Data processing method and device, equipment and storage medium

Abstract

The application discloses a data processing method, device and equipment and a storage medium. The method comprises the following steps: obtaining a to-be-detected cell data set based on the running state information of a plurality of cells of a charging battery; performing weighted entropy calculation on the to-be-detected cell data set to obtain a sub-detection index of each cell data; calculating a detection index of the to-be-detected cell data set based on a plurality of sub-detection indexes; performing discrete judgment on the to-be-detected cell data set based on the detection index; and determining an abnormal cell based on a plurality of sub-detection indexes if the to-be-detected cell data set is discrete. The technical scheme of the application can reduce the weight of relatively concentrated cell voltage data in the to-be-detected cell voltage data set and increase the weight of relatively dispersed cell voltage data in the to-be-detected cell voltage data set, so as to facilitate the detection of outlier cell data and finally determine an abnormal cell.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of rechargeable batteries, and particularly relates to a data processing method and device, equipment and a storage medium. BACKGROUND

[0002] With the continuous charging and discharging of the rechargeable batteries on the vehicle, the differences between the multiple battery cells in the rechargeable batteries are slowly reflected, and the pressure rise of the aging battery cells gradually deviates from the group, thereby causing the endurance of the vehicle to sharply decrease. Therefore, it is necessary to detect the outlier battery cells so as to replace them in time.

[0003] However, when the existing entropy value calculation method is used, the probability value of the outlier battery cell obtained by calculation is very small, and the influence on the entropy value is also small. For the part with concentrated battery cell data, although the actual distance is very close, the calculated entropy value will also be larger because of the larger probability value. In actual business, this situation is often not concerned, and therefore, the actual reference value of the current entropy value calculation method is low. SUMMARY

[0004] The present application aims to at least solve one of the technical problems in the related art. To this end, one object of the present application is to provide a data processing method, device, equipment and storage medium.

[0005] To solve the above technical problems, embodiments of the present application provide the following technical solutions:

[0006] A data processing method, comprising:

[0007] Based on the running state information of the multiple battery cells of the rechargeable battery, a battery cell data set to be detected is obtained;

[0008] Weighted entropy calculation is performed on the battery cell data set to be detected to obtain a sub-detection index of each battery cell data;

[0009] Based on the multiple sub-detection indexes, a detection index of the battery cell data set to be detected is calculated and obtained;

[0010] Based on the detection index, discrete judgment is performed on the battery cell data set to be detected;

[0011] If the battery cell data set to be detected is discrete, an abnormal battery cell is determined based on the multiple sub-detection indexes.

[0012] Optionally, the weighted entropy calculation performed on the battery cell data set to be detected to obtain the sub-detection index of each battery cell data comprises:

[0013] Based on the battery cell data set to be detected, a first reference data is calculated and obtained;

[0014] Based on the reference data set, a second reference data is obtained by calculation;

[0015] Based on the first reference data and the second reference data, a weight of each of the battery data is obtained;

[0016] Based on the weight, the weighted entropy of each of the battery data is obtained;

[0017] Based on the weighted entropy, a sub-detection index of each of the battery data is obtained.

[0018] Optionally, the weight of each of the battery data is obtained based on the first reference data and the second reference data, including:

[0019] Based on the second reference data, a third reference data is obtained by calculation;

[0020] Based on the first reference data, the second reference data and the third reference data, the weight of each of the battery data is obtained by calculation.

[0021] Optionally, the weight of each of the battery data is obtained based on the first reference data, the second reference data and the third reference data, including:

[0022] Based on the second reference data and the second reference data, a first term is obtained by calculation;

[0023] Based on the to-be-detected battery data set, the first reference data and the second reference data, a second term is obtained by calculation;

[0024] Based on the first term and the second term, the weight of each of the battery data is obtained by calculation.

[0025] Optionally, the weight is obtained by calculation based on the following calculation formula:

[0026] w(x i )=(Rs / Rs')*exp((x i -Xs) / Rs);

[0027] Wherein, x i is the i-th battery data, and i is a positive integer; Xs is the first reference data; Rs is the second reference data; Rs' is the third reference data.

[0028] Optionally, the sub-detection index is obtained by calculation based on the following formula:

[0029] C i =-w(x i )p(x i )log(p(x i ));

[0030] wherein, p(x i ) is x i The probability of the occurrence of the to-be-detected battery data set.

[0031] Optionally, if the to-be-detected battery data set is discrete, the determination of the abnormal battery based on the plurality of sub-detection indexes comprises:

[0032] A preset sub-detection index threshold is set.

[0033] If the to-be-detected battery data set is discrete, each sub-detection index is compared with the sub-detection index threshold.

[0034] If the sub-detection index is greater than the sub-detection index threshold, the battery corresponding to the sub-detection index is determined as the abnormal battery.

[0035] Embodiments of the present application also provide a data processing device, comprising:

[0036] An acquisition module is configured to acquire a to-be-detected battery data set based on the running state information of a plurality of batteries of a charging battery.

[0037] A first calculation module is configured to perform weighted entropy calculation on the to-be-detected battery data set to obtain a sub-detection index of each battery data.

[0038] A second calculation module is configured to calculate the to-be-detected battery data set based on the plurality of sub-detection indexes.

[0039] A judgment module is configured to judge the detection index of the data set, and judge the to-be-detected battery data set based on the detection index.

[0040] A determination module is configured to, if the to-be-detected battery data set is discrete, determine an abnormal battery based on the plurality of sub-detection indexes.

[0041] Embodiments of the present application also provide an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method as described above when executing the computer program.

[0042] Embodiments of the present application also provide a computer readable storage medium, comprising a stored computer program, wherein the computer readable storage medium controls the device where the computer readable storage medium is located to execute the method as described above when the computer program runs.

[0043] Embodiments of the present application have the following technical effects:

[0044] The above technical scheme of the present application 1) performs weighted calculation on the entropy value of each battery cell data, amplifies the weight of each battery cell data, so as to facilitate the judgment of the abnormal battery cell.

[0045] 2) Based on the weight and entropy value of each battery cell data The weighted entropy of each battery cell data is calculated, and the weighted entropy of each battery cell data is summed and calculated, that is, the detection index and its size are obtained, which can realize more accurate judgment of the dispersion and dispersion degree of the voltage to be detected battery cell data set of the embodiment of the present application, wherein the greater the value of the detection index, the more dispersed the to-be-detected battery cell data set.

[0046] 3) The weight of the relatively concentrated battery cell voltage value in the to-be-detected battery cell voltage data set can be reduced, and the weight of the relatively dispersed battery cell voltage data in the to-be-detected battery cell voltage data set can be increased. In the abnormal detection of the battery cell, more attention is paid to the outlier battery cell information, therefore, the weight of the part of the battery cell voltage data with concentrated values is reduced in the embodiment of the present application, which facilitates the detection of the outlier battery cell data and finally determines the abnormal battery cell.

[0047] Additional aspects and advantages of the present application will be described in part in the description that follows, and will become apparent from the description, or will be learned by practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 is a flow diagram of a data processing method provided by an embodiment of the present application;

[0049] Figure 2 is a structural schematic diagram of a data processing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0050] The embodiments of the present application will be described in detail below, and examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0051] An embodiment of the present application provides a data processing system, comprising:

[0052] A plurality of sensors, a processor and a memory; wherein the plurality of sensors respectively interact with the processor and the memory based on a network.

[0053] The plurality of sensors are connected with the charging battery, and are used for monitoring the running state of the plurality of battery cells of the charging battery in real time, and sending the monitored battery cell data set to the processor based on a network for processing.

[0054] Specifically, the plurality of sensors are respectively used for monitoring cell voltages, temperatures and other operating parameters of the cells of the charging battery; then, the sensors respectively send the obtained cell voltages or cell temperatures to the processor to form a cell voltage data set or a cell temperature data set;

[0055] Further, when detecting the inconsistency of the plurality of cells based on the to-be-detected cell data, the processor processes the cell data in one of the to-be-detected cell data sets, for example, selects the cell voltage data set or the cell temperature data set.

[0056] Further, for example, the to-be-detected cell voltage data set is selected to detect the outliers of the plurality of cells, the processor obtains the weight and entropy value of each cell voltage data based on the obtained to-be-detected cell voltage data set, then obtains a detection index of the entire to-be-detected cell voltage data set based on the weight of each cell voltage data, and further determines whether there is a discrete value in the to-be-detected cell voltage data set based on the detection index, and can determine the discrete degree of the entire to-be-detected cell voltage data set according to the size of the detection index.

[0057] Further, when it is determined that the to-be-detected cell voltage data set is discrete based on the detection index, the information is fed back to the processor, and the processor searches for the discrete value in the to-be-detected cell voltage data set;

[0058] Specifically, the sub-detection index of each cell voltage data is calculated and obtained, the processor outputs a plurality of sub-detection indexes, and then the discrete condition and discrete degree of each cell data can be determined based on the plurality of sub-detection indexes output by the processor, and further the abnormal cell is determined.

[0059] Further, the data in the system running process can be stored in the storage to facilitate subsequent calculation and calling of the data.

[0060] As shown in Figure 1 , the embodiment of the application provides a data processing method applied to the above system, comprising:

[0061] Step S1: obtaining a to-be-detected cell data set based on the operating state information of the plurality of cells of the charging battery;

[0062] Specifically, first, the embodiment of the application obtains a group of original cell voltage data sets, for example:

[0063] {x1:m1, x2:m2, x3:m3……x i :m i ……x k :m k};

[0064] Wherein, since there are generally repeated values in the cell voltage data in each original cell voltage data set; therefore, the number m of the i th (i is a positive integer) non-repeated cell voltage data in the original cell voltage data set i statistical calculation, and then based on the number m i and n (the number of all cell voltage data in the original cell voltage data set, i≤n) to obtain the probability p(x i ) of the i th non-repeated cell voltage data i in the voltage to be detected cell data set.

[0065] Wherein, p(x i )=m i / n.

[0066] Further, the embodiment of the present application performs deduplication processing on the original cell voltage data set, that is, deletes the repeated cell voltage data, and only retains one for the same voltage cell data, thereby obtaining the to-be-detected cell voltage data set of the embodiment of the present application:

[0067] {x1, x2, x3……x i ……x k}.

[0068] Wherein, x i represents the value of the i th cell voltage data in the to-be-detected cell voltage data set, the number of the to-be-detected cell voltage data set is k, and k is a positive integer, then i≤k≤n.

[0069] Step S2: performing weighted entropy calculation on the to-be-detected cell data set to obtain a sub-detection index of each cell data;

[0070] Specifically, the weighted entropy calculation is performed on the to-be-detected cell data set to obtain a sub-detection index of each cell data, including:

[0071] Based on the to-be-detected cell data set, a first reference data is calculated and obtained;

[0072] Based on the reference data set, a second reference data is calculated and obtained;

[0073] Based on the first reference data and the second reference data, a weight of each cell data is obtained;

[0074] Based on the weight, the weighted entropy of each cell data is obtained;

[0075] Based on the weighted entropy, a sub-detection index of each cell data is obtained.

[0076] Wherein, for the obtained plurality of sub-detection indicators, storage can be performed to facilitate direct calling of subsequent calculation.

[0077] Wherein, the first reference data can be the median or average value Xs of the to-be-detected battery voltage data set; the second reference data can be the range Rs of the to-be-detected battery voltage data set.

[0078] In actual application scenarios, each sub-detection indicator is represented by the weighted entropy of each battery voltage data, that is, the weighted entropy of each battery voltage data is its sub-detection indicator. Specifically, taking the average value Xs of the to-be-detected battery voltage data set as an example, the average value Xs of the to-be-detected battery voltage data set is calculated based on the values of the battery voltage data in the to-be-detected battery voltage data set and the number of battery voltage data.

[0079] Further, the obtaining of the weight of each battery data based on the first reference data and the second reference data comprises:

[0080] Based on the second reference data, a third reference data is calculated and obtained;

[0081] Based on the first reference data, the second reference data and the third reference data, the weight of each battery data is calculated and obtained.

[0082] Wherein, the third reference data can be calculated and obtained based on the following method:

[0083] The battery voltage data greater than x i in the to-be-detected battery voltage data set is deleted to obtain a first sub-to-be-detected battery voltage data set, and then a first sub-range, that is, the third reference data Rs', is obtained based on the first sub-to-be-detected battery voltage data set; or

[0084] The battery voltage data less than x i in the to-be-detected battery voltage data set is deleted to obtain a second sub-to-be-detected battery voltage data set, and then a second sub-range, that is, the third reference data Rs', is obtained based on the second sub-to-be-detected battery voltage data set.

[0085] Further, the calculation and obtaining of the weight of each battery data based on the first reference data, the second reference data and the third reference data comprises:

[0086] Based on the second reference data and the second reference data, a first term is calculated and obtained;

[0087] Based on the to-be-detected battery data set, the first reference data and the second reference data, a second term is calculated and obtained;

[0088] Based on the first term and the second term, the weight of each battery data is calculated and obtained.

[0089] wherein the weight is calculated based on the following calculation formula:

[0090] w(x i )=(Rs / Rs')*((x i -Xs) / Rs);

[0091] wherein x i is the i-th battery data, and i is a positive integer; Xs is the first reference data; Rs is the second reference data; and Rs' is the third reference data.

[0092] The embodiments of the present application can reduce the weight of the concentrated battery voltage data in the battery voltage data to be detected, and increase the weight of the dispersed battery voltage data in the battery voltage data to be detected, and the abnormal battery detection is more concerned about the outlying battery information, thus, the embodiments of the present application reduce the weight of the concentrated battery voltage data, facilitate the detection of the outlying battery, and finally determine the abnormal battery.

[0093] Further, the weight is calculated based on the following calculation formula:

[0094] w(x i )=(Rs / Rs')*exp((x i -Xs) / Rs);

[0095] wherein x i is the i-th battery data, and i is a positive integer; Xs is the first reference data; Rs is the second reference data; and Rs' is the third reference data.

[0096] The embodiments of the present application, since there are some battery data close to Xs in the battery data to be detected, x i -Xs=0 or (x i -Xs) is a very small value, and for this, the embodiments of the present application add an exponential calculation to the calculation result of (x-Xs) / Rs part;

[0097] Specifically, for x i -Xs=0, after adding the exponential operation, the weight corresponding to the battery data is not 0, and the subsequent calculation can be performed, avoiding the adjustment of the battery data and simplifying the calculation.

[0098] And for the case that (x i -Xs) is a very small value, after adding the exponential operation, the value is amplified, and the battery data is amplified for subsequent processing.

[0099] Further, since the probability of the outlier part is small, the square of the extreme part in the weight can be calculated, that is, w(x i )=(Rs / Rs') 2 *exp((x i -Xs) / Rs), which further realizes the amplification of the detection index to facilitate subsequent calculation.

[0100] Further, the sub-detection index is calculated based on the following formula:

[0101] C i =-w(x i )p(x i )log(p(x i ));

[0102] Wherein, p(x i ) is the probability of x i in the to-be-detected battery data set.

[0103] Embodiments of the present application, the entropy value of each battery is weighted and calculated, the weight of each battery data is amplified, so as to judge the discrete battery and determine the discrete degree, wherein the greater the value of the sub-detection index, the greater the discrete degree.

[0104] Step S4: based on the detection index, the discrete judgment of the to-be-detected battery data set is performed;

[0105] Specifically, a preset detection index threshold is set.

[0106] The detection index is compared with the detection index threshold.

[0107] If the detection index is greater than the detection index threshold, it is judged that the to-be-detected battery voltage data set is discrete.

[0108] Optionally, the detection index is calculated based on the following formula:

[0109]

[0110] Wherein, k is the number of battery data in the to-be-detected battery data set.

[0111] In actual application scenarios, through statistical analysis of the weighted entropy of multiple groups of battery voltage data sets during detection, a preset detection index threshold T (such as using 3σ method, etc.) is obtained, when the weighted entropy C of the to-be-detected battery data set is greater than T1 (the greater the entropy value, the more information, and the more likely to appear outlier or discrete situation, so there is no need to consider the case of C

[0112] The embodiment of the present application is based on the weight and entropy value of each battery data The weighted entropy of each battery data is calculated, and the weighted entropy of each battery data is summed to obtain a detection index and its size, which can more accurately determine the dispersion and dispersion degree of the voltage battery data set to be detected in the embodiment of the present application. The greater the value of the detection index, the more dispersed the battery voltage data set to be detected.

[0113] Step S5: If the battery data set to be detected is dispersed, determine the abnormal battery based on the plurality of sub-detection indexes.

[0114] Specifically, if the battery data set to be detected is dispersed, the abnormal battery is determined based on the plurality of sub-detection indexes, comprising:

[0115] A preset sub-detection index threshold is set;

[0116] If the battery data set to be detected is dispersed, each sub-detection index is compared with the sub-detection index threshold;

[0117] If the sub-detection index is greater than the sub-detection index threshold, the battery corresponding to the sub-detection index is determined as the abnormal battery.

[0118] Specifically, the sub-detection index threshold T2 is obtained using the 3σ method;

[0119] Or T2 is obtained based on T1 / n, n is the length of the original battery voltage data set, and the number of battery cells of the same battery pack is the same, that is, the number of battery voltage data in each original battery voltage data set is the same;

[0120] In actual application scenarios, each sub-detection index is compared with T2, and if C i >T2 T2, the x i corresponding to the sub-detection index is a dispersed value, and based on x i , the original battery voltage data set is searched to find all x i , and then according to these x i , all corresponding battery cells are found, and these battery cells are the abnormal battery cells.

[0121] In addition, the dispersion of each battery voltage data can also be determined based on the weight corresponding to each battery voltage data. Specifically, the w i of each battery voltage data x i in the battery voltage data set to be detected can be counted (such as using the 3σ method), and a preset weight threshold T3 is obtained. Similarly, if w i >T3, it is judged that a certain battery voltage data x i is a dispersed value, and based on xi Find all x in the original cell voltage data set i Then find all cells corresponding to these x i These cells are abnormal cells.

[0122] In the embodiment of the application, whether each cell is out of the group is determined based on the obtained sub-detection index or weight, and if there is an out-of-group cell.

[0123] The above-mentioned embodiment of the application can be realized based on the following implementation manners:

[0124] 1. Taking the following original cell voltage data set as an example:

[0125] [3.71, 3.711, 3.712, 3.711,..., 3.835], and the number of occurrences of each value is {3.71: 10, 3.711: 25, 3.712: 28, 3.715: 29, 3.717: 3, 3.835: 1};

[0126] Based on the original cell voltage data set, the following to-be-detected cell voltage data set can be obtained:

[0127] {3.71, 3.711, 3.712, 3.715, 3.717, 3.835};

[0128] 1) Based on the existing manner, the entropy value obtained by calculating the above-mentioned to-be-detected cell voltage data set is 1.4628, and the weighted entropy value obtained by calculating the embodiment of the application is 6.3895. It can be seen that both the entropy value and the weighted entropy value are greater than 1, so the to-be-detected cell voltage data set has discrete values.

[0129] Then obtain the sub-detection index of each cell voltage data, compare each sub-detection index with the sub-detection index threshold, and determine x i with the sub-detection index greater than T3 as a discrete value, and based on x i Find all x in the original cell voltage data set i Then find all cells corresponding to these x i These cells are abnormal cells.

[0130] 2) If the value of 3.835 is changed to 3.735, the entropy value calculated based on the existing manner is unchanged, and the weighted entropy value obtained by calculating the embodiment of the application is 2.7487 < 6.3895. It can be seen that the detection index, i.e. the weighted entropy value, is amplified based on the embodiment of the application, which facilitates the determination of the discrete degree of the to-be-detected cell voltage data set.

[0131] 3) If more attention is paid to the numerical outliers of the partial cell voltage data, the part of (Rs / Rs') in the above formula can be modified to the square of (Rs / Rs') (considering that the probability of outliers is small, so the difference part of the weight is squared, and the weight value of the outlier part is increased), and the weighted entropy values in the above 1), 2) are 110.7805, 6.7436 respectively, that is, the detection index will be further amplified when the outliers.

[0132] 2, taking a set of original cell voltage data with relatively concentrated numerical values as an example:

[0133] The number of times each cell voltage data value appears can be obtained as follows:

[0134] {3.71:10, 3.711:25, 3.712:28, 3.715:29, 3.717:3, 3.735:1};

[0135] Based on the original cell voltage data set, the following to-be-detected cell voltage data set can be obtained:

[0136] {3.71, 3.711, 3.712, 3.715, 3.717, 3.735};

[0137] The entropy value calculated based on the prior art is 1.4628, and the weighted entropy value calculated based on the embodiment of the present application is 2.7487.

[0138] Another set of original cell voltage data sets with the same range but relatively dispersed numerical values of cell voltage data as the first set is taken as an example; the number of times each cell voltage data value appears can be obtained as follows:

[0139] {3.71:16, 3.715:16, 3.72:16, 3.725:16, 3.73:16, 3.735:16};

[0140] Based on the original cell voltage data set, the following to-be-detected cell voltage data set can be obtained:

[0141] {3.71, 3.715, 3.72, 3.725, 3.73, 3.735};

[0142] The entropy value calculated based on the prior art is 1.7918, and the weighted entropy value calculated based on the embodiment of the present application is 4.2247, which shows that the embodiment of the present application is more sensitive to the dispersion distribution than the entropy value method of the prior art.

[0143] As shown in Figure 2 , the embodiment of the present application also provides a data processing device 200, which comprises:

[0144] The acquisition module 201 is configured to acquire a to-be-detected battery cell data set based on operating state information of a plurality of battery cells of a charging battery.

[0145] The first calculation module 202 is configured to perform weighted entropy calculation on the to-be-detected battery cell data set to obtain a sub-detection index of each battery cell data.

[0146] The second calculation module 203 is configured to calculate the to-be-detected battery cell based on a plurality of sub-detection indexes.

[0147] The judgment module 204 is configured to perform discrete judgment on the to-be-detected battery cell data set based on a detection index of the data set.

[0148] The determination module 205 is configured to determine an abnormal battery cell based on a plurality of sub-detection indexes if the to-be-detected battery cell data set is discrete.

[0149] Optionally, the weighted entropy calculation on the to-be-detected battery cell data set to obtain a sub-detection index of each battery cell data comprises:

[0150] The first reference data is calculated based on the to-be-detected battery cell data set.

[0151] The second reference data is calculated based on the reference data set.

[0152] The weight of each battery cell data is obtained based on the first reference data and the second reference data.

[0153] The weighted entropy of each battery cell data is obtained based on the weight.

[0154] The sub-detection index of each battery cell data is obtained based on the weighted entropy.

[0155] Optionally, the weight of each battery cell data is obtained based on the first reference data and the second reference data, and the weight comprises:

[0156] The third reference data is calculated based on the second reference data.

[0157] The weight of each battery cell data is calculated based on the first reference data, the second reference data, and the third reference data.

[0158] Optionally, the weight of each battery cell data is calculated based on the first reference data, the second reference data, and the third reference data, and the weight comprises:

[0159] The first term is calculated based on the second reference data and the second reference data.

[0160] The second term is calculated based on the to-be-detected battery data set, the first reference data, and the second reference data.

[0161] The weight of each of the battery data is calculated based on the first term and the second term.

[0162] Optionally, the weight is calculated based on the following calculation formula:

[0163] w(x i ) = (Rs / Rs') * exp((x i -Xs) / Rs);

[0164] wherein x i is the i-th battery data, and i is a positive integer; Xs is the first reference data; Rs is the second reference data; and Rs' is the third reference data.

[0165] Optionally, the sub-detection index is calculated based on the following formula:

[0166] C i = -w(x i )p(x i )log(p(x i ));

[0167] wherein p(x i ) is the probability of x i in the to-be-detected battery data set.

[0168] Optionally, if the to-be-detected battery data set is discrete, the abnormal battery is determined based on a plurality of the sub-detection indexes, including:

[0169] a sub-detection index threshold is preset;

[0170] if the to-be-detected battery data set is discrete, each of the sub-detection indexes is compared with the sub-detection index threshold;

[0171] if the sub-detection index is greater than the sub-detection index threshold, the battery corresponding to the sub-detection index is determined as the abnormal battery.

[0172] Embodiments of the present application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the method as described above when executing the computer program.

[0173] Embodiments of the present application also provide a computer-readable storage medium, including a stored computer program, wherein the computer-readable storage medium controls a device where the computer-readable storage medium is located to implement the method as described above when the computer program runs.

[0174] In addition, other configurations and effects of the device of the embodiments of the present application are known to those skilled in the art, and thus, detailed descriptions thereof are omitted herein.

[0175] It should be noted that the logic and / or steps represented in the flowcharts and / or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor- containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or a combination of both. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can specifically include the following, which are non-exhaustive list: electrical connection (electrical device having one or more wires), portable computer diskette (magnetic device), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fiber device, and portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable medium upon which the program is printed, since the program can be electronically obtained, for example, from the paper or other medium, by optically scanning the paper or other medium, then by electronically translating the optically scanned data into the program, and then by storing the program in a computer memory.

[0176] It should be understood that various parts of the present application can be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, a plurality of steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, any of the following technologies known in the art or a combination thereof can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits (ASICs) having appropriate combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0177] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the description of the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in one or more embodiments or examples.

[0178] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0179] In addition, the terms "first", "second" are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0180] In the present application, unless otherwise specifically defined and limited, the terms "mounting", "connection", "connection", "fixing" and the like should be broadly understood, for example, it can be fixed connection, or detachable connection, or integral; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through intermediate medium, it can be the internal communication of two elements or the interaction relationship of two elements, unless otherwise specifically limited. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0181] In the present application, unless otherwise explicitly specified and limited, a first feature is "on" or "under" a second feature can mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature is "over", "above" and "on top of" the second feature can mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is horizontally higher than the second feature. The first feature is "under", "below" and "underneath" the second feature can mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is horizontally lower than the second feature.

[0182] Although the embodiments of the present application have been shown and described above, it is to be understood that the above-described embodiments are exemplary only, and are not to be construed as limiting the present application, and that changes, modifications, substitutions and variations can be made thereto by those skilled in the art without departing from the scope of the present application.

Claims

1. A data processing method, characterized in that, include: Based on the operating status information of multiple cells of a rechargeable battery, a data set of cells to be tested is obtained, and the data set of cells to be tested is deduplicated. The data set of cells to be tested is a dataset composed of cell data, which may be a cell voltage dataset or a cell temperature dataset. The process involves calculating a weighted entropy on the dataset of cells to be tested to obtain a sub-detection index for each cell data point. This calculation includes: calculating a first reference data point based on the dataset, where the first reference data point is the median or average of the voltage dataset of the cells to be tested; calculating a second reference data point based on the dataset, where the second reference data point is the range of the voltage dataset of the cells to be tested; obtaining a weight for each cell data point based on the first and second reference data points; obtaining the weighted entropy for each cell data point based on the weights; and obtaining a sub-detection index for each cell data point based on the weighted entropy. The step of obtaining the weight for each cell data point based on the first and second reference data points includes: calculating the weighted entropy based on the median or average of the voltage dataset of the cells to be tested; calculating a second reference data point based on the median or average of the voltage dataset of the cells to be tested; calculating a second reference data point based on the median or average of the voltage dataset of the cells to be tested; obtaining a weight for each cell data point based on the first and second reference data points; obtaining the weight for each cell data point based on the first and second reference data points; and calculating the weight for each cell data point based on the median or average of the voltage dataset of the cells to be tested. The second reference data is used to calculate the third reference data, which is either the first sub-range calculated from the sub-cell voltage dataset obtained after deleting cell data larger than a certain cell data, or the second sub-range calculated from the sub-cell voltage dataset obtained after deleting cell data smaller than a certain cell data; based on the first reference data, the second reference data, and the third reference data, the weight of each cell data is calculated; the calculation of the weight of each cell data based on the first reference data, the second reference data, and the third reference data includes: calculating a first term based on the second reference data and the third reference data; calculating a second term based on the cell dataset to be tested, the first reference data, and the second reference data; and calculating the weight of each cell data based on the first term and the second term; the weight is calculated based on the following formula: W( = (Rs / Rs') * exp(( -Xs) / Rs); where, Let Xs be the data for the i-th battery cell, where i is a positive integer; Xs is the first reference data; Rs is the second reference data; and Rs' is the third reference data. Based on multiple sub-detection indicators, the detection indicators of the battery cell dataset to be detected are calculated; and the battery cell dataset to be detected is discretely judged based on the detection indicators. If the dataset of cells to be detected is discrete, then abnormal cells are identified based on multiple sub-detection indicators.

2. The method according to claim 1, characterized in that, The sub-detection index is calculated based on the following formula: ； Where p ( )for The probability of the detected battery cell appearing in the dataset.

3. The method according to claim 1, characterized in that, If the dataset of cells to be detected is discrete, then based on multiple sub-detection indicators, abnormal cells are determined, including: Preset sub-detection index thresholds; If the dataset of cells to be detected is discrete, then each of the sub-detection indicators is compared with the threshold of the sub-detection indicator; If the sub-detection index is greater than the sub-detection index threshold, then the cell corresponding to the sub-detection index is identified as the abnormal cell.

4. A data processing apparatus, characterized in that, include: The acquisition module is used to acquire a dataset of cells to be tested based on the operating status information of multiple cells of a rechargeable battery, and to perform deduplication processing on the dataset of cells to be tested. The dataset of cells to be tested is a dataset composed of cell data, which is either a cell voltage dataset or a cell temperature dataset. A first calculation module is used to perform weighted entropy calculation on the battery cell dataset to be tested, and obtain a sub-detection index for each battery cell data. The step of performing weighted entropy calculation on the battery cell dataset to be tested and obtaining the sub-detection index for each battery cell data includes: calculating a first reference data based on the battery cell dataset to be tested, wherein the first reference data is the median or average of the battery cell voltage dataset to be tested; calculating a second reference data based on the battery cell dataset to be tested, wherein the second reference data is the range of the battery cell voltage dataset to be tested; obtaining a weight for each battery cell data based on the first reference data and the second reference data; obtaining the weighted entropy for each battery cell data based on the weight; and obtaining the sub-detection index for each battery cell data based on the weighted entropy. The step of obtaining the weight for each battery cell data based on the first reference data and the second reference data includes... Based on the second reference data, a third reference data is calculated, wherein the third reference data is either the first sub-range obtained by deleting a sub-cell voltage dataset after deleting a cell data larger than a certain cell data, or the second sub-range obtained by deleting a sub-cell voltage dataset after deleting a cell data smaller than a certain cell data; based on the first reference data, the second reference data, and the third reference data, the weight of each cell data is calculated; the calculation of the weight of each cell data based on the first reference data, the second reference data, and the third reference data includes: calculating a first term based on the second reference data and the third reference data; calculating a second term based on the cell dataset to be tested, the first reference data, and the second reference data; and calculating the weight of each cell data based on the first term and the second term; the weight is calculated based on the following formula: W( = (Rs / Rs') * exp(( -Xs) / Rs); where, Let Xs be the data for the i-th battery cell, where i is a positive integer; Xs is the first reference data; Rs is the second reference data; and Rs' is the third reference data. The second calculation module is used to calculate the value of the battery cell under test based on multiple sub-detection indicators. The judgment module is used for the detection indicators of the dataset; it performs discrete judgments on the dataset of battery cells to be tested based on the detection indicators. The determination module is used to determine abnormal cells based on multiple sub-detection indicators if the dataset of cells to be detected is discrete.

5. An electronic device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the method as described in any one of claims 1 to 3.

Images