Abnormal battery detection method, device, electronic device and storage medium

Abstract

The present disclosure proposes an abnormal battery detection method, device, electronic device and storage medium, which relate to the field of new energy power batteries. The method includes: obtaining the detection time and voltage value of the battery pack to be detected in each detection process; determining the voltage change parameter corresponding to each battery pack according to the detection time and voltage value of the battery pack in each detection process; determining the cluster to which each battery pack belongs and the number of batteries contained in each cluster according to the voltage change parameter corresponding to each battery pack in the same batch of battery packs; when the number of batteries contained in any cluster is less than the number threshold, determining the battery pack in any cluster as an abnormal battery pack. In this way, it is possible to realize abnormal identification in the battery pack production process, enhance the detection effect of defects with slight change trends, help improve and troubleshoot battery pack process defects, improve the qualification rate and safety of battery packs, and effectively avoid battery accidents.

Description

Technical Field

[0001] The present disclosure relates to the field of new energy power batteries, and in particular to an abnormal battery detection method, device, electronic device, and storage medium. Background Art

[0002] Safety is a core concern for new energy vehicle power batteries. Battery thermal events not only bring negative public opinion and financial losses to automakers, but also pose life and property risks to electric vehicle users. Given the frequent occurrence of thermal events in new energy vehicles within the industry, more precise interception and prevention of abnormal battery outflow during the production phase is more meaningful than early warning and interception during product operation. This not only prevents safety incidents but also saves the industry significant manpower and resources. Summary of the Invention

[0003] The present disclosure aims to solve one of the technical problems in the related art at least to a certain extent.

[0004] The first embodiment of the present disclosure provides a method for detecting abnormal batteries, including:

[0005] Obtain the test time and voltage value of the battery pack to be tested in each test process;

[0006] Determining a voltage variation parameter corresponding to each battery pack according to the detection time and voltage value of the battery pack in each detection process;

[0007] Determining the cluster to which each battery pack belongs and the number of batteries contained in each cluster based on the voltage variation parameter corresponding to each battery pack in the same batch of battery packs;

[0008] When the number of batteries included in any cluster is less than a quantity threshold, the battery pack in the cluster is determined to be an abnormal battery pack.

[0009] A second embodiment of the present disclosure provides an abnormal battery detection device, comprising:

[0010] The first acquisition module is used to obtain the detection time and voltage value of the battery pack to be detected in each detection process;

[0011] A first determining module is configured to determine a voltage variation parameter corresponding to each battery pack according to a detection time and a voltage value of the battery pack in each detection process;

[0012] a second determining module, configured to determine the cluster to which each battery pack belongs and the number of batteries contained in each cluster based on the voltage variation parameter corresponding to each battery pack in the same batch of battery packs;

[0013] The third determining module is configured to determine that the battery packs in any cluster are abnormal battery packs when the number of batteries contained in any cluster is less than a quantity threshold.

[0014] The third embodiment of the present disclosure proposes an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the abnormal battery detection method proposed in the first embodiment of the present disclosure is implemented.

[0015] The fourth embodiment of the present disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the abnormal battery detection method provided in the first embodiment of the present disclosure is implemented.

[0016] The abnormal battery detection method, device, electronic device, and storage medium provided by the present disclosure have the following beneficial effects:

[0017] In the disclosed embodiment, all battery packs in the same batch are clustered based on the voltage variation parameters of each battery pack between testing steps. All battery packs within any cluster containing fewer than a threshold number of battery packs are identified as abnormal batteries, thereby completing abnormal battery detection. This enables abnormality identification during the battery pack production process, enhances the detection of defects with slight variation trends, helps improve and troubleshoot battery pack process defects, increases battery pack qualification rate and safety, and effectively prevents battery accidents.

[0018] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0020] Figure 1 A flowchart of an abnormal battery detection method provided by an embodiment of the present disclosure;

[0021] Figure 2 A flowchart of an abnormal battery detection method provided by another embodiment of the present disclosure;

[0022] Figure 3 A flowchart of an abnormal battery detection method provided by another embodiment of the present disclosure;

[0023] Figure 4 A flowchart of an abnormal battery detection method provided by another embodiment of the present disclosure;

[0024] Figure 5 A schematic structural diagram of an abnormal battery detection device provided by one embodiment of the present disclosure;

[0025] Figure 6 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0026] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0027] The abnormal battery detection method, device, electronic device, and storage medium according to embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0028] Figure 1 A flowchart of an abnormal battery detection method provided by an embodiment of the present disclosure is provided.

[0029] The embodiment of the present disclosure uses the abnormal battery detection method configured in an abnormal battery detection device as an example. The abnormal battery detection device can be applied to any electronic device so that the electronic device can perform an abnormality detection function during the battery pack production process.

[0030] like Figure 1 As shown, the abnormal battery detection method may include the following steps:

[0031] Step 101: Obtain the detection time and voltage value of the battery pack to be detected in each detection process.

[0032] Among them, a battery pack is a battery system that combines multiple battery cells (i.e., battery cells) according to a certain configuration and connection method.

[0033] It's important to note that after a battery cell rolls off the production line, environmental conditions, human error, and substandard process conditions during the production process can cause irreversible damage to the battery, impacting the safety of the pack. Therefore, it's necessary to perform anomaly detection on the battery pack at each step of the production process to identify defects with subtle trends. This can effectively intercept abnormal batteries and prevent them from entering the market.

[0034] In the embodiment of the present disclosure, each process of pack production is a detection process, and the pack production processes are in the following order: open circuit voltage (OCV) test of battery cell, single module communication test, PACK communication test, end of line (EOL) test of battery pack production line and vehicle electrical inspection test. The voltage value of each detection process is the cell voltage measured by the battery pack in the detection process. In addition, the start time of each detection process can be determined as the detection time of the detection process.

[0035] Step 102 : determining a voltage variation parameter corresponding to each battery pack according to the detection time and voltage value of the battery pack in each detection process.

[0036] Among them, the voltage change parameter is used to describe the voltage change characteristics of the battery cells between each process in the production process of the battery pack. It can include multiple voltage change values, each of which is the average daily voltage drop between two detection processes.

[0037] In the embodiment of the present disclosure, since some battery defects are not obvious in appearance and in a short period of time, they need to be identified based on the trend changes in the time dimension. Therefore, the difference between the voltage values ​​of each two detection processes and the time difference between the corresponding detection times can be calculated based on the voltage value of the battery pack in each detection process. The obtained difference is then divided by the time difference to obtain the voltage change value between the two detection processes, thereby obtaining the voltage change parameter corresponding to each battery pack.

[0038] It should be noted that the two detection processes corresponding to the voltage change value can be two adjacent detection processes or two non-adjacent detection processes. This can make the time dimension corresponding to the voltage change parameter wider, the change more obvious, and be more conducive to detecting abnormalities.

[0039] For example, for a battery pack to be tested, the voltage change value dv1 between the battery cell offline and the OCV test, the voltage change value dv2 between the OCV test and single-module communication, the voltage change value dv3 between single-module communication and dual-module communication, the voltage change value dv4 between dual-module communication and the EOL test of the pack, the voltage change value dv5 between the OCV test and dual-module communication, the voltage change value dv6 between the OCV test and the EOL test of the pack, and the voltage change value dv7 between single-module communication and dual-module communication can be determined, thereby obtaining the voltage change parameters dv1, dv2, dv3, dv4, dv5, dv6 and dv7 corresponding to the battery pack to be tested.

[0040] Step 103 : determining the cluster to which each battery pack belongs and the number of batteries contained in each cluster based on the voltage variation parameter corresponding to each battery pack in the same batch of battery packs.

[0041] In the embodiment of the present disclosure, any clustering algorithm including but not limited to birch, k-means, DBSCAN, particle swarm, etc. can be selected to build a battery anomaly detection model. Then, using this detection model, all battery packs in the same batch are divided into multiple clusters according to the voltage change parameters corresponding to each battery pack in the same batch of battery packs, and the cluster to which each battery pack belongs and the number of batteries contained in each cluster are determined.

[0042] For example, the model uses the k-means algorithm to divide all battery packs from the same batch into K clusters, where the initial value of K can be 3. Based on the similarity measure between the voltage variation parameters corresponding to each battery pack, battery packs with similar voltage variation parameters are grouped into the same cluster, while battery packs with dissimilar voltage variation parameters are grouped into different clusters.

[0043] Alternatively, in an embodiment of the present application, a model may not be used, but the battery packs may be clustered directly based on the similarity between the voltage change parameters corresponding to each battery pack, divided into multiple clusters, and the number of batteries contained in each cluster may be obtained.

[0044] Step 104 : When the number of batteries in any cluster is less than a quantity threshold, determine that the battery pack in any cluster is an abnormal battery pack.

[0045] The quantity threshold may be 1% or 2% of the total number of battery packs to be detected, etc., and may be determined based on experience or detection accuracy requirements, etc., and is not limited in this disclosure.

[0046] In the embodiment of the present disclosure, after determining the number of batteries contained in each cluster, the number can be compared with the number threshold. If the number of batteries contained in any cluster is less than the number threshold, it means that the voltage data of the battery pack in any cluster is abnormal. It can be determined that the battery pack in the cluster is defective and is an abnormal battery pack, thereby completing the abnormal battery detection.

[0047] In the disclosed embodiment, the detection time and voltage value of the battery pack to be inspected in each detection process are first obtained. Then, based on the detection time and voltage value of the battery pack in each detection process, the voltage variation parameter corresponding to each battery pack is determined. Thereafter, based on the voltage variation parameter corresponding to each battery pack in the same batch of battery packs, the cluster to which each battery pack belongs and the number of batteries contained in each cluster are determined. In the case where the number of batteries contained in any cluster is less than a quantity threshold, the battery pack in any cluster is determined to be an abnormal battery pack. Thus, by clustering all battery packs in the same batch based on the voltage variation parameter of each battery pack between detection processes, all battery packs in any cluster containing a number of battery packs less than the threshold are determined to be abnormal batteries, thereby completing the abnormal battery detection. This makes it possible to identify abnormalities in the battery pack production process, enhance the detection effect of defects with slight variation trends, help improve and troubleshoot battery pack process defects, improve the qualification rate and safety of battery packs, and effectively avoid battery accidents.

[0048] It should be noted that the abnormal battery detection method proposed in this disclosure can be applied not only to the battery pack production process, but also to other product production scenarios. The scenarios in which abnormalities can be detected include, but are not limited to: when incoming battery cells have a slightly higher self-discharge rate, they are outliers; during battery cell transportation, a discharge path occurs, resulting in a lower battery cell voltage; during module assembly, improper anti-static operation causes micro-short circuits; micro-short circuits caused by human error; and slight voltage fluctuations caused by abnormal voltage and temperature sampling in the module / pack.

[0049] Figure 2 A flowchart of an abnormal battery detection method provided by an embodiment of the present disclosure is shown as follows: Figure 2 As shown, the abnormal battery detection method may include the following steps:

[0050] Step 201 : Obtain the detection time and voltage value of the battery pack to be detected in each detection process.

[0051] For a detailed description of the above step 201, please refer to other embodiments of the present disclosure and will not be repeated here.

[0052] In step 202 , a plurality of voltage variation values ​​corresponding to the battery pack are determined according to the detection time and voltage value of the battery pack in each detection process.

[0053] In the embodiment of the present disclosure, any two detection processes of the battery pack can be selected, and the difference between the voltage values ​​of the two detection processes and the time difference between the corresponding detection times can be calculated. The obtained difference is then divided by the time difference to obtain the voltage change value between the two detection processes. Thereafter, the voltage change values ​​are calculated for the other two detection processes, thereby obtaining multiple voltage change values ​​corresponding to each battery pack.

[0054] It should be noted that the two detection steps corresponding to each voltage change value may be two detection steps that are adjacent in detection order, or two detection steps that are not adjacent in detection order. Therefore, the method for determining the voltage change value may be one or more of the following:

[0055] Optionally, the voltage change value of the battery pack between each two adjacent detection steps may be determined based on the detection time and voltage value of the battery pack in each two adjacent detection steps.

[0056] Furthermore, the voltage change value of the battery pack between any two testing steps may be determined based on the testing time and voltage value of the battery pack in any two testing steps.

[0057] For example, all inspection processes of a battery pack are, in order, process A, process B, and process C. The inspection time and voltage values ​​of process A are t1 and v1, the inspection time and voltage values ​​of process B are t2 and v2, and the inspection time and voltage values ​​of process C are t3 and v3. The multiple voltage change values ​​corresponding to the battery pack may include: voltage change values ​​dv1 = (v1-v2) / (t2-t1) corresponding to processes A and B, dv2 = (v2-v3) / (t3-t2) corresponding to processes B and C, and dv3 = (v1-v3) / (t3-t1) corresponding to processes A and C.

[0058] In the embodiment of the present disclosure, by calculating the voltage change value of two adjacent detection processes or any two detection processes, the voltage change characteristics of the battery pack between the various production processes can be clarified, which helps to identify defects that are not obvious in a short period of time and improve the reliability of abnormality detection.

[0059] Step 203 : determining the cluster to which each battery pack belongs and the number of batteries contained in each cluster based on the multiple voltage change values ​​corresponding to each battery pack in the same batch of battery packs.

[0060] In the embodiment of the present disclosure, the multiple voltage change values ​​are the voltage change parameters in the above embodiment. The detailed description of step 203 can refer to the above embodiment of the present disclosure and will not be repeated here.

[0061] Step 204 : When the number of batteries in any cluster is less than a quantity threshold, determine that the battery pack in any cluster is an abnormal battery pack.

[0062] For a detailed description of the above step 204, please refer to other embodiments of the present disclosure and will not be repeated here.

[0063] In the embodiment of the present disclosure, the process section where the battery abnormality occurs can be located based on the characteristic changes between different processes, and it can be checked whether it is caused by process defects, providing a direction for checking and improving the process defects.

[0064] In the disclosed embodiment, multiple voltage change values ​​corresponding to the battery pack are determined based on the detection time and voltage value of the battery pack in each detection process, and then abnormality detection is performed. This can clarify the voltage change characteristics of the battery pack between various production processes, help identify faults that are not obvious in a short period of time, check defects in the production process, and improve the reliability of abnormality detection.

[0065] Figure 3 This is a signaling interaction diagram of an abnormal battery detection method provided by an embodiment of the present disclosure, such as Figure 3 As shown, the abnormal battery detection method may include the following steps:

[0066] Step 301: Obtain the detection time and voltage value of the battery pack to be detected in each detection process.

[0067] Step 302 : determining a voltage variation parameter corresponding to each battery pack according to the detection time and voltage value of the battery pack in each detection process.

[0068] For detailed description of the above steps 301 and 302, please refer to other embodiments of the present disclosure and will not be repeated here.

[0069] Step 303 : determining a parameter matrix corresponding to the same batch of battery packs based on the voltage variation parameter corresponding to each battery pack in the same batch of battery packs.

[0070] Among them, the parameters in each row of the parameter matrix are the voltage change parameters corresponding to a battery pack, and the parameters in each column of the parameter matrix are the voltage change parameters of each battery pack in the same dimension.

[0071] In the disclosed embodiment, a parameter matrix representing the voltage variation characteristics of the same batch of battery packs can be constructed, and the voltage variation parameters corresponding to each battery pack in the same batch of battery packs are listed in the matrix according to the row and column arrangement rules of the parameter matrix to obtain the parameter matrix corresponding to the same batch of battery packs.

[0072] It is understood that the rows of the parameter matrix represent the sample numbers corresponding to each battery pack in the same batch, and the number of rows corresponds to the number of battery packs in the same batch, with the number of battery packs in a batch being no less than 10,000. Each column of the parameter matrix is ​​a one-dimensional vector consisting of the voltage change values ​​determined for all battery packs under the same two test steps.

[0073] In step 304 , the parameter matrix is ​​input into a preset detection model to obtain the cluster to which each battery pack belongs and the number of batteries contained in each cluster output by the detection model.

[0074] The preset detection matrix can be used to cluster the data in the parameter matrix based on similarity to obtain multiple data clusters. Clustering algorithms that can be selected for the detection matrix include but are not limited to birch, k-means, DBSCAN, particle swarm, etc.

[0075] In an embodiment of the present disclosure, the parameter matrix corresponding to the same batch of battery packs can be input into a preset detection model, and all battery packs can be clustered by the detection matrix to obtain the cluster to which each battery pack belongs and the number of batteries contained in each cluster output by the detection model.

[0076] It should be noted that each cluster output by the detection model can be distinguished by a label, such as 0, 1, 2, etc.

[0077] It should be noted that because the absolute value of the difference between the voltage change parameters is small and the clustering algorithm involves distance measurement, it is not suitable for linear normalization. Therefore, standard deviation normalization is used to process the parameter matrix in this disclosure, which can accelerate the convergence speed of the clustering algorithm, improve the performance of the detection model for anomaly detection, and improve stability.

[0078] Optionally, the standard deviation of each row element in the parameter matrix may be normalized to obtain a normalized parameter matrix, and then the normalized parameter matrix may be input into a preset detection model.

[0079] In the embodiment of the present disclosure, the standard deviation normalization used, also known as z-score normalization, can adjust each row element in the parameter matrix to a distribution with a mean of 0 and a standard deviation of 1, so that the processed parameter matrix is ​​suitable for situations where the data is approximately Gaussian distributed and distance measurement is required.

[0080] In this embodiment, a preset detection matrix is ​​used to cluster battery packs from the same batch based on a parameter matrix determined by the voltage variation parameters corresponding to each battery pack in the batch. The cluster to which each battery pack belongs and the number of batteries within each cluster are determined. This enables automated battery anomaly detection and improves battery testing efficiency.

[0081] Step 305 : When the number of batteries in any cluster is less than a quantity threshold, the battery pack in any cluster is determined to be an abnormal battery pack.

[0082] For a detailed description of the above step 305, please refer to other embodiments of the present disclosure and will not be repeated here.

[0083] In step 306 , the detection time and voltage value of each detection process corresponding to the battery packs in any cluster are determined as data to be verified.

[0084] In the disclosed embodiment, after determining that the battery pack in any cluster is an abnormal battery pack, the batteries with smaller outliers can be selected from the detected abnormal batteries for disassembly and analysis. Therefore, the detection time and voltage value of each detection process corresponding to the battery pack in any cluster can be determined as the data to be verified, which is used to further verify whether the battery pack is abnormal.

[0085] Step 307: Send the data to be verified to the data verification device.

[0086] In the embodiment of the present disclosure, the data to be verified can be sent to a data verification device to automatically verify the anomaly detection result.

[0087] Step 308, when the verification result returned by the verification device indicates that the battery pack in any cluster has passed the verification, the preset detection model is updated until the number of battery packs contained in the cluster to which the battery pack in any cluster belongs determined based on the detection model is greater than or equal to the number threshold.

[0088] In the embodiment of the present disclosure, when the verification result returned by the verification device indicates that the battery pack in any cluster has passed the verification, there is no abnormality in the battery pack. At this time, it may be because the parameters of the detection model are not accurate enough, resulting in abnormal detection failure, so the parameters of the detection model need to be adjusted and updated until the updated detection model determines that the cluster whose detection result was abnormal before is no longer abnormal, that is, the number of battery packs contained in the cluster to which the battery pack in the cluster belongs is greater than or equal to the quantity threshold.

[0089] It should be noted that in the present disclosure, the model parameters can be updated according to a fixed correction gradient, or a grid search can be added to achieve automatic parameter tuning based on the offline results of abnormal samples to complete the update of the detection model.

[0090] Alternatively, the central battery pack corresponding to each cluster output by the detection model can be determined. Then, based on the voltage variation parameter corresponding to each battery pack, the distance between the first central battery pack corresponding to any cluster and the second central battery pack corresponding to another cluster can be determined. A model update gradient can then be determined based on the distance, and the preset detection model can be updated based on the updated gradient.

[0091] In the disclosed embodiment, the initial number of cluster centers in the detection model can be set as needed (for example, 3). After obtaining all battery packs corresponding to each cluster using Euclidean distance as a similarity metric between voltage variation parameters, the central battery pack corresponding to each cluster can be determined based on the distance between the voltage variation parameters of the battery packs within the cluster. The distance between the first central battery pack corresponding to any cluster and the second central battery packs corresponding to other clusters can then be calculated. The first central battery pack can then be assigned to the cluster with the closest distance. The average value of all data points within each cluster is then recalculated and used as the new cluster center, completing one iteration of the model update.

[0092] It should be noted that model updating is a multi-iteration process. When the model reaches the convergence condition, the model update can be determined to be complete. The convergence condition can be that the number of iterations reaches a preset maximum value, for example, 300.

[0093] In this embodiment, the detection time and voltage values ​​for each detection process corresponding to the battery packs in any cluster are first determined as the data to be verified. This data is then sent to a data verification device. Upon receiving a verification result from the verification device indicating that the battery packs in any cluster have passed verification, the preset detection model is updated until the number of battery packs in the cluster to which the battery packs in any cluster belong, as determined by the detection model, is greater than or equal to a threshold number. Thus, by further verifying battery packs with abnormal detection results and updating the detection model parameters when it is determined that the battery packs are normal, the accuracy and stability of the detection model can be improved.

[0094] Figure 4 This is a signaling interaction diagram of an abnormal battery detection method provided by an embodiment of the present disclosure, such as Figure 4 As shown, the abnormal battery detection method may include the following steps:

[0095] Step 401 : Obtain the detection time and voltage value of the battery pack to be detected in each detection process.

[0096] Step 402 : determining a voltage variation parameter corresponding to each battery pack according to the detection time and voltage value of the battery pack in each detection process.

[0097] Step 403 : Determine the cluster to which each battery pack belongs and the number of batteries contained in each cluster based on the voltage variation parameter corresponding to each battery pack in the same batch of battery packs.

[0098] For detailed description of steps 401 to 403 , please refer to other embodiments of the present disclosure and will not be repeated here.

[0099] Step 404 : determining a quantity threshold value based on the total quantity of batteries contained in the same batch of battery packs and at least one of the test results corresponding to the reference batch of battery packs.

[0100] The performance parameters of the reference batch of battery packs match the performance parameters of the same batch of battery packs to a degree greater than the matching threshold.

[0101] In the disclosed embodiment, since the performance parameters of the reference batch of battery packs match the performance parameters of the same batch of battery packs to a greater degree than the matching threshold, the voltage variations during the production process should also be similar. Therefore, based on the proportion of abnormal battery packs in the test results of the reference battery packs, the percentage of the quantity threshold in the total number of battery packs in the batch is determined, and then the quantity threshold is determined in combination with the total number of batteries contained in the same batch of battery packs. For example, the percentage corresponding to the quantity threshold is 1%, or 2%, and so on, of the total number. Alternatively, the quantity threshold can be determined based only on the total number of batteries contained in the same batch of battery packs or the test results corresponding to the reference batch of battery packs.

[0102] Step 405 : When the number of batteries in any cluster is less than a quantity threshold, the battery pack in any cluster is determined to be an abnormal battery pack.

[0103] For a detailed description of the above step 405, please refer to other embodiments of the present disclosure and will not be repeated here.

[0104] In this embodiment, by determining the quantity threshold based on the total number of batteries contained in the same batch of battery packs and at least one of the test results corresponding to the reference batch of battery packs, it is possible to avoid setting the quantity threshold unrealistically, which may lead to inaccurate test results, and provide conditions for improving the reliability of abnormal detection results.

[0105] In order to implement the above embodiments, the present disclosure also provides an abnormal battery detection device.

[0106] Figure 5 This is a schematic diagram of the structure of the abnormal battery detection device provided by an embodiment of the present disclosure.

[0107] like Figure 5 As shown, the abnormal battery detection device 500 may include:

[0108] The first acquisition module 501 is used to obtain the detection time and voltage value of the battery pack to be detected in each detection process;

[0109] A first determining module 502 is configured to determine a voltage variation parameter corresponding to each battery pack based on the detection time and voltage value of the battery pack in each detection process;

[0110] A second determining module 503 is configured to determine the cluster to which each battery pack belongs and the number of batteries contained in each cluster based on the voltage variation parameter corresponding to each battery pack in the same batch of battery packs;

[0111] The third determining module 504 is configured to determine that the battery packs in any cluster are abnormal battery packs when the number of batteries in any cluster is less than a quantity threshold.

[0112] Optionally, the first determining module 502 may be specifically configured to:

[0113] According to the detection time and voltage value of the battery pack in each detection process, a plurality of voltage change values ​​corresponding to the battery pack are determined.

[0114] Optionally, the first determining module 502 may be configured to perform one or more of the following:

[0115] Determine the voltage change value of the battery pack between each two adjacent testing steps based on the testing time and voltage value of the battery pack in each two adjacent testing steps;

[0116] According to the detection time and voltage value of the battery pack in any two detection processes, the voltage change value corresponding to the battery pack between any two detection processes is determined.

[0117] Optionally, the second determining module 503 may be specifically configured to:

[0118] Determine the parameter matrix corresponding to the same batch of battery packs based on the voltage variation parameters corresponding to each battery pack in the same batch of battery packs, where each row parameter in the parameter matrix is ​​the voltage variation parameter corresponding to one battery pack, and each column parameter in the parameter matrix is ​​the voltage variation parameter of each battery pack in the same dimension;

[0119] The parameter matrix is ​​input into the preset detection model to obtain the cluster to which each battery pack belongs and the number of batteries contained in each cluster output by the detection model.

[0120] Optionally, the third determining module 504 may also be used to:

[0121] Determine the detection time and voltage value of each detection process corresponding to the battery pack in any cluster as the data to be verified;

[0122] Sending the data to be verified to the data verification device;

[0123] When the verification result returned by the verification device indicates that the battery pack in any cluster has passed the verification, the preset detection model is updated until the number of battery packs contained in the cluster to which the battery pack in any cluster belongs, as determined based on the detection model, is greater than or equal to the quantity threshold.

[0124] Optionally, the third determining module 504 may also be used to:

[0125] Determine the central battery pack corresponding to each cluster output by the detection model;

[0126] Determine the distance between the first central battery pack corresponding to any cluster and the second central battery pack corresponding to other clusters based on the voltage variation parameter corresponding to each battery pack;

[0127] According to the distance, determine the model update gradient;

[0128] Based on the updated gradient, the preset detection model is updated.

[0129] Optionally, the third determining module 504 may be specifically configured to:

[0130] Normalize the standard deviation of each row element in the parameter matrix to obtain a normalized parameter matrix;

[0131] Input the normalized parameter matrix into the preset detection model.

[0132] Optionally, the abnormal battery detection device 500 may further include:

[0133] The fourth determination module is used to determine the quantity threshold based on the total number of batteries contained in the same batch of battery packs and at least one of the test results corresponding to the reference batch of battery packs, wherein the performance parameters of the reference batch of battery packs have a matching degree with the performance parameters of the same batch of battery packs that is greater than the matching threshold.

[0134] The functions and specific implementation principles of the above modules in the embodiments of the present disclosure can be referred to the above method embodiments and will not be repeated here.

[0135] The abnormal battery detection device of the disclosed embodiment clusters all battery packs from the same batch based on the voltage variation parameters of each battery pack between testing steps. It then identifies all battery packs within any cluster containing fewer than a threshold number of battery packs as abnormal batteries, thereby completing abnormal battery detection. This enables abnormality identification during the battery pack production process, enhances the detection of defects with slight variation trends, helps improve and troubleshoot battery pack process defects, increases the pass rate and safety of battery packs, and effectively prevents battery accidents.

[0136] In order to implement the above embodiments, the present disclosure also proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the abnormal battery detection method proposed in the above embodiments of the present disclosure is implemented.

[0137] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the abnormal battery detection method proposed in the above embodiments of the present disclosure is implemented.

[0138] Figure 6 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Figure 5 The electronic device 12 shown is only an example and should not limit the functionality and scope of use of the embodiments of the present disclosure.

[0139] like Figure 6 As shown, electronic device 12 is implemented as a general-purpose computing device. Components of electronic device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 that connects various system components (including system memory 28 and processing unit 16).

[0140] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of such architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnection (PCI) bus.

[0141] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0142] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 6 Not shown, often called a "hard drive"). Although Figure 6 Although not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a Compact Disc Read Only Memory (hereinafter referred to as: CD-ROM), a Digital Video Disc Read Only Memory (hereinafter referred to as: DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the various embodiments of the present disclosure.

[0143] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally implement the functions and / or methods of the embodiments described herein.

[0144] The electronic device 12 can also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and / or any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). This communication can occur via an input / output (I / O) interface 22. Furthermore, the electronic device 12 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that, although not shown, other hardware and / or software modules can be used in conjunction with the electronic device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0145] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the methods mentioned in the above embodiments.

[0146] The technical solution disclosed in the present invention can realize the identification of anomalies in the battery pack production process, enhance the detection effect of defects with slight change trends, help to improve and troubleshoot battery pack process defects, improve the qualification rate and safety of battery packs, and effectively avoid battery accidents.

[0147] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and features of different embodiments or examples, unless they are mutually inconsistent.

[0148] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0149] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure belong.

[0150] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0151] It should be understood that various parts of the present disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0152] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0153] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0154] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. A person of ordinary skill in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for detecting abnormal batteries, characterized in that: include: Obtain the test time and voltage value of the battery pack to be tested in each test process; Determining a voltage variation parameter corresponding to each battery pack according to the detection time and voltage value of the battery pack in each detection process; Determine a parameter matrix corresponding to the same batch of battery packs based on the voltage variation parameters corresponding to each battery pack in the same batch of battery packs, wherein each row parameter in the parameter matrix is ​​a voltage variation parameter corresponding to one battery pack, and each column parameter in the parameter matrix is ​​a voltage variation parameter of each battery pack in the same dimension; Input the parameter matrix into a preset detection model to obtain the cluster to which each battery pack belongs and the number of batteries contained in each cluster output by the detection model; When the number of batteries contained in any cluster is less than a quantity threshold, determining that the battery pack in any cluster is an abnormal battery pack; Determining the detection time and voltage value of each detection process corresponding to the battery packs in any one of the clusters as data to be verified; Sending the data to be verified to a data verification device; When the verification result returned by the verification device indicates that the battery packs in any cluster have passed the verification, the preset detection model is updated until the number of battery packs contained in the cluster to which the battery packs in any cluster belong, as determined based on the detection model, is greater than or equal to the number threshold.

2. The method according to claim 1, wherein Determining the voltage variation parameter corresponding to each battery pack according to the detection time and voltage value of the battery pack in each detection process includes: A plurality of voltage change values ​​corresponding to the battery pack are determined according to the detection time and voltage value of the battery pack in each detection process.

3. The method according to claim 2, wherein Determining a plurality of voltage change values ​​corresponding to the battery pack according to the detection time and voltage value of the battery pack in each detection process includes one or more of the following: Determining a voltage change value of the battery pack between each two adjacent detection steps according to the detection time and voltage value of the battery pack in each two adjacent detection steps; According to the detection time and voltage value of the battery pack in any two detection processes, the voltage change value of the battery pack corresponding to the two detection processes is determined.

4. The method according to claim 1, wherein The updating of the preset detection model includes: Determine a central battery pack corresponding to each cluster output by the detection model; determining, based on a voltage variation parameter corresponding to each of the battery packs, a distance between a first central battery pack corresponding to any one of the clusters and a second central battery pack corresponding to another cluster; Determining a model update gradient based on the distance; Based on the update gradient, the preset detection model is updated.

5. The method according to claim 1, wherein Inputting the parameter matrix into a preset detection model includes: Normalizing the standard deviation of each row element in the parameter matrix to obtain a normalized parameter matrix; The normalized parameter matrix is ​​input into the preset detection model.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: The quantity threshold is determined based on the total number of batteries contained in the same batch of battery packs and at least one of the test results corresponding to the reference batch of battery packs, wherein the performance parameters of the reference batch of battery packs match the performance parameters of the same batch of battery packs to a degree greater than the matching threshold.

7. An abnormal battery detection device, characterized in that: The device comprises: The first acquisition module is used to obtain the detection time and voltage value of the battery pack to be detected in each detection process; A first determining module is configured to determine a voltage variation parameter corresponding to each battery pack according to a detection time and a voltage value of the battery pack in each detection process; A second determination module is configured to determine a parameter matrix corresponding to the same batch of battery packs based on the voltage variation parameters corresponding to each battery pack in the same batch of battery packs, wherein each row of parameters in the parameter matrix represents a voltage variation parameter corresponding to one battery pack, and each column of parameters in the parameter matrix represents a voltage variation parameter of each battery pack in the same dimension; input the parameter matrix into a preset detection model to obtain the cluster to which each battery pack belongs and the number of batteries contained in each cluster, as output by the detection model; The third determination module is used to determine that the battery packs in any cluster are abnormal battery packs when the number of batteries contained in any cluster is less than a quantity threshold; determine the detection time and voltage value of each detection process corresponding to the battery packs in any cluster as data to be verified; send the data to be verified to a data verification device; and update the preset detection model when receiving a verification result returned by the verification device indicating that the battery packs in any cluster have passed the verification, until the number of battery packs contained in the cluster to which the battery packs in any cluster belong, as determined based on the detection model, is greater than or equal to the quantity threshold.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the abnormal battery detection method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the abnormal battery detection method according to any one of claims 1 to 6 is implemented.

Images