 4, characterized in that: The matching of the first failure feature with each second failure feature corresponding to the target node to obtain a matching result includes: Obtaining weights of each second failure feature corresponding to the target node; Matching the first failure feature with each second failure feature corresponding to the target node to obtain a probability of each second failure feature; The probability of the target node is calculated according to the weights and probabilities of the second failure features, and the probability of the target node is determined as the matching result.

6. The method according to claim 1, characterized in that The statistical processing of the production process data to determine the failure cause of the target battery includes: Calculating the defect rate of each of the first failure factors in the failure factor set according to the production process data; The defect rates of the plurality of the first failure factors are statistically processed to obtain the failure cause of the target battery.

7. The method according to claim 6, characterized in that The performing statistical processing on the defective rates of the plurality of first failure factors to obtain the failure cause of the target battery includes: m first failure factors are selected in descending order of defective rate; m is a positive integer; When the defective rates of the selected m first failure factors satisfy a concentration condition, the m first failure factors are determined as the failure causes of the target battery.

8. The method according to claim 1, characterized in that: The method further comprises: Obtaining an on-site verification result of the failure cause of the target battery; If the on-site verification result is failure, the verified failure cause is eliminated, and the process returns to execute the step of statistically processing the production process data.

9. A battery failure analysis device, characterized in that: The device comprises: A feature acquisition module, used to acquire the failure mode and the first failure feature of the target battery; a cause analysis module, configured to determine a target failure analysis tree according to the failure mode, and perform factor matching processing in the target failure analysis tree according to the first failure feature to obtain a failure factor set; wherein the failure factor set includes at least one first failure factor, and the failure analysis tree is pre-constructed based on a plurality of second failure factors and a plurality of second failure features; the first failure feature and the second failure feature are used to characterize a failure phenomenon, and the first failure factor and the second failure factor are used to characterize a failure cause; A data collection module, used to collect data according to the failure factor set to obtain production process data; The cause determination module is used to perform statistical processing on the production process data to determine the failure cause of the target battery.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images