Battery pack fault analysis method and system

Abstract

The invention provides a battery pack fault analysis method and system, and the method comprises the steps: obtaining the detection information of each detection type of a battery pack, and recognizing the detection result of each detection type corresponding to the battery pack; on the basis of the detection result of each detection type, through a battery pack fault logic analysis network, predicting each piece of initial fault information of the battery pack, and on the basis of fault representation information of each piece of initial fault information, generating a fault representation detection strategy of each piece of initial fault information; and in response to a fault characterization detection result operation uploaded by a worker, obtaining characterization detection information of each piece of initial fault information, and based on the characterization detection information of each piece of initial fault information, identifying target fault information of the battery pack. By adopting the scheme, the accuracy of fault analysis of the battery pack can be improved.

Description

Technical Field

[0001] The present invention relates to the technical fields of battery packs and fault analysis and detection, and particularly to a method and system for battery pack fault analysis. Background Art

[0002] As a power supply unit for various current electronic devices, battery packs are widely used in the market and have a very common application range. However, with the continuous improvement of the device functions and performance of electronic devices, the charge and discharge frequency, charge and discharge rate, and charge and discharge voltage of battery packs are relatively high during actual application, resulting in an increasing probability and types of battery pack failures. Therefore, how to improve the efficiency and accuracy of battery pack fault analysis is the current research focus.

[0003] The traditional method for battery pack fault analysis is to use a battery pack detection device to detect the battery pack for fault detection to determine the fault information of the battery pack. However, the fault detection of the battery pack detection device can only obtain the relevant numerical information of the battery pack, and it is necessary for manual judgment and identification of the fault types and fault information of the battery pack. This judgment and identification method is affected by the experience of the staff and the subjective judgment of the staff, resulting in poor accuracy of battery pack fault analysis. Summary of the Invention

[0004] The main objective of the present invention is to provide a method and system for battery pack fault analysis, aiming to solve the problem in the prior art that since the fault detection of the battery pack detection device can only obtain the relevant numerical information of the battery pack, it is necessary for manual judgment and identification of the fault types and fault information of the battery pack, and this judgment and identification method is affected by the experience of the staff and the subjective judgment of the staff, resulting in poor accuracy of battery pack fault analysis.

[0005] To achieve the above objective, the present invention provides a method for battery pack fault analysis, the method comprising:

[0006] Obtaining battery pack detection information of each detection type performed on the battery pack, and identifying detection results of each detection type corresponding to the battery pack;

[0007] Based on the detection results of each detection type, predicting initial fault information of the battery pack through a battery pack fault logic analysis network, and generating a fault characterization detection strategy for each initial fault information based on the fault characterization information of each initial fault information;

[0008] In response to the operation of the fault characterization detection result uploaded by the staff, obtaining the characterization detection information of each initial fault information, and identifying the target fault information of the battery pack based on the characterization detection information of each initial fault information.

[0009] Optionally, identifying the detection results of each detection type corresponding to the battery pack includes:

[0010] For each detection type, based on the battery pack detection information of the detection type, identify the detection data of the battery pack and the detection strategy of the battery pack, and based on the detection strategy of the battery pack, identify the detection logic of the detection type and the detection process of the detection type;

[0011] Split the detection data into sub-detection data of each process node of the detection process, and based on the detection logic and the sub-detection data of each process node, identify the detection results of the battery pack.

[0012] Optionally, the identifying the detection results of the battery pack based on the detection logic and the sub-detection data of each process node includes:

[0013] Based on the detection logic, identify the process progression logic of each process node of the detection type, and based on the process progression logic of each process node and the sub-detection data of each process node, identify the sub-detection results of each process node;

[0014] Arrange the sub-detection results of each process node in the process order of each process node to obtain the detection results of the battery pack.

[0015] Optionally, the battery fault logic analysis network includes sub-fault analysis networks of each detection type. Based on the detection results of each detection type, predicting the initial fault information of the battery pack through the battery pack fault logic analysis network includes:

[0016] For each detection type, based on the sub-detection results of each process node of the detection type and the process progression logic of each process node, identify the process progression reasons of each process node and the process progression abnormal information of each process node;

[0017] Based on the process progression abnormal information of each process node and the process progression reasons of each process node, through the sub-fault analysis network corresponding to the detection type, identify the initial fault types corresponding to each process node and the fault basis information of each initial fault type;

[0018] Use the fault basis information of each initial fault type as the initial fault information of the battery pack.

[0019] Optionally, generating a fault characterization detection strategy for each initial fault information based on the fault characterization information of each initial fault information includes:

[0020] In the fault database, query the fault characterization information of each initial fault information, and for each initial fault information, based on the fault characterization information of the initial fault information, identify the fault characterization type of each initial fault information and the fault characterization range of each initial fault information;

[0021] Based on the fault characterization type of each initial fault information, query the fault detection strategy of the fault characterization type in the fault detection database, and based on the fault characterization range of the initial fault information, query the fault results corresponding to each sub-characterization range in the database;

[0022] Take the fault detection strategy of each initial fault information and the fault results corresponding to each sub-characterization range of each initial fault information as the fault characterization detection strategy of the initial fault information.

[0023] Optionally, the identifying the target fault information of the battery pack based on the characterization detection information of each initial fault information includes:

[0024] For each initial fault information, based on the characterization detection information of the initial fault information, identify the characterization detection data of the initial fault information, and based on the characterization detection data of the initial fault information, screen the target sub-characterization range corresponding to the initial fault information from the characterization detection data of the initial fault information;

[0025] Take the fault results corresponding to the target sub-characterization range as the characterization detection results of the initial fault information, and based on the characterization detection results of each initial fault information, calculate the fault probabilities of the fault detection results of the battery pack;

[0026] Take each of the fault detection results and the fault probabilities of each of the fault detection results as the target fault information of the battery pack.

[0027] In addition, to achieve the above object, the present invention also provides a battery pack fault analysis system, and the battery pack fault analysis system includes:

[0028] An acquisition module, configured to acquire the battery pack detection information of each detection type for the battery pack and identify the detection results of each detection type corresponding to the battery pack;

[0029] A generation module, configured to predict each initial fault information of the battery pack through a battery pack fault logic analysis network based on the detection results of each detection type, and generate a fault characterization detection strategy for each initial fault information based on the fault characterization information of each initial fault information;

[0030] An identification module, configured to obtain the characterization detection information of each of the initial fault information in response to an operation of the fault characterization detection result uploaded by a staff member, and identify the target fault information of the battery pack based on the characterization detection information of each of the initial fault information.

[0031] Optionally, the obtaining module is specifically configured to:

[0032] For each detection type, based on the battery pack detection information of the detection type, identify the detection data of the battery pack and the detection strategy of the battery pack, and based on the detection strategy of the battery pack, identify the detection logic of the detection type and the detection process of the detection type;

[0033] Split the detection data into sub-detection data of each process node of the detection process, and identify the detection result of the battery pack based on the detection logic and the sub-detection data of each process node.

[0034] Optionally, the generating module is specifically configured to:

[0035] Based on the detection logic, identify the process progression logic of each process node of the detection type, and based on the process progression logic of each process node and the sub-detection data of each process node, identify the sub-detection result of each process node;

[0036] Arrange the sub-detection results of each process node in the process order of each process node to obtain the detection result of the battery pack.

[0037] Optionally, the generating module is specifically configured to:

[0038] For each detection type, based on the sub-detection results of each process node of the detection type and the process progression logic of each process node, identify the process progression reason of each process node and the process progression abnormal information of each process node;

[0039] Based on the process progression abnormal information of each process node and the process progression reason of each process node, through the sub-fault analysis network corresponding to the detection type, identify the initial fault type corresponding to each process node and the fault basis information of each initial fault type;

[0040] Use the fault basis information of each initial fault type as the initial fault information of the battery pack.

[0041] Optionally, the generating module is specifically configured to:

[0042] In the fault database, query the fault characterization information of each initial fault information, and for each initial fault information, based on the fault characterization information of the initial fault information, identify the fault characterization type of each initial fault information and the fault characterization range of each initial fault information;

[0043] Based on the fault characterization type of each initial fault information, query the fault detection strategy of the fault characterization type in the fault detection database, and based on the fault characterization range of the initial fault information, query the fault results corresponding to each sub-characterization range in the fault characterization range in the database;

[0044] Take the fault detection strategy of each initial fault information and the fault results corresponding to each sub-characterization range of each initial fault information as the fault characterization detection strategy of the initial fault information.

[0045] Optionally, the identification module is specifically configured to:

[0046] For each initial fault information, based on the characterization detection information of the initial fault information, identify the characterization detection data of the initial fault information, and based on the characterization detection data of the initial fault information, screen the target sub-characterization range corresponding to the initial fault information from the characterization detection data of the initial fault information;

[0047] Take the fault results corresponding to the target sub-characterization range as the characterization detection results of the initial fault information, and based on the characterization detection results of each initial fault information, calculate the fault probabilities of the fault detection results of the battery pack;

[0048] Take each of the fault detection results and the fault probabilities of each of the fault detection results as the target fault information of the battery pack.

[0049] In a third aspect, the present application provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method described in any one of the first aspects are implemented.

[0050] In a fourth aspect, the present application provides a computer-readable storage medium. A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method described in any one of the first aspects are implemented.

[0051] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of the first aspects are implemented.

[0052] The present invention provides a method and system for analyzing battery pack faults. The method includes: obtaining battery pack detection information of various detection types for the battery pack, and identifying detection results of various detection types corresponding to the battery pack; based on the detection results of various detection types, predicting initial fault information of the battery pack through a battery pack fault logic analysis network, and generating a fault characterization detection strategy for each of the initial fault information based on the fault characterization information of each of the initial fault information; in response to an operation of uploading a fault characterization detection result by a staff member, obtaining characterization detection information of each of the initial fault information, and identifying target fault information of the battery pack based on the characterization detection information of each of the initial fault information. In this solution, by obtaining battery pack detection information of various detection types, the detection results of each monitoring type are intelligently identified, and then through the battery pack fault logic analysis network, initial fault information that may exist in the battery pack is predicted. Then, based on the fault characterization information of each initial fault information, a secondary detection strategy for the battery pack is generated, and based on the detection results obtained by the secondary detection strategy, a comprehensive judgment is made on the fault information of the battery pack, so as to identify the target fault information in which the battery pack is located. Among them, the target fault information includes the fault probability of each fault result in which the battery pack is located. This avoids the problems of low accuracy and low comprehensiveness of manual fault judgment. Then, through two rounds of detection and two rounds of judgment, this solution progressively analyzes various possible fault results and the fault probabilities of each fault result of the battery pack, thereby effectively improving the fault detection probability while enhancing the comprehensiveness of fault detection and the logic of fault judgment, providing a comprehensive reference for the staff to judge the specific fault information in which the battery pack is located, and thus improving the accuracy of fault analysis of the battery pack. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the solutions in the present application, the following will briefly introduce the drawings required for description in the embodiments of the present application. Obviously, the following-described drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 is a flowchart of the battery pack fault analysis method provided by an embodiment of the present invention;

[0055] Figure 2 is a schematic structural diagram of the battery pack fault analysis system provided by an embodiment of the present invention;

[0056] Figure 3 is an internal structure diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] The battery pack fault analysis method provided by the embodiments of the present invention is applied to a battery pack fault analysis system. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0058] Referring to "embodiments" herein means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0059] To enable those skilled in the technical field to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the drawings.

[0060] The battery pack fault analysis method provided by the embodiments of the present application can be applied to the application environment of battery pack fault analysis. Among them, this method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptop computers, etc. Among them, the terminal obtains the battery pack detection information of each detection type, thereby intelligently identifying the detection results of each monitoring type, and then predicts the possible initial fault information of the battery pack through the battery pack fault logic analysis network. Then, based on the fault characterization information of each initial fault information, the terminal generates a secondary detection strategy for the battery pack, and based on the detection results obtained by the secondary detection strategy, comprehensively judges the fault information of the battery pack, thereby identifying the target fault information of the battery pack. Among them, the target fault information includes the fault probabilities of each fault result in which the battery pack is located. This avoids the problems of low accuracy and low comprehensiveness of manual fault judgment. Then, through two rounds of detection and two rounds of judgment, this solution progressively analyzes the possible fault results of the battery pack and the fault probabilities of each fault result, thereby effectively improving the fault detection probability while enhancing the comprehensiveness of fault detection and the logic of fault judgment, providing a comprehensive reference for the staff to judge the specific fault information in which the battery pack is located, and thus improving the accuracy of the fault analysis of the battery pack.

[0061] In one embodiment, as Figure 1 shown, a battery pack fault analysis method is provided. Taking the application of this method to a terminal as an example, it includes the following steps:

[0062] Step S101: Obtain the battery pack detection information of each detection type performed on the battery pack, and identify the detection results of each detection type corresponding to the battery pack.

[0063] In this embodiment, the terminal responds to the information uploading operation of the staff member and obtains the detection information obtained by the staff member through various detection devices for fault detection of the battery pack. Among them, each detection device can perform fault detection of one or more detection types on the battery pack. The detection device includes, but is not limited to, a battery comprehensive tester: This tester can measure the open-circuit voltage, internal resistance, charging, discharging performance, and battery capacity of the battery. It also has functions such as overcharge protection, overdischarge protection, overcurrent protection, and short-circuit protection, and can accurately measure the basic parameters of the battery quantitatively, facilitating the production and after-sales service of the battery; battery safety detection equipment: including extrusion and puncture series, short-circuit series, combustion series, impact series, drop series, thermal abuse series, thermal shock series, low-pressure series, and temperature cycle series of equipment. These devices detect the safety of the battery through different test methods, such as extrusion, puncture, short-circuit, combustion, impact, drop, etc., to ensure the performance and safety of the battery under extreme conditions such as alternating high and low temperatures, extrusion, and puncture. Electrochemical workstation: used for electrochemical research, which can provide accurate electrochemical measurements and analyses to help researchers understand the electrochemical performance and fault causes of the battery. Field emission electron microscope (SEM), X-ray diffractometer (XRD), Raman spectrometer (Raman), infrared spectrometer (IR), etc.: These devices are mainly used for the composition analysis and structure analysis of battery materials to help researchers diagnose the root causes of battery faults. Thermal analyzer: such as accelerating rate calorimeter (ARC) and thermogravimetry-derivative thermogravimetry (TG-DTA), which are used to study the thermal stability and thermal safety of the battery to help discover potential fault points. Chromatography and mass spectrometer: such as gas chromatograph (GC) and mass spectrometer (MS), which are used to analyze the chemical components in battery materials to help diagnose battery faults caused by material problems. Among them, each detection type also respectively includes battery parameter detection type, battery performance detection type, electrochemical detection type, battery heat anomaly detection type, and battery material detection type, etc. Finally, the terminal identifies the detection results of each detection type corresponding to the battery pack based on the battery pack detection information of each detection type of the battery pack. Among them, the detection result of each battery pack is the sub-detection data corresponding to each process node in the detection process of the battery pack, and the sub-detection result of each process node identified through the detection logic of the battery pack. The specific identification process will be described in detail later. Among them, when performing battery pack detection, each process node in the detection process of the battery pack corresponds to one or more detection targets, and each detection target corresponds to a process progression logic. This process progression logic is used to represent the judgment logic for judging the deviation information between the battery pack and the detection target. Then, the terminal analyzes the sub-detection results corresponding to each process node through the process progression logic corresponding to each detection target. Among them, each process node can be a node corresponding to a progressive process detection process or a node corresponding to a parallel process detection process.Among them, the progressive process detection process is characterized in that there is associated information between each process node, and there is a progressive relationship between the detection objectives of each process node. For example, when detecting the battery heat of a battery pack, first measure the temperature of the battery pack housing, and then measure the internal temperature of the battery pack, so as to be able to identify the actual temperature distribution data of the battery pack. The parallel process detection process is characterized in that there is no associated information between each process node, and the detection objectives of each process node are relatively independent. For example, the detection process of detecting each battery parameter of a battery pack.

[0064] Step S102, based on the detection results of each detection type, through the battery pack fault logic analysis network, predict each initial fault information of the battery pack, and based on the fault characterization information of each initial fault information, generate a fault characterization detection strategy for each initial fault information.

[0065] In this embodiment, the terminal, based on the detection results of each detection type, through the battery pack fault logic analysis network, predicts each initial fault information of the battery pack, and based on the fault characterization information of each initial fault information, generates a fault characterization detection strategy for each initial fault information. Among them, the battery fault logic analysis network includes sub-fault analysis networks of each detection type. Among them, each sub-fault analysis network of a detection type can identify the fault type to which the battery pack belongs and the judgment basis (i.e., fault basis information) for judging the fault type to which the battery pack belongs. Among them, each sub-fault analysis network is a neural network based on reinforcement learning, which can identify the fault type of the battery pack according to the detection results of each battery pack, and after outputting the fault information, the terminal, through the respective fault basis information corresponding to the fault type, identifies the fault basis information of the battery pack. And each fault information corresponds to a fault characterization information. For example, the fault characterization information corresponding to the temperature anomaly fault is that the housing temperature data of the battery pack is higher than the temperature threshold, and the fault characterization information corresponding to the battery pack breakage and leakage fault is that there is breakage on the housing of the battery pack, etc. The specific identification process will be described in detail later.

[0066] Step S103, in response to the operation of the fault characterization detection result uploaded by the staff, obtain the characterization detection information of each initial fault information, and based on the characterization detection information of each initial fault information, identify the target fault information of the battery pack.

[0067] In this embodiment, the terminal feeds back the detection requirements corresponding to the fault characterization information corresponding to each fault information to the staff client, guides the staff to perform secondary detection on each fault characterization information, so as to obtain the fault characterization detection results corresponding to each fault characterization information transmitted by the staff. Finally, the terminal obtains the characterization detection information of each initial fault information, and based on the characterization detection information of each initial fault information, identifies the target fault information of the battery pack. The specific process of identifying the target fault information will be described in detail later.

[0068] Based on the above solution, by obtaining the battery pack detection information of each detection type, the detection results of each monitoring type are intelligently identified. Then, through the battery pack fault logic analysis network, the initial fault information that may exist in the battery pack is predicted. Subsequently, based on the fault characterization information of each initial fault information, the terminal generates a secondary detection strategy for the battery pack, and based on the detection results obtained from the secondary detection strategy, comprehensively judges the fault information of the battery pack, so as to identify the target fault information of the battery pack. Among them, the target fault information includes the fault probabilities of the fault results in which the battery pack is located. This avoids the problems of low accuracy and low comprehensiveness in manual fault judgment. Then, through two rounds of detection and two rounds of judgment, this solution progressively analyzes the possible fault results of the battery pack and the fault probabilities of each fault result, effectively improving the fault detection probability while enhancing the comprehensiveness of fault detection and the logic of fault judgment, providing a comprehensive reference for the staff to judge the specific fault information of the battery pack, and thus improving the accuracy of fault analysis of the battery pack.

[0069] Optionally, identifying the detection results of each detection type corresponding to the battery pack includes: for each detection type, based on the battery pack detection information of the detection type, identifying the detection data of the battery pack and the detection strategy of the battery pack, and based on the detection strategy of the battery pack, identifying the detection logic of the detection type and the detection process of the detection type; splitting the detection data into sub-detection data of each process node of the detection process, and based on the detection logic and the sub-detection data of each process node, identifying the detection results of the battery pack.

[0070] In this embodiment, for each detection type, the terminal, based on the battery pack detection information of the detection type, identifies the detection data of the battery pack and the detection strategy of the battery pack, and based on the detection strategy of the battery pack, identifies the detection logic of the detection type and the detection process of the detection type. Among them, the detection logic of each detection type includes the process progression logic of each process node in the detection process of each detection type, and this process progression logic is used to judge the deviation information between the detection data of this process node and the detection target of this process node. The specific judgment process will be described in detail later.

[0071] Finally, the terminal splits the detection data into sub-detection data of each process node of the detection process, and based on the detection logic and the sub-detection data of each process node, identifies the detection results of the battery pack.

[0072] Based on the above solution, by splitting the battery pack detection information of each detection type into each process node of each detection process and then identifying the detection results, the comprehensiveness and accuracy of identifying the detection results are improved.

[0073] Optionally, based on the detection logic and the sub-detection data of each process node, identify the detection result of the battery pack, including: based on the detection logic, identify the process progression logic of each process node of the detection type, and based on the process progression logic of each process node and the sub-detection data of each process node, identify the sub-detection result of each process node; arrange the sub-detection results of each process node in the process order of each process node to obtain the detection result of the battery pack.

[0074] In this embodiment, the terminal identifies the process progression logic of each process node of the detection type based on the detection logic, and identifies the sub-detection result of each process node based on the process progression logic of each process node and the sub-detection data of each process node. Specifically, for each process node, the process progression logic of the process node includes the target detection data range of the detection target of the process node and the abnormal detection data range corresponding to each abnormal information. The terminal determines whether the sub-detection data belongs to the detection target or the abnormal information by identifying the detection data range to which the sub-detection data belongs.

[0075] Finally, the terminal arranges the sub-detection results of each process node in the process order of each process node to obtain the detection result of the battery pack.

[0076] Based on the above solution, through the process progression logic of each process node, the data logic judgment is respectively performed on the self-detection data of each process node, which improves the comprehensiveness and accuracy of the identification of the detection result of the battery pack.

[0077] Optionally, the battery fault logic analysis network includes sub-fault analysis networks of each detection type. Based on the detection results of each detection type, through the battery pack fault logic analysis network, predict the initial fault information of the battery pack, including: for each detection type, based on the sub-detection results of each process node of the detection type and the process progression logic of each process node, identify the process progression reasons of each process node and the process progression abnormal information of each process node; based on the process progression abnormal information of each process node and the process progression reasons of each process node, through the sub-fault analysis network corresponding to the detection type, identify the initial fault types corresponding to each process node and the fault basis information of each initial fault type; use the fault basis information of each initial fault type as the initial fault information of the battery pack.

[0078] In this embodiment, for each detection type, the terminal identifies the process progression reasons and process progression anomaly information of each process node based on the sub-detection results of each process node of the detection type and the process progression logic of each process node. Among them, the process progression reason is the association information between the detection data range to which the sub-inspection data of this process node belongs and the anomaly information. That is, the reason why this detection data range corresponds to this anomaly information. Then, the terminal uses the anomaly information corresponding to the detection data range to which the sub-detection data of this process node belongs as the process progression anomaly information of this process node.

[0079] Subsequently, based on the process progression anomaly information of each process node and the process progression reasons of each process node, the terminal identifies the initial fault types corresponding to each process node and the fault basis information of each initial fault type through the sub-fault analysis network corresponding to the detection type. Among them, the fault basis information of each initial fault type is the identification basis information of each initial fault type. Specifically, the sub-fault analysis network performs fault classification processing on the anomaly information of each process node based on the anomaly information of each process node and the process progression reasons of each process node to obtain the fault type of this process node. Then, the terminal queries the fault basis type similar to this process progression reason among the fault basis information of this fault type as the fault basis information corresponding to this process progression reason. Among them, each fault type corresponds to multiple fault basis information, and this fault basis information is the fault characterization data that generates this fault type. The terminal identifies the data type corresponding to each fault characterization data, queries the fault characterization data with the same data type as that in the detection data range corresponding to this process progression reason as the initial fault basis information. Then, the terminal calculates the coincidence degree of each fault characterization data and this detection data range, and uses the coincidence degree greater than the coincidence degree threshold as the fault basis information.

[0080] Finally, the terminal uses the fault basis information of each initial fault type as the initial fault information of the battery pack.

[0081] Based on the above solution, after classifying the fault types, the identification of the fault basis information corresponding to each process node improves the identification accuracy of the fault information of each process node.

[0082] Optionally, based on the fault characterization information of each initial fault information, generate a fault characterization detection strategy for each initial fault information, including: query the fault characterization information of each initial fault information in the fault database, and for each initial fault information, based on the fault characterization information of the initial fault information, identify the fault characterization type of each initial fault information and the fault characterization range of each initial fault information; based on the fault characterization type of each initial fault information, query the fault detection strategy of the fault characterization type in the fault detection database, and based on the fault characterization range of the initial fault information, query the fault results corresponding to each sub-characterization range in the fault characterization range in the database; use the fault detection strategy of each initial fault information and the fault results corresponding to each sub-characterization range of each initial fault information as the fault characterization detection strategy of the initial fault information.

[0083] In this embodiment, the terminal queries the fault characterization information of each initial fault information in the fault database, and for each initial fault information, based on the fault characterization information of the initial fault information, identifies the fault characterization type of each initial fault information and the fault characterization range of each initial fault information. Among them, each initial fault information corresponds to a fault characterization type and a fault characterization range.

[0084] Subsequently, the terminal queries the fault detection strategy of the fault characterization type in the fault detection database based on the fault characterization type of each initial fault information, and queries the fault results corresponding to each sub-characterization range in the fault characterization range in the database based on the fault characterization range of the initial fault information. Among them, different sub-characterization ranges correspond to different fault results.

[0085] Finally, the terminal uses the fault detection strategy of each initial fault information and the fault results corresponding to each sub-characterization range of each initial fault information as the fault characterization detection strategy of the initial fault information.

[0086] Based on the above solution, by identifying the fault characterization information of each initial fault information and the fault results corresponding to each sub-characterization range of each initial fault information, a fault characterization detection strategy for the initial fault information is generated, improving the comprehensiveness and accuracy of the identification of the fault characterization detection strategy.

[0087] Optionally, based on the characterization detection information of each initial fault information, identify the target fault information of the battery pack, including: for each initial fault information, based on the characterization detection information of the initial fault information, identify the characterization detection data of the initial fault information, and based on the characterization detection data of the initial fault information, screen the target sub-characterization range corresponding to the initial fault information from the characterization detection data of the initial fault information; use the fault result corresponding to the target sub-characterization range as the characterization detection result of the initial fault information, and based on the characterization detection results of each initial fault information, calculate the fault probability of each fault detection result of the battery pack; use each fault detection result and the fault probability of each fault detection result as the target fault information of the battery pack.

[0088] In this embodiment, the terminal, for each initial fault information, based on the characterization detection information of the initial fault information, identifies the characterization detection data of the initial fault information, and based on the characterization detection data of the initial fault information, screens the target sub-characterization range corresponding to the initial fault information from the characterization detection data of the initial fault information.

[0089] Then, the terminal uses the fault result corresponding to the target sub-characterization range as the characterization detection result of the initial fault information, and based on the characterization detection results of each initial fault information, calculates the fault probability of each fault detection result of the battery pack. Specifically, each initial fault information corresponds to a fault type, and each characterization detection result of the initial fault information corresponds to a fault probability. The terminal uses the fault probability corresponding to the characterization detection result of each initial fault information as the fault probability corresponding to the fault detection result of the initial fault information.

[0090] Finally, the terminal uses each fault detection result and the fault probability of each fault detection result as the target fault information of the battery pack.

[0091] Based on the above solution, by performing probability judgment on each fault detection result, the fault probability corresponding to each fault detection result is identified, improving the comprehensiveness and accuracy of the identification of each fault detection result existing in the battery pack.

[0092] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless specifically stated herein, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0093] Based on the same inventive concept, an embodiment of the present application further provides a battery pack fault analysis system for implementing the battery pack fault analysis method described above. The solution provided by this system to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the battery pack fault analysis system provided below can refer to the limitations on the battery pack fault analysis method in the above text, and will not be repeated here.

[0094] Further referring to Figure 2 , as an implementation of the method shown above Figure 1 , an embodiment of the present application provides a battery pack fault analysis system 200. The battery pack fault analysis system includes an acquisition module 210, a generation module 220, and an identification module 230, where:

[0095] The acquisition module 210 is configured to acquire battery pack detection information of each detection type for the battery pack, and identify the detection results of each detection type corresponding to the battery pack;

[0096] The generation module 220 is configured to predict the initial fault information of the battery pack through a battery pack fault logic analysis network based on the detection results of each detection type, and generate a fault characterization detection strategy for each initial fault information based on the fault characterization information of each initial fault information;

[0097] The identification module 230 is configured to obtain the characterization detection information of each initial fault information in response to the operation of the fault characterization detection result uploaded by the staff, and identify the target fault information of the battery pack based on the characterization detection information of each initial fault information.

[0098] Optionally, the acquisition module 210 is specifically configured to:

[0099] For each detection type, based on the battery pack detection information of the detection type, identify the detection data of the battery pack and the detection strategy of the battery pack, and based on the detection strategy of the battery pack, identify the detection logic of the detection type and the detection process of the detection type;

[0100] Split the detection data into sub-detection data of each process node of the detection process, and based on the detection logic and the sub-detection data of each process node, identify the detection result of the battery pack.

[0101] Optionally, the generation module 220 is specifically configured to:

[0102] Based on the detection logic, identify the process progression logic of each process node of the detection type, and based on the process progression logic of each process node and the sub-detection data of each process node, identify the sub-detection result of each process node;

[0103] Arrange the sub-detection results of each process node in the process order of each process node to obtain the detection result of the battery pack.

[0104] Optionally, the generation module 220 is specifically configured to:

[0105] For each detection type, based on the sub-detection results of each process node of the detection type and the process progression logic of each process node, identify the process progression reason of each process node and the process progression exception information of each process node;

[0106] Based on the process progression exception information of each process node and the process progression reason of each process node, through the sub-fault analysis network corresponding to the detection type, identify the initial fault type corresponding to each process node and the fault basis information of each initial fault type;

[0107] Use the fault basis information of each initial fault type as the initial fault information of the battery pack.

[0108] Optionally, the generation module 220 is specifically configured to:

[0109] In the fault database, query the fault characterization information of each initial fault information, and for each initial fault information, based on the fault characterization information of the initial fault information, identify the fault characterization type of each initial fault information and the fault characterization range of each initial fault information;

[0110] Based on the fault characterization type of each initial fault information, query the fault detection strategy of the fault characterization type in the fault detection database, and based on the fault characterization range of the initial fault information, query the fault results corresponding to each sub-characterization range in the fault characterization range in the database;

[0111] Take the fault detection strategy of each initial fault information and the fault results corresponding to each sub-characterization range of each initial fault information as the fault characterization detection strategy of the initial fault information.

[0112] Optionally, the recognition module 230 is specifically configured to:

[0113] For each initial fault information, based on the characterization detection information of the initial fault information, identify the characterization detection data of the initial fault information, and based on the characterization detection data of the initial fault information, screen the target sub-characterization range corresponding to the initial fault information from the characterization detection data of the initial fault information;

[0114] Take the fault result corresponding to the target sub-characterization range as the characterization detection result of the initial fault information, and based on the characterization detection results of each initial fault information, calculate the fault probability of each fault detection result of the battery pack;

[0115] Take each fault detection result and the fault probability of each fault detection result as the target fault information of the battery pack.

[0116] Each module in the above battery pack fault analysis system can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0117] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 3As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input system connected by a system bus. Among them, 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 computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, mobile cellular networks, NFC (Near Field Communication) or other technologies. When the computer program is executed by the processor, it realizes a method for analyzing battery pack failures. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input system of the computer device can be a touch layer covered on the display screen, or buttons, trackballs or touchpads provided on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0118] Those skilled in the art can understand that Figure 3 the structure shown in the figure is only a block diagram of some structures 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 some components, or have different component arrangements.

[0119] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it realizes the steps of the method described in any one of the first aspects.

[0120] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, it realizes the steps of the method described in any one of the first aspects.

[0121] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, it realizes the steps of the method described in any one of the first aspects.

[0122] It should be noted that the patient information (including but not limited to patient device information, patient personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the patient or fully authorized by all parties.

[0123] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. 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. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0124] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0125] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A battery pack failure analysis method, characterized in that: The method comprises: Acquire battery pack detection information of each detection type performed on the battery pack, and identify detection results of each detection type corresponding to the battery pack; Based on the detection results of each detection type, predict each initial fault information of the battery pack through a battery pack fault logic analysis network, and generate a fault characterization detection strategy for each initial fault information based on the fault characterization information of each initial fault information; In response to the fault characterization detection result operation uploaded by the staff, the characterization detection information of each of the initial fault information is obtained, and based on the characterization detection information of each of the initial fault information, the target fault information of the battery pack is identified.

2. The method according to claim 1, characterized in that The identifying the test results of each test type corresponding to the battery pack includes: For each detection type, based on the battery pack detection information of the detection type, identifying the detection data of the battery pack and the detection strategy of the battery pack, and based on the detection strategy of the battery pack, identifying the detection logic of the detection type and the detection process of the detection type; The detection data is split into sub-detection data of each process node of the detection process, and the detection result of the battery pack is identified based on the detection logic and the sub-detection data of each process node.

3. The method according to claim 2, characterized in that The identifying the detection result of the battery pack based on the detection logic and the sub-detection data of each process node includes: Based on the detection logic, identifying the process progression logic of each process node of the detection type, and based on the process progression logic of each process node and the sub-detection data of each process node, identifying the sub-detection result of each process node; The sub-detection results of each of the process nodes are arranged and processed according to the process sequence of each of the process nodes to obtain the detection result of the battery pack.

4. The method according to claim 3, characterized in that The battery fault logic analysis network includes sub-fault analysis networks of each detection type. Based on the detection results of each detection type, the battery pack fault logic analysis network is used to predict each initial fault information of the battery pack, including: For each detection type, based on the sub-detection results of each process node of the detection type and the process progression logic of each process node, identify the process progression reason of each process node and the process progression exception information of each process node; Based on the process progression exception information of each process node and the process progression reason of each process node, the initial fault type corresponding to each process node and the fault basis information of each initial fault type are identified through the sub-fault analysis network corresponding to the detection type; The fault basis information of each of the initial fault types is used as each of the initial fault information of the battery pack.

5. The method according to claim 1, characterized in that The generating of the fault characterization detection strategy of each of the initial fault information based on the fault characterization information of each of the initial fault information comprises: In a fault database, query the fault characterization information of each initial fault information, and for each initial fault information, identify the fault characterization type of each initial fault information and the fault characterization range of each initial fault information based on the fault characterization information of the initial fault information; Based on the fault characterization type of each initial fault information, query the fault detection strategy of the fault characterization type in the fault detection database, and based on the fault characterization range of the initial fault information, query the fault result corresponding to each sub-characterization range in the fault characterization range in the database; The fault detection strategy of each of the initial fault information and the fault result corresponding to each sub-representation range of each of the initial fault information are used as the fault representation detection strategy of the initial fault information.

6. The method according to claim 5, characterized in that The identifying target fault information of the battery pack based on the characterization detection information of each of the initial fault information includes: For each initial fault information, based on the characterization detection information of the initial fault information, identifying the characterization detection data of the initial fault information, and based on the characterization detection data of the initial fault information, screening a target sub-characterization range corresponding to the initial fault information from each characterization detection data of the initial fault information; Taking the fault result corresponding to the target sub-characterization range as the characterization detection result of the initial fault information, and calculating the fault probability of each fault detection result of the battery pack based on the characterization detection results of each initial fault information; Each of the fault detection results and the fault probability of each of the fault detection results are used as target fault information of the battery pack.

7. A battery pack fault analysis system, characterized in that: The system comprises: An acquisition module, used to acquire battery pack detection information of various detection types performed on the battery pack, and identify detection results of various detection types corresponding to the battery pack; A generating module, configured to predict each initial fault information of the battery pack based on the detection results of each detection type through a battery pack fault logic analysis network, and generate a fault characterization detection strategy for each initial fault information based on the fault characterization information of each initial fault information; The identification module is used to respond to the fault characterization detection result operation uploaded by the staff, obtain the characterization detection information of each of the initial fault information, and identify the target fault information of the battery pack based on the characterization detection information of each of the initial fault information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images