Battery pack fault diagnosis method and device, electronic equipment, readable storage medium and computer program product

Abstract

The invention discloses a battery pack fault diagnosis method. The method comprises the following steps: acquiring an original voltage sequence of each battery cell of a battery pack of the electric vehicle in a driving state and a charging state; preprocessing the original voltage sequence to obtain a preprocessed voltage sequence; according to a preset sliding window and the preprocessing voltage sequence, calculating a normalized two-dimensional voltage feature vector corresponding to each sliding window; according to a preset algorithm parameter, a density clustering algorithm and the normalized two-dimensional voltage feature vector, performing dynamic identification on each cell of the electric vehicle battery pack to obtain an abnormal cluster identification result; and performing corresponding abnormal cell fault early warning operation on the abnormal cluster identification result according to a preset multi-level risk threshold. According to the method, the battery pack fault in the running process of the electric vehicle can be detected on line, the fault battery cell can be accurately positioned, the response rate is improved, and dependence on off-line data is avoided, so that the thermal runaway condition is avoided, and subsequent fault maintenance is facilitated.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle fault diagnosis, and specifically to a battery pack fault diagnosis method, device, electronic device, readable storage medium and computer program product. Background Art

[0002] The electric vehicle industry is booming at an unprecedented rate. As a core component of electric vehicles, battery packs face increasingly prominent safety concerns, becoming a critical challenge that the entire industry urgently needs to address. Existing battery pack fault detection schemes typically pre-set thresholds for key parameters such as voltage and temperature. Once the monitored data exceeds these thresholds, the system triggers a fault alarm. However, in practical applications, this detection method has significant shortcomings. It can only assess abnormalities in the overall battery pack state and cannot accurately locate specific abnormalities. Moreover, the setting of thresholds relies heavily on the engineer's experience and lacks a scientific and precise basis, which significantly reduces the sensitivity of anomaly identification. Therefore, existing methods suffer from insufficient fault location accuracy and a high false alarm rate, seriously affecting the accuracy and timeliness of battery pack fault detection, posing a potential risk to the safe and stable operation of electric vehicles. Summary of the Invention

[0003] In view of the above problems, the present application provides a battery pack fault diagnosis method, device, electronic device, readable storage medium and computer program product, which can solve the problems of insufficient fault location accuracy, high false alarm rate and insufficient accuracy and timeliness of battery pack fault detection.

[0004] In a first aspect, the present application provides a battery pack fault diagnosis method, comprising:

[0005] Obtain the original voltage sequence of each cell in the electric vehicle battery pack during driving and charging;

[0006] Preprocessing the original voltage sequence to obtain a preprocessed voltage sequence;

[0007] Calculating a normalized two-dimensional voltage feature vector corresponding to each sliding window according to a preset sliding window and the preprocessed voltage sequence;

[0008] Dynamically identifying each cell of the electric vehicle battery pack according to preset algorithm parameters, density clustering algorithm and the normalized two-dimensional voltage feature vector to obtain abnormal cluster identification results;

[0009] The abnormal cell fault warning operation is performed correspondingly on the abnormal cluster identification result according to the preset multi-level risk threshold.

[0010] In the above technical solution, the method can detect battery pack faults of electric vehicles online in real time, accurately locate faulty cells, and implement multi-level risk warnings, thereby improving the accuracy and timeliness of fault diagnosis and helping to avoid safety accidents such as thermal runaway.

[0011] In some embodiments, preprocessing the original voltage sequence to obtain a preprocessed voltage sequence includes:

[0012] reordering the original voltage sequence in descending order of timestamps to obtain a first processed sequence;

[0013] Performing data missing and outlier processing on the first processing sequence to obtain a second processing sequence;

[0014] Perform logarithmic transformation on the second processing sequence to obtain a preprocessing voltage sequence.

[0015] In the above technical solution, this method can effectively handle timestamp sorting errors, data missing and outlier problems in the original voltage sequence, thereby obtaining a high-quality preprocessed voltage sequence and providing a reliable data basis for subsequent fault diagnosis.

[0016] In some embodiments, calculating a normalized two-dimensional voltage feature vector corresponding to each sliding window according to a preset sliding window and the preprocessed voltage sequence includes:

[0017] Dividing the preprocessed voltage sequence through a preset sliding window to obtain a plurality of voltage subsequences;

[0018] Calculating a voltage consistency feature and a modified Shannon entropy feature corresponding to each sliding window according to the multiple voltage subsequences;

[0019] Constructing a two-dimensional feature matrix corresponding to each sliding window according to the voltage consistency feature and the modified Shannon entropy feature;

[0020] The two-dimensional feature matrix is ​​normalized to obtain a two-dimensional normalized feature matrix corresponding to each sliding window.

[0021] In the above technical solution, this method can effectively extract key features from the preprocessed voltage sequence, and provide representative feature data for subsequent density clustering analysis and fault diagnosis by constructing and normalizing a two-dimensional feature matrix.

[0022] In some embodiments, performing corresponding abnormal cell failure warning operations on the abnormal cluster identification results according to preset multi-level risk thresholds includes:

[0023] According to the abnormal cluster identification result, the frequency of each battery cell being marked as an abnormal cluster is counted to obtain the abnormal marking frequency corresponding to each battery cell;

[0024] Determine the abnormal cell identification result according to the abnormal marking frequency and the preset multi-level risk threshold; wherein the abnormal cell identification result includes a low-risk abnormal cell, a medium-risk abnormal cell, and a high-risk abnormal cell; wherein the preset multi-level risk threshold includes a low-risk threshold, a medium-risk threshold, and a high-risk threshold;

[0025] Output abnormal cell prompt information including the abnormal cell identification result.

[0026] In the above technical solution, the method can achieve multi-level early warning and refined management of battery pack failures.

[0027] In some embodiments, the method further comprises:

[0028] Continuously monitoring the high-risk abnormal battery cells to obtain monitoring results;

[0029] When thermal runaway is detected in the high-risk abnormal battery cell according to the monitoring result, thermal runaway alarm information is output.

[0030] In the above technical solution, the method can conduct real-time and continuous monitoring of high-risk abnormal battery cells, and output alarm information in a timely manner when serious faults such as thermal runaway are detected, thereby effectively preventing the occurrence of battery pack safety accidents and ensuring the safe operation of electric vehicles.

[0031] In some embodiments, the preset algorithm parameters include a preset neighborhood radius and a preset minimum number of samples;

[0032] The preset algorithm parameters are obtained by dynamically adjusting the original algorithm parameters in combination with historical vehicle data, battery type, vehicle driving conditions and vehicle working environment;

[0033] The original algorithm parameters include a pre-calibrated original neighborhood radius and a pre-calibrated original minimum number of samples.

[0034] In the above technical solution, the method can dynamically adjust the original algorithm parameters to optimize the preset algorithm parameters, thereby improving the accuracy of the density clustering algorithm in battery pack fault diagnosis.

[0035] In a second aspect, the present application provides a battery pack fault diagnosis device, comprising:

[0036] An acquisition unit is used to obtain the original voltage sequence of each cell in the electric vehicle battery pack during driving and charging;

[0037] a preprocessing unit, configured to preprocess the original voltage sequence to obtain a preprocessed voltage sequence;

[0038] A feature calculation unit, configured to calculate a normalized two-dimensional voltage feature vector corresponding to each sliding window based on a preset sliding window and the preprocessed voltage sequence;

[0039] An abnormality identification unit is used to dynamically identify each cell of the electric vehicle battery pack according to preset algorithm parameters, density clustering algorithm and the normalized two-dimensional voltage feature vector to obtain abnormal cluster identification results;

[0040] The early warning unit is used to perform corresponding abnormal battery cell fault early warning operations on the abnormal cluster identification results according to preset multi-level risk thresholds.

[0041] In the above technical solution, the device can detect battery pack faults of electric vehicles online in real time, accurately locate faulty cells, and implement multi-level risk warnings, thereby improving the accuracy and timeliness of fault diagnosis and helping to avoid safety accidents such as thermal runaway.

[0042] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the battery pack fault diagnosis method described in any one of the first aspects.

[0043] In a fourth aspect, the present application provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the battery pack fault diagnosis method described in any one of the first aspects is executed.

[0044] In a fifth aspect, the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it executes the battery pack fault diagnosis method described in any one of the first aspects.

[0045] The beneficial effects of this application are: it can detect battery pack failures during the driving of electric vehicles online and accurately locate the faulty battery cells, while improving the response rate and avoiding dependence on offline data, thereby avoiding the occurrence of thermal runaway and facilitating subsequent fault repair. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 Schematic diagram of a flow chart of a battery pack fault diagnosis method in some embodiments of the present application;

[0048] Figure 2 This is a schematic diagram of density-based voltage fault clustering results in some embodiments of the present application;

[0049] Figure 3 Schematic diagram of a flow chart of a battery pack fault diagnosis method in some embodiments of the present application;

[0050] Figure 4 This is a schematic structural diagram of a battery pack fault diagnosis device in some embodiments of the present application;

[0051] Figure 5 This is a schematic diagram of the structure of an electronic device in some embodiments of the present application. DETAILED DESCRIPTION

[0052] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0054] In the description of the embodiments of the present application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more (including two). Similarly, "multiple groups" refers to two or more (including two groups), and "multiple pieces" refers to two or more (including two pieces) unless otherwise clearly and specifically defined.

[0055] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0056] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0057] With the popularity of electric vehicles, the safety of battery packs has become a core challenge of concern to the industry. The battery pack fault detection solutions currently widely used in the industry mainly include rule-based judgment methods based on fixed thresholds and offline detection methods based on traditional clustering algorithms. The former triggers a fault alarm through a preset voltage / temperature threshold (such as an alarm when the single cell voltage exceeds the average voltage ±50mV). Its core logic relies on the engineer's experience value setting. The technical implementation is simple but the sensitivity is low; the latter uses K-means and other clustering methods to perform offline analysis of historical charge and discharge data, and identifies abnormal fragments by matching the voltage curve morphology, but it relies on complete charge and discharge cycle data and cannot respond to sudden faults during driving in real time. The above methods all focus on the overall status assessment of the battery pack, and have not established a cell-level fault location mechanism. In addition, the feature extraction dimension is single, and usually only basic statistics such as voltage mean and range are used.

[0058] Through benchmarking analysis, the embodiment of the present application proposes an online fault diagnosis method based on outlier clustering to address the defects of the existing technology, such as strong threshold dependence, offline detection lag, insufficient fault location accuracy, and high false alarm rate.

[0059] By implementing this method, fast and accurate fault detection and cell-level fault location can be achieved through multi-dimensional feature extraction and density clustering technology, thereby systematically solving the lag, missed detection rate and false alarm problems of existing solutions.

[0060] like Figure 1 As shown, some embodiments of the present application provide a battery pack fault diagnosis method, which includes:

[0061] S101, obtaining the original voltage sequence of each cell of the electric vehicle battery pack in the driving and charging states;

[0062] S102, preprocessing the original voltage sequence to obtain a preprocessed voltage sequence;

[0063] S103, calculating a normalized two-dimensional voltage feature vector corresponding to each sliding window according to a preset sliding window and a preprocessed voltage sequence;

[0064] S104, dynamically identifying each cell of the electric vehicle battery pack according to preset algorithm parameters, density clustering algorithm and normalized two-dimensional voltage feature vector to obtain abnormal cluster identification results;

[0065] S105 , performing corresponding abnormal cell fault warning operations on the abnormal cluster identification results according to the preset multi-level risk threshold.

[0066] In some embodiments, the method can use sensors to collect data to obtain the voltage curve (i.e., the original voltage sequence) of each cell in the electric vehicle battery pack during driving and charging. The sensor acquisition frequency is 0.1 Hz, i.e., data is collected every 10 seconds.

[0067] In some embodiments, the method uses a density-based clustering (DBSCAN) algorithm to dynamically identify fault fragments, with the input being the normalized feature matrix F of a single window. norm , pre-set the neighborhood radius ε and the minimum number of samples min_samples parameters, the following is the algorithm flow:

[0068] (1) Randomly select an unvisited cell i , i represents the i-th battery cell (all batteries are not visited at the beginning of the algorithm);

[0069] (2) Check Cell i ε neighborhood, if |Nε(Cell i )|≥MinPt, it is marked as a core point and a new cluster is created, otherwise it is temporarily marked as a noise point;

[0070] (3) Cell i To expand density: If Cell i As the core point, recursively i All reachable points within the ε neighborhood are added to the current cluster. In this process, the newly discovered core points continue to expand and repeat this step;

[0071] (4) Repeat the above steps until all points are visited. If any point is still marked as a noise point, it is considered an abnormal point.

[0072] The algorithm output includes clusters of all densely connected points and outliers not included in any cluster. By adjusting ε and min_samples, normal cells can be distinguished from faulty cells.

[0073] In some embodiments, the method sets the frequency P of cells marked as abnormal clusters to be counted in each k sliding windows. i ; Set three-level thresholds t1, t2, and t3 for low / medium / high risk, and optimize the threshold settings based on historical data.

[0074] In some embodiments, a continuous monitoring and thermal runaway warning process is initiated for abnormal high-frequency cells exceeding a threshold value t3 to reduce the impact of occasional interference.

[0075] In some embodiments, fault diagnosis using multiple features and dynamic adjustment of density-based clustering parameters according to the real-time operating conditions of the vehicle can improve the accuracy by 30% compared to methods using a single feature and fixed clustering parameters.

[0076] In these embodiments, the method can detect battery pack faults of electric vehicles online in real time, accurately locate faulty cells, and implement multi-level risk warnings, thereby improving the accuracy and timeliness of fault diagnosis and helping to avoid safety accidents such as thermal runaway.

[0077] In some embodiments, preprocessing the original voltage sequence to obtain a preprocessed voltage sequence includes:

[0078] Reorder the original voltage sequence in descending order of timestamps to obtain a first processed sequence;

[0079] Processing missing data and outliers on the first processing sequence to obtain a second processing sequence;

[0080] Perform logarithmic transformation on the second processing sequence to obtain a preprocessing voltage sequence.

[0081] In some embodiments, due to issues such as sensor acquisition and data uploading, there may be timestamp sorting errors in the original voltage sequence, and the voltage sequence needs to be reordered in descending order of timestamps.

[0082] In some embodiments, there are problems such as missing data (null value) and abnormal values ​​(0 or 255) of some battery cells in the voltage sequence. For the missing and abnormal values ​​of some battery cell voltage data, the voltage value of the battery cell without missing problems at the same time is used instead.

[0083] In some embodiments, for missing or abnormal values ​​of all cell voltage data, normal data at the previous and next moments are used for interpolation and logarithmic transformation to reduce data skewness. The following is the logarithmic transformation formula:

[0084] V′=logV;

[0085] Where V is the original voltage sequence, and V' is the voltage sequence after logarithmic transformation.

[0086] For example, Figure 2 A schematic diagram of density-based voltage fault clustering results is shown. Based on the results shown in this figure, it can be seen that these embodiments can optimize the voltage data processing process, reducing the false alarm rate to 5% to 10% compared to its previous application (the false alarm rate of online detection methods with similar functions was 30% to 40%). Figure 2 Monomer 8, monomer 18, and monomer 81 in the figure correspond to false positive points.

[0087] In these embodiments, the method can effectively handle timestamp sorting errors, data missing, and outlier problems in the original voltage sequence, thereby obtaining a high-quality preprocessed voltage sequence and providing a reliable data basis for subsequent fault diagnosis.

[0088] In some embodiments, according to a preset sliding window and a preprocessed voltage sequence, calculating a normalized two-dimensional voltage feature vector corresponding to each sliding window includes:

[0089] The preprocessed voltage sequence is divided by a preset sliding window to obtain multiple voltage subsequences;

[0090] Calculate the voltage consistency feature and modified Shannon entropy feature corresponding to each sliding window based on multiple voltage subsequences;

[0091] According to the voltage consistency feature and the modified Shannon entropy feature, a two-dimensional feature matrix corresponding to each sliding window is constructed;

[0092] The two-dimensional feature matrix is ​​normalized to obtain a two-dimensional normalized feature matrix corresponding to each sliding window.

[0093] In some embodiments, the method can utilize voltage data collected by the sensor to accurately identify faulty cells by extracting voltage difference features and modified Shannon entropy features, combined with DBSCAN cluster analysis.

[0094] In some embodiments, the voltage consistency feature quantifies the abnormal deviation trend of a single cell by calculating the dynamic offset of the voltage of each cell within a window from the cluster mean.

[0095] In some embodiments, Shannon entropy is widely used in fields such as thermodynamics and information science to determine the degree of system disorder. In battery fault diagnosis, it can be used to determine the degree of voltage fluctuation. In this method, calculating the modified Shannon entropy as a feature can reduce the requirements for online computing.

[0096] Exemplarily, the feature extraction method includes:

[0097] First, a sliding window is used to divide the charging data into segments;

[0098] Next, the voltage mean difference and modified Shannon entropy are calculated for each cell voltage sequence, and the mean of the voltage mean difference within the window is extracted as the voltage consistency feature.

[0099] Finally, the fusion feature of the maximum-minimum normalized voltage consistency feature and the modified Shannon entropy feature is defined as a two-dimensional feature vector.

[0100] It can be seen that this feature extraction method takes into account the voltage value deviation and voltage fluctuation difference of each battery cell when a fault occurs, which at least includes the voltage consistency feature and the modified Shannon entropy feature.

[0101] In some embodiments, the method divides the voltage sequence by a sliding window (window size N), calculates two types of core features, and constructs a two-dimensional feature vector.

[0102] In some embodiments, the mean deviation of the voltage of each cell in the window from the average value of all cells is used to characterize the voltage deviation state of the single cell, and a voltage consistency feature matrix is ​​obtained:

[0103] ΔV=[ΔV1…ΔV n ];

[0104]

[0105] Where i is the number of the battery cell, T is the length of the sliding window, n is the total number of batteries, V i，t is the voltage value of cell i at time t.

[0106] In some embodiments, the modified Shannon entropy can effectively identify abnormal voltage fluctuations by quantifying the differences in randomness of voltage distribution.

[0107] In some embodiments, the method performs the discretization of the voltage matrix X of any window. k×n , where k is the window sequence length, n is the number of cells, and the maximum value x of the matrix is ​​calculated max With the minimum value x min , now define the matrix:

[0108]

[0109] Where a=0, 1, 2...l, l is a custom hyperparameter.

[0110] At this point, calculate the frequency matrix:

[0111]

[0112] Then, the modified Shannon entropy feature matrix H = [H1…H n ],in,

[0113]

[0114] n is the number of battery cells.

[0115] Among them, the modified Shannon entropy is used to quantify the random anomalies of voltage distribution in battery fault diagnosis.

[0116] Finally, construct the two-dimensional feature matrix:

[0117]

[0118] In some embodiments, this method uses minimum-maximum normalization to map features of different dimensions to a unified interval ([0,1]). This solves the problem of feature weight imbalance caused by differences in numerical ranges and enhances data comparability, allowing the model to treat all features fairly and facilitating multi-feature fusion. The specific normalization operations are as follows:

[0119]

[0120] Where f is ΔV or H, f norm is the normalized one-dimensional feature vector.

[0121] It can be seen that the above operation is performed on the row vector of the feature F in the sliding window to obtain the two-dimensional normalized feature matrix f norm .

[0122] In these embodiments, the method can effectively extract key features from the preprocessed voltage sequence, and provide representative feature data for subsequent density clustering analysis and fault diagnosis by constructing and normalizing a two-dimensional feature matrix.

[0123] In some embodiments, performing corresponding abnormal cell fault warning operations on the abnormal cluster identification results according to preset multi-level risk thresholds includes:

[0124] According to the abnormal cluster identification results, the frequency of each battery cell being marked as an abnormal cluster is counted to obtain the abnormal marking frequency corresponding to each battery cell;

[0125] Determine the abnormal cell identification result based on the abnormal marking frequency and the preset multi-level risk threshold; wherein the abnormal cell identification result includes low-risk abnormal cells, medium-risk abnormal cells and high-risk abnormal cells; wherein the preset multi-level risk threshold includes a low-risk threshold, a medium-risk threshold and a high-risk threshold;

[0126] Output abnormal cell prompt information including abnormal cell identification results.

[0127] In these embodiments, the method can achieve multi-level early warning and refined management of battery pack failures.

[0128] In some embodiments, the method further comprises:

[0129] Continuously monitor high-risk abnormal cells and obtain monitoring results;

[0130] When a high-risk abnormal battery cell is detected to have thermal runaway according to the monitoring results, a thermal runaway alarm message is output.

[0131] In these embodiments, the method can perform real-time and continuous monitoring of high-risk abnormal cells, and promptly output alarm information when serious faults such as thermal runaway are detected, thereby effectively preventing the occurrence of battery pack safety accidents and ensuring the safe operation of electric vehicles.

[0132] In some embodiments, the preset algorithm parameters include a preset neighborhood radius and a preset minimum number of samples;

[0133] The preset algorithm parameters are obtained by dynamically adjusting the original algorithm parameters based on historical vehicle data, battery type, vehicle driving conditions, and vehicle working environment;

[0134] The original algorithm parameters include a pre-calibrated original neighborhood radius and a pre-calibrated original minimum number of samples.

[0135] In some embodiments, since the ε and min_samples parameters need to be set in advance, after combining historical data research, the method can dynamically adjust the ε and min_samples parameters according to the battery type and vehicle driving conditions, such as charging, discharging, high temperature, low temperature and other environments, to achieve better fault diagnosis results.

[0136] In these embodiments, the method can dynamically adjust the original algorithm parameters to optimize the preset algorithm parameters, thereby improving the accuracy of the density clustering algorithm in battery pack fault diagnosis.

[0137] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be described clearly and completely below. In some embodiments, Figure 3 As shown, the battery pack fault diagnosis method includes:

[0138] S201, obtaining a voltage sequence of each cell in the battery pack from a sensor;

[0139] S202, data preprocessing;

[0140] S203, dividing the voltage sequence into a number of sliding windows, and calculating a normalized two-dimensional voltage feature vector in each window;

[0141] S204, the obtained normalized two-dimensional voltage feature vector is input into a density clustering algorithm to distinguish normal clusters from abnormal clusters;

[0142] S205 , enabling a multi-level alarm mechanism according to the frequency of each battery cell being recorded as an abnormal cluster within a certain window, and obtaining a final fault diagnosis result.

[0143] In some embodiments, the application scenarios of this method may include: online fault monitoring of electric vehicle battery packs, faulty cell location, thermal runaway warning, and time series data anomaly detection.

[0144] In these embodiments, the method can take into account that different minor faults are difficult to identify, and add logarithmic transformation to amplify the characteristic differences between faulty cells and normal cells, thereby achieving the effect of reducing data skewness.

[0145] In these embodiments, the method can apply features of two different dimensions to the fault diagnosis algorithm, thereby improving the accuracy of the algorithm and reducing the false alarm rate compared to using a single feature.

[0146] In these embodiments, the method can dynamically adjust density clustering-based parameters in combination with the real-time operating conditions of the vehicle, thereby improving the robustness of the algorithm.

[0147] In these embodiments, the method can design an algorithm to ignore occasional fault alarms to avoid false alarms.

[0148] Figure 4 A schematic diagram of the structure of a battery pack fault diagnosis device is shown. It should be understood that the device is Figure 1 The method executed in the embodiment corresponds to the embodiment, and the steps involved in the aforementioned method can be executed. The specific functions and effects of the device can be found in the description above. To avoid repetition, detailed description is appropriately omitted here.

[0149] The battery pack fault diagnosis device includes:

[0150] An acquisition unit 310 is used to acquire the original voltage sequence of each cell of the electric vehicle battery pack when the battery pack is in a driving and charging state;

[0151] The preprocessing unit 320 is used to preprocess the original voltage sequence to obtain a preprocessed voltage sequence;

[0152] A feature calculation unit 330 is configured to calculate a normalized two-dimensional voltage feature vector corresponding to each sliding window based on a preset sliding window and a preprocessed voltage sequence;

[0153] The abnormality identification unit 340 is used to dynamically identify each cell of the electric vehicle battery pack according to preset algorithm parameters, density clustering algorithm and normalized two-dimensional voltage feature vector to obtain abnormal cluster identification results;

[0154] The early warning unit 350 is used to perform corresponding abnormal cell fault early warning operations on the abnormal cluster identification results according to the preset multi-level risk thresholds.

[0155] In some embodiments, the pre-processing unit 320 includes:

[0156] The sorting subunit 321 is configured to re-sort the original voltage sequence in descending order of timestamps to obtain a first processed sequence;

[0157] a processing subunit 322, configured to perform data missing and outlier processing on the first processing sequence to obtain a second processing sequence;

[0158] The transformation subunit 323 is configured to perform logarithmic transformation on the second processing sequence to obtain a preprocessing voltage sequence.

[0159] In some embodiments, the feature calculation unit 330 includes:

[0160] A division subunit 331 is configured to divide the pre-processed voltage sequence by a preset sliding window to obtain a plurality of voltage sub-sequences;

[0161] A calculation subunit 332 is configured to calculate a voltage consistency feature and a modified Shannon entropy feature corresponding to each sliding window based on the multiple voltage subsequences;

[0162] A construction subunit 333 is used to construct a two-dimensional feature matrix corresponding to each sliding window according to the voltage consistency feature and the modified Shannon entropy feature;

[0163] The normalization subunit 334 is used to perform normalization processing on the two-dimensional feature matrix to obtain a two-dimensional normalized feature matrix corresponding to each sliding window.

[0164] In some embodiments, the early warning unit 350 includes:

[0165] A statistics subunit 351 is configured to count the frequency of each battery cell being marked as an abnormal cluster according to the abnormal cluster identification result, and obtain the abnormal marking frequency corresponding to each battery cell;

[0166] A determination subunit 352 is configured to determine an abnormal cell identification result based on the abnormal marking frequency and a preset multi-level risk threshold; wherein the abnormal cell identification result includes a low-risk abnormal cell, a medium-risk abnormal cell, and a high-risk abnormal cell; wherein the preset multi-level risk threshold includes a low-risk threshold, a medium-risk threshold, and a high-risk threshold;

[0167] The output subunit 353 is configured to output abnormal cell prompt information including abnormal cell identification results.

[0168] In some embodiments, the battery pack fault diagnosis device further includes:

[0169] The monitoring unit 360 is used to continuously monitor high-risk abnormal cells and obtain monitoring results;

[0170] The early warning unit 350 is configured to output a thermal runaway alarm message when a high-risk abnormal battery cell is detected to be in thermal runaway according to the monitoring results.

[0171] In some embodiments, the preset algorithm parameters include a preset neighborhood radius and a preset minimum number of samples;

[0172] The preset algorithm parameters are obtained by dynamically adjusting the original algorithm parameters based on historical vehicle data, battery type, vehicle driving conditions, and vehicle working environment;

[0173] The original algorithm parameters include a pre-calibrated original neighborhood radius and a pre-calibrated original minimum number of samples.

[0174] like Figure 5 As shown, the present application provides an electronic device 400, which includes a processor 401 and a memory 402. The processor 401 and the memory 402 are interconnected and communicate with each other through a communication bus 403 and / or other forms of connection mechanisms (not shown). The memory 402 stores a computer program executable by the processor 401. When the computing device is running, the processor 401 executes the computer program to perform the method in any of the aforementioned optional implementations.

[0175] The present application provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the method in any of the aforementioned optional implementations is executed.

[0176] Among them, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0177] The present application provides a computer program product, which includes computer programmability. When the computer program is executed by a processor, the method in any of the aforementioned optional implementations is executed.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A battery pack fault diagnosis method, characterized in that: include: Obtain the original voltage sequence of each cell in the electric vehicle battery pack during driving and charging; Preprocessing the original voltage sequence to obtain a preprocessed voltage sequence; Calculating a normalized two-dimensional voltage feature vector corresponding to each sliding window according to a preset sliding window and the preprocessed voltage sequence; Dynamically identifying each cell of the electric vehicle battery pack according to preset algorithm parameters, density clustering algorithm and the normalized two-dimensional voltage feature vector to obtain abnormal cluster identification results; The abnormal cell fault warning operation is performed correspondingly on the abnormal cluster identification result according to the preset multi-level risk threshold.

2. The battery pack fault diagnosis method according to claim 1, characterized in that: The preprocessing of the original voltage sequence to obtain a preprocessed voltage sequence includes: reordering the original voltage sequence in descending order of timestamps to obtain a first processed sequence; Performing data missing and outlier processing on the first processing sequence to obtain a second processing sequence; Perform logarithmic transformation on the second processing sequence to obtain a preprocessing voltage sequence.

3. The battery pack fault diagnosis method according to claim 1, characterized in that: The step of calculating a normalized two-dimensional voltage feature vector corresponding to each sliding window according to the preset sliding window and the preprocessed voltage sequence includes: Dividing the preprocessed voltage sequence by a preset sliding window to obtain a plurality of voltage subsequences; Calculating a voltage consistency feature and a modified Shannon entropy feature corresponding to each sliding window according to the multiple voltage subsequences; Constructing a two-dimensional feature matrix corresponding to each sliding window according to the voltage consistency feature and the modified Shannon entropy feature; The two-dimensional feature matrix is ​​normalized to obtain a two-dimensional normalized feature matrix corresponding to each sliding window.

4. The battery pack fault diagnosis method according to claim 1, characterized in that: The performing corresponding abnormal cell fault warning operation on the abnormal cluster identification result according to the preset multi-level risk threshold includes: According to the abnormal cluster identification result, the frequency of each battery cell being marked as an abnormal cluster is counted to obtain the abnormal marking frequency corresponding to each battery cell; Determine the abnormal cell identification result according to the abnormal marking frequency and the preset multi-level risk threshold; wherein the abnormal cell identification result includes a low-risk abnormal cell, a medium-risk abnormal cell, and a high-risk abnormal cell; wherein the preset multi-level risk threshold includes a low-risk threshold, a medium-risk threshold, and a high-risk threshold; Output abnormal cell prompt information including the abnormal cell identification result.

5. The battery pack fault diagnosis method according to claim 4, characterized in that: The method further comprises: Continuously monitoring the high-risk abnormal battery cells to obtain monitoring results; When thermal runaway is detected in the high-risk abnormal battery cell according to the monitoring result, thermal runaway alarm information is output.

6. The battery pack fault diagnosis method according to claim 1, characterized in that: The preset algorithm parameters include a preset neighborhood radius and a preset minimum number of samples; The preset algorithm parameters are obtained by dynamically adjusting the original algorithm parameters in combination with historical vehicle data, battery type, vehicle driving conditions and vehicle working environment; The original algorithm parameters include a pre-calibrated original neighborhood radius and a pre-calibrated original minimum number of samples.

7. A battery pack fault diagnosis device, characterized in that: The battery pack fault diagnosis device includes: An acquisition unit is used to obtain the original voltage sequence of each cell in the battery pack of the electric vehicle when it is driving and charging; a preprocessing unit, configured to preprocess the original voltage sequence to obtain a preprocessed voltage sequence; A feature calculation unit, configured to calculate a normalized two-dimensional voltage feature vector corresponding to each sliding window based on a preset sliding window and the preprocessed voltage sequence; An abnormality identification unit is used to dynamically identify each cell of the electric vehicle battery pack according to preset algorithm parameters, density clustering algorithm and the normalized two-dimensional voltage feature vector to obtain abnormal cluster identification results; The early warning unit is used to perform corresponding abnormal battery cell fault early warning operations on the abnormal cluster identification results according to preset multi-level risk thresholds.

8. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the battery pack fault diagnosis method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that The readable storage medium stores a computer program, and when the computer program is executed by a processor, the battery pack fault diagnosis method according to any one of claims 1 to 6 is executed.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the battery pack fault diagnosis method according to any one of claims 1 to 6 is executed.

Images