Battery fault early warning method and device, computer equipment, readable storage medium and program product

By denoising the battery impedance data and classifying the category, the problem of timely warning of traditional technologies is solved, effective analysis and fault warning of complex battery data is realized, and the accuracy and real-timeness of battery health status monitoring is improved.

CN119024186AActive Publication Date: 2024-11-26SHENZHEN POWER SUPPLY BUREAU
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411365042.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-29
Publication Date
2024-11-26
Estimated Expiration
2044-09-29

AI Technical Summary

Technical Problem

Traditional electrochemical impedance spectrum analysis is difficult to provide timely battery failure warning when facing high complexity battery data.

Method used

By denoising the impedance data of multiple batteries, local density and dynamically adjust density thresholds are calculated, data points are divided into groups, and distances between groups are calculated to determine battery failure.

Benefits of technology

It realizes effective processing of complex battery data, promptly detects battery failures and issues early warnings, improving the accuracy and real-timeness of battery health status monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119024186A_ABST
    Figure CN119024186A_ABST
Patent Text Reader

Abstract

The invention relates to a battery fault early warning method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: respectively carrying out de-noising processing on impedance data of a plurality of batteries to obtain de-noised impedance data; taking each piece of denoised impedance data as a data point, and calculating the local density corresponding to each data point; dynamically adjusting a density threshold value according to the local density corresponding to each data point to obtain a density threshold value corresponding to each data point; dividing all the data points into a plurality of class groups according to the density threshold values corresponding to the different data points; and calculating the distance between every two class groups in the plurality of class groups, and determining that a battery fault exists in the plurality of batteries under the condition that the distance between every two class groups is greater than a preset distance. By adopting the method, the fault of the battery can be found in time, and early warning is given out, so that the next treatment is carried out.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] With the widespread application of batteries in new energy, electric vehicles, smart grids and other fields, monitoring their health status has become increasingly important. Electrochemical impedance spectroscopy, as a widely used non-destructive detection method, can analyze the internal state of the battery through electrochemical responses at different frequencies.

[0003] Traditional electrochemical impedance spectroscopy is mainly based on equivalent circuit models to extract characteristic parameters. Cluster analysis, as an unsupervised learning method, can improve the efficiency and accuracy of electrochemical impedance spectroscopy analysis by automatically discovering potential patterns in data, identifying battery anomalies or inconsistencies.

[0004] However, when faced with highly complex data, traditional technical means cannot handle it well and cannot provide timely battery failure warnings. Summary of the invention

[0005] Based on this, it is necessary to provide a battery fault warning method, device, computer equipment, computer-readable storage medium and computer program product that can process highly complex battery data in order to address the above technical problems.

[0006] In a first aspect, the present application provides a battery failure early warning method, comprising:

[0007] De-noising the impedance data of multiple batteries respectively to obtain de-noised impedance data;

[0008] Taking each denoised impedance data as a data point, calculating the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points;

[0009] According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point;

[0010] According to the density thresholds corresponding to the different data points, all data points are divided into multiple groups;

[0011] The distance between every two groups in the plurality of groups is calculated, and when the distance between two groups is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

[0012] In one embodiment, the denoising of the impedance data of the plurality of batteries is performed respectively to obtain the denoised impedance data, including:

[0013] Testing a plurality of batteries to obtain impedance data of the plurality of batteries;

[0014] Filtering is performed on the impedance data of the plurality of batteries to obtain denoised impedance data.

[0015] In one embodiment, taking each denoised impedance data as a data point and calculating the local density corresponding to each data point includes:

[0016] For each data point, calculate the distance between the data point and the remaining data points;

[0017] The local density corresponding to the data point is calculated according to the distance and a preset smoothing parameter.

[0018] In one embodiment, dynamically adjusting the density threshold according to the local density corresponding to each data point to obtain the density threshold corresponding to each data point includes:

[0019] Determine the adjustment factor corresponding to each data point according to the local density corresponding to each data point;

[0020] The adjustment factor is divided by the local density to obtain a density threshold corresponding to each data point.

[0021] In one embodiment, the dividing all data points into a plurality of groups according to the density thresholds corresponding to the different data points comprises:

[0022] Calculate the distance between every two data points;

[0023] If the distance between the two data points is greater than a preset value, then the distance between the two data points is compared with the smallest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the smallest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group;

[0024] If the distance between the two data points is less than a preset value, the distance between the two data points is compared with the largest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the largest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group.

[0025] In one embodiment, calculating the distance between every two groups in the plurality of groups, and determining that a battery failure exists in the plurality of batteries when the distance between the two groups is greater than a preset distance, includes:

[0026] Calculating the center of each cluster in the plurality of clusters, and calculating the distance between the centers of every two clusters in the plurality of clusters;

[0027] In the case where the distance between the centers of two clusters is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

[0028] In a second aspect, the present application also provides a battery failure warning device, comprising:

[0029] An acquisition module, used for performing denoising processing on the impedance data of multiple batteries respectively to obtain denoised impedance data;

[0030] A calculation module, used to take each denoised impedance data as a data point and calculate the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points;

[0031] The calculation module is further used to dynamically adjust the density threshold according to the local density corresponding to each data point to obtain the density threshold corresponding to each data point;

[0032] A division module, used for dividing all data points into multiple groups according to density thresholds corresponding to the different data points;

[0033] The determination module is used to calculate the distance between every two groups in the plurality of groups, and determine that a battery failure exists in the plurality of batteries when the distance between two groups is greater than a preset distance.

[0034] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0035] De-noising the impedance data of multiple batteries respectively to obtain de-noised impedance data;

[0036] Taking each denoised impedance data as a data point, calculating the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points;

[0037] According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point;

[0038] According to the density thresholds corresponding to the different data points, all data points are divided into multiple groups;

[0039] The distance between every two groups in the plurality of groups is calculated, and when the distance between two groups is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0041] De-noising the impedance data of multiple batteries respectively to obtain de-noised impedance data;

[0042] Taking each denoised impedance data as a data point, calculating the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points;

[0043] According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point;

[0044] According to the density thresholds corresponding to the different data points, all data points are divided into multiple groups;

[0045] The distance between every two groups in the plurality of groups is calculated, and when the distance between two groups is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

[0046] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0047] De-noising the impedance data of multiple batteries respectively to obtain de-noised impedance data;

[0048] Taking each denoised impedance data as a data point, calculating the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points;

[0049] According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point;

[0050] According to the density thresholds corresponding to the different data points, all data points are divided into multiple groups;

[0051] The distance between every two groups in the plurality of groups is calculated, and when the distance between two groups is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

[0052] The battery fault warning method, device, computer equipment, computer-readable storage medium and computer program product described above first perform denoising on the impedance data of multiple batteries to obtain denoised impedance data. The interference of noise in the data processing process is eliminated, and the validity of the data is ensured. Each denoised impedance data is used as a data point, and the local density corresponding to each data point is calculated; the local density is used to measure the distance between the data point and the remaining data points. The distance between each data point and the remaining data points is quantified and converted into the corresponding local density, making subsequent data processing more convenient. According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point. According to the density thresholds corresponding to different data points, the data points are divided into multiple groups. The distance between each two groups in the multiple groups is calculated, and when the distance between the two groups is greater than the preset distance, it is determined that there is a battery fault in the multiple batteries. In this way, by analyzing the impedance data of multiple batteries, it is possible to timely detect battery failures, issue warnings, and then proceed to the next step of processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0054] FIG1 is a schematic diagram of a flow chart of a battery failure early warning method in one embodiment;

[0055] FIG2 is a schematic flow chart of a battery failure early warning method in another embodiment;

[0056] FIG3 is a structural block diagram of a battery failure early warning device in one embodiment;

[0057] FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] In one embodiment, as shown in FIG1 , a battery failure warning method is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps 102 to 110:

[0060] Step 102 , denoising the impedance data of the multiple batteries respectively to obtain denoised impedance data.

[0061] The impedance data of the battery is a complex number, which consists of a real part and an imaginary part. The denoising process may be a filtering process.

[0062] Specifically, the terminal may perform filtering processing on the impedance data of the multiple batteries respectively to obtain the impedance data of the multiple batteries after denoising.

[0063] Step 104, taking each denoised impedance data as a data point, and calculating the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points.

[0064] Among them, the distance is the Euclidean distance, which is the true distance between two data points.

[0065] In some embodiments, the terminal uses each denoised impedance data as a data point, calculates the distance between each data point and the remaining other data points, and calculates the local density corresponding to each data point based on the distance between each data point and the remaining other data points and a preset smoothing parameter, wherein the smoothing parameter is used to control the smoothing degree of the data point.

[0066] Step 106: dynamically adjust the density threshold according to the local density corresponding to each data point to obtain the density threshold corresponding to each data point.

[0067] In some embodiments, the terminal determines the adjustment factor corresponding to each data point according to the local density corresponding to each data point, and divides the adjustment factor corresponding to each data point by the local density of each data point to obtain the density threshold corresponding to each data point.

[0068] Step 108, dividing all data points into multiple groups according to density thresholds corresponding to different data points;

[0069] In some embodiments, the terminal calculates the distance between every two data points, and further determines the size between the distance between the two data points and the density threshold based on the size relationship between the distance between the two data points and the preset value, thereby determining whether the two data points belong to the same group.

[0070] Step 110 , calculating the distance between every two groups in the plurality of groups, and determining that a battery failure exists in the plurality of batteries when the distance between two groups is greater than a preset distance.

[0071] In some embodiments, the terminal calculates the center of each cluster, and then calculates the distance between every two cluster centers in the multiple clusters. When the distance between the centers of two clusters is greater than a preset distance, it is determined that there is a battery failure in the battery.

[0072] In the above-mentioned battery fault warning method, the impedance data of multiple batteries are denoised respectively to obtain the denoised impedance data. The interference of noise in the data processing process is eliminated, and the validity of the data is guaranteed. Each denoised impedance data is used as a data point, and the local density corresponding to each data point is calculated; the local density is used to measure the distance between the data point and the remaining data points. The distance between each data point and the remaining data points is quantified and converted into the corresponding local density, making subsequent data processing more convenient. According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point. According to the density thresholds corresponding to different data points, the data points are divided into multiple groups. The distance between each two groups in the multiple groups is calculated, and when the distance between the two groups is greater than the preset distance, it is determined that there is a battery fault in the multiple batteries. In this way, by analyzing the impedance data of multiple batteries, it is possible to timely detect battery failures, issue warnings, and then proceed to the next step of processing.

[0073] In an exemplary embodiment, the impedance data of multiple batteries are denoised respectively to obtain the denoised impedance data, including: testing multiple batteries to obtain the impedance data of multiple batteries; filtering the impedance data of multiple batteries to obtain the denoised impedance data.

[0074] In actual implementation, the terminal will perform EIS (electrochemical impedance spectroscopy) tests on the battery under different working conditions to obtain the battery impedance data of the battery within a preset frequency range. The obtained battery impedance data is then filtered to obtain the battery impedance data after eliminating the influence of noise.

[0075] The noise may be any noise, which is not limited in the present embodiment. The filtering method may be Gaussian filtering or other filtering methods that can remove noise, which is not limited in the present embodiment.

[0076] In the above embodiment, the terminal uses a filtering method to eliminate noise interference for the battery impedance data, thereby ensuring the validity of the battery impedance data.

[0077] In some exemplary embodiments, each denoised impedance data is taken as a data point, and the local density corresponding to each data point is calculated, including: for each data point, calculating the distance between the data point and the remaining data points; and calculating the local density corresponding to the data point based on the distance and a preset smoothing parameter.

[0078] In some embodiments, the terminal uses each denoised impedance data as a data point and calculates the Euclidean distance between each data point and the remaining data points. The specific calculation formula is shown in (1). Each data point represents the impedance data of a battery.

[0079]

[0080] in, is the real part of the battery impedance data represented by data point i, is the imaginary part of the battery impedance data represented by data point i, is the real part of the battery impedance data represented by data point j, is the imaginary part of the battery impedance data represented by data point j.

[0081] According to the Euclidean distance of each data point and the preset smoothing parameter, the local density corresponding to each data point is calculated. The specific calculation formula is shown in (2).

[0082]

[0083] in, is the Euclidean distance between data point i and data point j, is the preset smoothing parameter.

[0084] In the above embodiment, the terminal controls the smoothing degree of the data by customizing the smoothing parameters, thereby improving the readability and interpretability of the data and enhancing the accuracy of the final result.

[0085] In some exemplary embodiments, the density threshold is dynamically adjusted according to the local density corresponding to each data point to obtain the density threshold corresponding to each data point, including: determining the adjustment factor corresponding to each data point according to the local density corresponding to each data point; dividing the adjustment factor by the local density to obtain the density threshold corresponding to each data point.

[0086] In some embodiments, the terminal determines the corresponding adjustment factor according to the local density corresponding to each data point. The adjustment factor corresponding to each data point is divided by the local density corresponding to the data point to obtain the density threshold corresponding to the data point. The specific calculation formula is shown in (3).

[0087]

[0088] in, is the adjustment factor, is the local density.

[0089] In the above embodiment, the terminal achieves the purpose of dynamically setting the density threshold by dynamically setting the adjustment factor. Using a smaller density threshold in an area with high local density can capture subtle characteristic changes; using a larger density threshold in an area with low local density can avoid misidentifying noise points as abnormal points.

[0090] In some exemplary embodiments, all data points are divided into multiple groups according to density thresholds corresponding to different data points, including: calculating the distance between every two data points; if the distance between the two data points is greater than a preset value, comparing the distance between the two data points with the smallest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the smallest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group; if the distance between the two data points is less than a preset value, comparing the distance between the two data points with the largest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the largest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group.

[0091] In actual implementation, the terminal will calculate the distance between every two data points. When the distance between the two data points is greater than a preset value, the terminal will compare the distance between the two data points with the smallest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the smallest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group.

[0092] When the distance between two data points is less than the preset value, the distance between the two data points is compared with the maximum density threshold value among the density threshold values ​​corresponding to the two data points; if the distance between the two data points is greater than the maximum density threshold value, the two data points belong to the same group; otherwise, the two data points do not belong to the same group. The preset value is determined by the specific battery impedance data in the actual test process.

[0093] In the above embodiment, the terminal divides all data points into multiple groups, so that when abnormal situations occur in the subsequent monitoring process, the abnormalities are more obvious.

[0094] In some exemplary embodiments, the distance between every two groups in a plurality of groups is calculated, and when the distance between two groups is greater than a preset distance, it is determined that a battery fault exists in the plurality of batteries, including: calculating the center of each group in the plurality of groups, and calculating the distance between the centers of every two groups in the plurality of groups; and when the distance between the centers of two groups is greater than a preset distance, it is determined that a battery fault exists in the plurality of batteries.

[0095] In some embodiments, for multiple clusters, the terminal calculates the center of each cluster. The specific calculation formula is shown in (4).

[0096]

[0097] in, is the number of data points in cluster k, is the impedance data of the ith data point.

[0098] Furthermore, the distance between the centers of each two of the multiple groups is calculated, and when the distance between the centers of the two groups is greater than a preset distance, it is determined that a battery failure exists in the multiple batteries. The specific calculation formula is shown in (5).

[0099]

[0100] in, For the preset distance, is the distance between the center of cluster k and the center of cluster l, is the center of cluster k, is the center of cluster l.

[0101] In the above embodiment, the terminal quantifies the states of multiple batteries, and when inconsistency occurs, it can promptly discover that a battery failure occurs among the multiple batteries, thereby further issuing an early warning.

[0102] To explain the battery fault warning method in the present application in detail, an embodiment is used for explanation below. The specific flow chart is shown in FIG2 . By way of example, the present application is explained with a specific lithium battery fault warning method.

[0103] First, the terminal will perform electrochemical impedance spectroscopy tests on the battery at different states of charge to obtain battery impedance data in the frequency range of 10mHz to 100kHz. Then, the obtained battery impedance data is denoised using wavelet transform to obtain battery impedance data after noise is eliminated.

[0104] The terminal will take each denoised impedance data as a data point and calculate the Euclidean distance between each data point and the remaining data points. The specific calculation formula is shown in (1). Among them, each data point represents the impedance data of a battery. According to the Euclidean distance of each data point and the preset smoothing parameter, the local density corresponding to each data point is calculated. The specific calculation formula is shown in (2). The terminal will determine the corresponding adjustment factor according to the different local densities corresponding to each data point. The adjustment factor corresponding to each data point is divided by the local density corresponding to the data point to obtain the density threshold corresponding to the data point. The specific calculation formula is shown in (3).

[0105] The terminal will calculate the distance between every two data points. When the distance between two data points is greater than the preset value, the terminal will compare the distance between the two data points with the smallest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the smallest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group.

[0106] When the distance between two data points is less than the preset value, the distance between the two data points is compared with the maximum density threshold value among the density threshold values ​​corresponding to the two data points; if the distance between the two data points is greater than the maximum density threshold value, the two data points belong to the same group; otherwise, the two data points do not belong to the same group. The preset value is determined by the specific battery impedance data in the actual test process.

[0107] Specifically, take a set of impedance data as an example.

[0108] Data Point 1: ;

[0109] Data Point 2: ;

[0110] Data Point 3: ;

[0111] The above formula can be used to calculate the local density of each data point. .

[0112] According to the local density of the above data points and the corresponding adjustment factor, the density threshold of the data points is calculated. Set to 0.05.

[0113] Data Point 1: ;

[0114] Data Point 2: ;

[0115] Data Point 3: ;

[0116] Because among the local densities of the three data points, the local density of data point 2 is relatively high and belongs to the high-density area, the smallest density threshold is used for comparison when comparing density thresholds; the local density of data point 3 is relatively low and belongs to the low-density area, the largest density threshold is used for comparison when comparing density thresholds.

[0117] The Euclidean distance between data point 1 and data point 2 is , compared with the smallest density threshold between the two, that is, the density threshold of data point 2, which is less than , so data point 1 and data point 2 belong to the same cluster.

[0118] The Euclidean distance between data point 1 and data point 3 is , compared with the largest density threshold between the two, that is, the density threshold of data point 3, which is greater than , so data point 1 and data point 3 do not belong to the same cluster.

[0119] According to the above rules, all data points are divided into multiple clusters. For multiple clusters, the terminal calculates the center of each cluster. The specific calculation formula is shown in (4).

[0120] Furthermore, the distance between the centers of each two of the multiple groups is calculated, and when the distance between the centers of the two groups is greater than a preset distance, it is determined that a battery failure exists in the multiple batteries. The specific calculation formula is shown in (5).

[0121] The present application can monitor the impedance data of multiple batteries after electrochemical impedance spectroscopy processing, calculate the local density of each data point, dynamically adjust the density threshold, and automatically identify outliers in the data points, thereby providing timely fault warnings and improving the accuracy and real-time performance of battery health status monitoring.

[0122] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0123] Based on the same inventive concept, the embodiment of the present application also provides a battery fault warning device for implementing the battery fault warning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more battery fault warning device embodiments provided below can refer to the limitations of the battery fault warning method above, and will not be repeated here.

[0124] In an exemplary embodiment, as shown in FIG3 , a battery failure early warning device is provided, including: an acquisition module 301, a calculation module 302, a division module 303 and a determination module 304, wherein:

[0125] The acquisition module is used to perform denoising on the impedance data of multiple batteries respectively to obtain denoised impedance data.

[0126] The calculation module is used to take each denoised impedance data as a data point and calculate the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points.

[0127] The calculation module is also used to dynamically adjust the density threshold according to the local density corresponding to each data point to obtain the density threshold corresponding to each data point.

[0128] The division module is used to divide all data points into multiple groups according to the density thresholds corresponding to the different data points.

[0129] The determination module is used to calculate the distance between every two groups in the plurality of groups, and determine that a battery failure exists in the plurality of batteries when the distance between two groups is greater than a preset distance.

[0130] In some embodiments, the acquisition module is further used to test multiple batteries to obtain impedance data of the multiple batteries; and to filter the impedance data of the multiple batteries to obtain denoised impedance data.

[0131] In some embodiments, the above-mentioned calculation module is also used to calculate the distance between each data point and the remaining data points; and calculate the local density corresponding to the data point based on the distance and a preset smoothing parameter.

[0132] In some embodiments, the calculation module is further used to determine the adjustment factor corresponding to each data point according to the local density corresponding to each data point; and divide the adjustment factor by the local density to obtain the density threshold corresponding to each data point.

[0133] In some embodiments, the above-mentioned division module is also used to calculate the distance between every two data points; if the distance between the two data points is greater than a preset value, the distance between the two data points is compared with the smallest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the smallest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group; if the distance between the two data points is less than a preset value, the distance between the two data points is compared with the largest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the largest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group.

[0134] In some embodiments, the above-mentioned determination module is also used to calculate the center of each group in the multiple groups, and calculate the distance between the centers of every two groups in the multiple groups; when the distance between the centers of two groups is greater than a preset distance, it is determined that there is a battery failure in the multiple batteries.

[0135] Each module in the above battery failure warning device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0136] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG4. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a battery failure warning method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0137] Those skilled in the art will understand that the structure shown in FIG. 4 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0138] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0139] De-noising the impedance data of multiple batteries respectively to obtain de-noised impedance data;

[0140] Taking each denoised impedance data as a data point, calculating the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points;

[0141] According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point;

[0142] According to the density thresholds corresponding to the different data points, all data points are divided into multiple groups;

[0143] The distance between every two groups in the plurality of groups is calculated, and when the distance between two groups is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

[0144] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0145] De-noising the impedance data of multiple batteries respectively to obtain de-noised impedance data;

[0146] Taking each denoised impedance data as a data point, calculating the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points;

[0147] According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point;

[0148] According to the density thresholds corresponding to the different data points, all data points are divided into multiple groups;

[0149] The distance between every two groups in the plurality of groups is calculated, and when the distance between two groups is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

[0150] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0151] De-noising the impedance data of multiple batteries respectively to obtain de-noised impedance data;

[0152] Taking each denoised impedance data as a data point, calculating the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points;

[0153] According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point;

[0154] According to the density thresholds corresponding to the different data points, all data points are divided into multiple groups;

[0155] The distance between every two groups in the plurality of groups is calculated, and when the distance between two groups is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

[0156] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0157] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0158] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0159] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A battery failure early warning method, characterized in that: The method comprises: De-noising the impedance data of multiple batteries respectively to obtain de-noised impedance data; Taking each denoised impedance data as a data point, calculating the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points; According to the local density corresponding to each data point, the density threshold is dynamically adjusted to obtain the density threshold corresponding to each data point; According to the density thresholds corresponding to the different data points, all data points are divided into multiple groups; The distance between every two groups in the plurality of groups is calculated, and when the distance between two groups is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

2. The method according to claim 1, characterized in that The step of performing denoising processing on the impedance data of the plurality of batteries respectively to obtain denoised impedance data includes: Testing a plurality of batteries to obtain impedance data of the plurality of batteries; Filtering is performed on the impedance data of the plurality of batteries to obtain denoised impedance data.

3. The method according to claim 1, characterized in that The method of taking each denoised impedance data as a data point and calculating the local density corresponding to each data point includes: For each data point, calculate the distance between the data point and the remaining data points; The local density corresponding to the data point is calculated according to the distance and a preset smoothing parameter.

4. The method according to claim 1, characterized in that: The method of dynamically adjusting the density threshold according to the local density corresponding to each data point to obtain the density threshold corresponding to each data point includes: Determine the adjustment factor corresponding to each data point according to the local density corresponding to each data point; The adjustment factor is divided by the local density to obtain a density threshold corresponding to each data point.

5. The method according to claim 1, characterized in that The method of dividing all data points into multiple groups according to the density thresholds corresponding to the different data points includes: Calculate the distance between every two data points; If the distance between the two data points is greater than a preset value, then the distance between the two data points is compared with the smallest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the smallest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group; If the distance between the two data points is less than a preset value, the distance between the two data points is compared with the largest density threshold among the density thresholds corresponding to the two data points; if the distance between the two data points is greater than the largest density threshold, the two data points belong to the same group; otherwise, the two data points do not belong to the same group.

6. The method according to claim 1, characterized in that The calculating the distance between every two groups in the plurality of groups, and determining that a battery failure exists in the plurality of batteries when the distance between the two groups is greater than a preset distance, includes: Calculating the center of each cluster in the plurality of clusters, and calculating the distance between the centers of every two clusters in the plurality of clusters; In the case where the distance between the centers of two clusters is greater than a preset distance, it is determined that a battery failure exists in the plurality of batteries.

7. A battery failure warning device, characterized in that: The device comprises: An acquisition module, used for performing denoising processing on the impedance data of multiple batteries respectively to obtain denoised impedance data; A calculation module, used to take each denoised impedance data as a data point and calculate the local density corresponding to each data point; the local density is used to measure the distance between the data point and the remaining data points; The calculation module is further used to dynamically adjust the density threshold according to the local density corresponding to each data point to obtain the density threshold corresponding to each data point; A division module, used for dividing all data points into multiple groups according to density thresholds corresponding to the different data points; The determination module is used to calculate the distance between every two groups in the plurality of groups, and determine that a battery failure exists in the plurality of batteries when the distance between two groups is greater than a preset distance.

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

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

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

Citation Information

Patent Citations

  • Battery cell consistency evaluation method based on charging fragment data and unsupervised algorithm

    CN115372828A

  • Method and device for eliminating abnormal data of fuel cell based on LOF

    CN118412500A

  • Extended clustering for improved positioning

    US20100062790A1