Battery pack internal short circuit diagnosis method and device, related system and storage medium
By establishing and detecting target models for the target detection parameter sequences of each battery cell in the battery pack, the problem of insufficient accuracy of short circuit diagnosis in the battery pack in the prior art is solved, and higher diagnostic accuracy is achieved.
Patent Information
- Application Number
- CN202410520572.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-26
- Publication Date
- 2025-02-18
AI Technical Summary
Existing short-circuit diagnosis methods in the battery pack are prone to diagnosis errors due to increased internal resistance and temperature changes, and the accuracy is insufficient.
By obtaining the target detection parameter sequence of each cell in the battery pack, a target model is established, and these models are significantly detected to determine whether there is an internal short circuit in each cell in the battery pack.
Improve the diagnostic accuracy of short circuits in the battery pack and reduce misdiagnosis caused by other factors.
Smart Images
Figure CN119471414A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of battery diagnosis technology, and in particular to a method, device, related system and storage medium for diagnosing short circuits in a battery pack. Background Art
[0002] With the widespread use of batteries, battery safety issues have become a focus of attention. Battery failure is mainly manifested as short circuit, and battery fault diagnosis is needed to avoid safety problems caused by short circuit. Existing solutions are mainly based on online diagnosis of battery management systems (BMS).
[0003] For battery packs, diagnosis is usually performed by setting corresponding thresholds based on the voltage and temperature parameters of the battery pack, such as the average voltage, the minimum voltage of the single cells in the battery pack, and the maximum temperature. However, in addition to being affected by short circuits, the voltage of single cells is also affected by other factors. Under the influence of other factors, the internal resistance increases, which can also cause the minimum voltage of the single cells in the battery pack to decrease and the maximum temperature to increase, leading to diagnostic errors. Summary of the invention
[0004] The present invention provides a method, device, related system and storage medium for diagnosing short circuit in a battery pack, which are used to improve the accuracy of diagnosing short circuit in a battery pack.
[0005] A first aspect of an embodiment of the present invention provides a method for diagnosing short circuits in a battery pack, comprising: obtaining a target detection parameter sequence for each battery cell in the battery pack, wherein the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; establishing a target model for each battery cell based on the target detection parameter sequence for each battery cell; performing significance detection on the target model for each battery cell to obtain significance detection results for each target model; and determining whether each battery cell in the battery pack is short-circuited based on the significance detection results for each target model.
[0006] A second aspect of an embodiment of the present invention provides a battery pack internal short circuit diagnosis device, comprising: an acquisition module, used to acquire a target detection parameter sequence of each battery cell in the battery pack, wherein the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; an establishment module, used to establish a target model of each battery cell based on the target detection parameter sequence of each battery cell; a detection module, used to perform significance detection on the target model of each battery cell to obtain significance detection results of each target model; and a determination module, used to determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
[0007] A third aspect of an embodiment of the present invention provides a battery management system, comprising: a normal operating condition operation module and an internal short circuit monitoring module, wherein the normal operating condition operation module and the internal short circuit monitoring module are electrically connected to a battery pack respectively; the normal operating condition operation module is used to control the battery pack to operate in a normal operating condition; the internal short circuit monitoring module is used to control the battery pack to operate in an internal short circuit detection condition; the internal short circuit monitoring module comprises an acquisition unit, an establishment unit, a detection unit and a determination unit, wherein the acquisition unit is used to acquire a target detection parameter sequence of each battery cell in the battery pack, and the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; the establishment unit is used to establish a target model of each battery cell based on the target detection parameter sequence of each battery cell; the detection unit is used to perform significance detection on the target model of each battery cell to obtain a significance detection result of each target model; the determination unit is used to determine whether there is an internal short circuit in each battery cell in the battery pack based on the significance detection result of each target model.
[0008] A fourth aspect of an embodiment of the present invention provides an energy storage system, comprising: a plurality of battery packs, a data acquisition device and a battery management system, wherein the data acquisition device and the battery management system are electrically connected to the plurality of battery packs, respectively, and the data acquisition device and the battery management system are electrically connected; the data acquisition device is used to collect operating data of each battery pack; the battery management system comprises a normal operating condition operation module and an internal short circuit monitoring module, wherein the normal operating condition operation module and the internal short circuit monitoring module are electrically connected to each battery pack, respectively; the normal operating condition operation module is used to control each battery pack to operate in a normal operating condition; the internal short circuit monitoring module is used to control each battery pack to operate in a normal operating condition. Internal short circuit detection working condition; the internal short circuit monitoring module includes an acquisition unit, an establishment unit, a detection unit and a determination unit, wherein the acquisition unit is used to acquire a target detection parameter sequence of each battery cell in the battery pack, and the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; the establishment unit is used to establish a target model of each battery cell based on the target detection parameter sequence of each battery cell; the detection unit is used to perform significance detection on the target model of each battery cell to obtain a significance detection result of each target model; the determination unit is used to determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection result of each target model.
[0009] A fifth aspect of the present invention provides a computer-readable storage medium, in which instructions are stored, which, when executed on a computer, enable the computer to execute the above-mentioned method for diagnosing short circuits in a battery pack.
[0010] In the technical solution provided by the present invention, a target detection parameter sequence of each battery cell in a battery pack is obtained, and the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; a target model of each battery cell is established based on the target detection parameter sequence of each battery cell; a significance test is performed on the target model of each battery cell to obtain a significance test result of each target model; and based on the significance test result of each target model, it is determined whether each battery cell in the battery pack has an internal short circuit. In an embodiment of the present invention, a target model corresponding to each battery cell is established through a target detection parameter sequence corresponding to each battery cell, and by checking the significance of the target model corresponding to each battery cell, it is determined whether each battery cell has an internal short circuit, thereby improving the accuracy of diagnosing short circuits in battery packs. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 A schematic diagram of an embodiment of a method for diagnosing a short circuit in a battery pack according to an embodiment of the present invention;
[0012] Figure 2 Schematic diagram of the change of the remaining power and the number of cycles under different coulombic efficiencies in an embodiment of the present invention;
[0013] Figure 3 A schematic diagram of another embodiment of a method for diagnosing a short circuit in a battery pack according to an embodiment of the present invention;
[0014] Figure 4 A schematic diagram of a SOC-OCV curve in an embodiment of the present invention;
[0015] Figure 5 A schematic diagram of another embodiment of a method for diagnosing a short circuit in a battery pack according to an embodiment of the present invention;
[0016] Figure 6 A schematic diagram of a short circuit diagnosis device in a battery pack according to an embodiment of the present invention;
[0017] Figure 7 A schematic diagram of a battery management system according to an embodiment of the present invention;
[0018] Figure 8 Schematic diagram of an energy storage system in an embodiment of the present invention. DETAILED DESCRIPTION
[0019] The present invention provides a method, device, related system and storage medium for diagnosing short circuit in a battery pack, which are used to improve the accuracy of diagnosing short circuit in a battery pack.
[0020] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein, for example, can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0021] The short circuit diagnosis method in a battery pack provided by an embodiment of the present invention can be applied to a battery pack composed of multiple battery cells. The battery pack can be a lithium battery or a sodium battery with graphite as the negative electrode, or other types of batteries. This application is described using a lithium battery as an example.
[0022] See also Figure 1 , a flow chart of a short circuit diagnosis method in a battery pack provided by an embodiment of the present invention specifically includes:
[0023] 101. Obtain a target detection parameter sequence for each battery cell in a battery pack, where the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell.
[0024] It is understandable that when detecting the operating data of the battery pack, in general, the target detection parameter is the remaining power or the charge. In practical applications, the remaining power and charge of each battery cell can also be detected at the same time, and a required target detection parameter can be selected during calculation. Preferably, the present application embodiment is described by taking obtaining a target detection parameter as an example.
[0025] It should be noted that, in this embodiment, the target detection parameter may be the remaining power, which is related to the open circuit voltage of each battery cell in the battery pack. Therefore, it is necessary to measure the voltage value of each battery cell to establish a functional relationship model between the remaining power and the number of charge and discharge cycles.
[0026] 102. Establish a target model for each battery cell based on the target detection parameter sequence of each battery cell.
[0027] It is understandable that different target detection parameters correspond to different target linear models. When the target detection parameter is the remaining power, the target model can be a functional relationship model between the remaining power and the number of charge and discharge cycles; when the target detection parameter is the charge amount, the target model is a functional relationship model between the charge amount and the number of charge and discharge cycles; if the charging current is constant, the target detection parameter can be the charging time, and the target model can also be expressed as a functional relationship model between the charging time and the number of charge and discharge cycles. Among them, the number of charge and discharge cycles refers to a complete charge and discharge cycle, and a complete charge and discharge cycle includes a charging process and a discharge process.
[0028] When a cell has an internal short circuit and there is a self-discharge current, the self-discharge current is relatively small at the beginning. According to the formula η CEX is the Coulomb efficiency of the cell, Q out is the discharge capacity, Q in is the charge amount, t discharge is the discharge time, t charge is the charging time, I is the charging and discharging current, and I self It is the self-discharge current, also called leakage current.
[0029] Please refer to Figure 2 , Figure 2 is the change of coulombic efficiency and remaining capacity with the number of cycles (i.e., the number of charge and discharge cycles), where CE_0.98, CE_0.985, CE_0.99, CE_0.995 and CE_1 in the figure represent the coulombic efficiency η CE The five values are 0.98, 0.985, 0.99, 0.995 and 1. At the beginning of the internal short circuit, after 30 charge and discharge cycles, the change pattern of the remaining power of the normal battery cell. It can be seen that the remaining power corresponding to the same coulomb efficiency is approximately a straight line. The more the coulomb efficiency decreases, the greater the slope of the curve; if there is no internal short circuit and the coulomb efficiency is close to 1 (assuming that the coulomb efficiency of the normal battery cell is relatively 1), the remaining power of the normal battery cell is close to 0. Therefore, a target model of the remaining power of each battery cell and the number of charge and discharge cycles can be established, and different target models correspond to different coulomb efficiencies of each battery cell.
[0030] 103. Perform significance detection on the target model of each battery cell to obtain significance detection results of each target model.
[0031] The embodiment of the present application analyzes each target model through a significance test to test whether the significance of each target model is established; before performing the significance test, it is also necessary to determine the statistics required for the significance test. Depending on the method of the significance test, the determined statistics are also different, and the specific details are not limited here.
[0032] 104. Determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
[0033] Based on the significance test results of each target model, determine whether each battery cell in the battery pack has an internal short circuit. When the significance of a target model is established and the coulomb efficiency is less than 1, it means that the corresponding battery cell has an internal short circuit; if the insignificance of the target model is established, or the coulomb efficiency is equal to 1, it means that the corresponding battery cell does not have an internal short circuit.
[0034] In an embodiment of the present invention, a target model corresponding to each battery cell is established through a target detection parameter sequence corresponding to each battery cell, and the significance of the target model corresponding to each battery cell is tested to determine whether each battery cell has an internal short circuit, thereby improving the diagnostic accuracy of the short circuit in the battery pack.
[0035] See also Figure 3 , another flow chart of the short circuit diagnosis method in the battery pack provided by the embodiment of the present invention specifically includes:
[0036] 301. Obtain operating data of a battery pack, where the operating data includes a plurality of voltage data of each static period, and the static period is used to indicate the duration between two adjacent charge and discharge cycles of the battery pack.
[0037] It is understandable that when detecting the operating data of the battery pack, in general, the target detection parameter is the remaining power or the charge. In practical applications, the remaining power and charge of each battery cell can also be detected at the same time, and a required target detection parameter can be selected during calculation. Preferably, the present application embodiment is described by taking obtaining a target detection parameter as an example.
[0038] In this embodiment, the remaining power is taken as an example for explanation. The remaining power of each battery cell corresponding to each rest period is arranged according to the order of the rest periods to obtain a remaining power sequence, wherein the order of the rest periods is determined by the order of the charge and discharge cycle time. The rest period refers to the length of time between two adjacent charge and discharge cycles of the battery cell, that is, the period after the last discharge to the cut-off voltage and before the start of the next charge. The battery cell in the rest period is neither charged nor discharged, and the voltage measured in the rest period is the required open circuit voltage of the battery cell.
[0039] 302. Determine the average voltage of each battery cell in the battery pack in each static period based on multiple voltage data in each static period, and obtain an average voltage sequence of each battery cell, where the average voltage sequence is used to indicate the average voltage of a single battery cell in each static period.
[0040] Because the battery pack will be charged and discharged repeatedly (i.e., multiple charge and discharge cycles), there will be multiple rest periods. Among the multiple rest periods corresponding to each battery cell, the rest period that meets the preset duration requirement is selected. The duration of each rest period is not exactly the same. In order to ensure that the voltage data of the battery cell is stable and improve the accuracy of the test results, the rest period in the embodiment of the present application needs to be greater than the preset duration, for example, 30 minutes, or other durations, for example, 20 minutes, which is not specifically limited here.
[0041] It should be noted that the number of rest periods can be set in advance. For example, if the number of rest periods is 30, then the voltage data of each battery cell in the 30 rest periods needs to be extracted. The number of rest periods can also be other values, such as 20, 35, etc., which is not limited here.
[0042] In a feasible implementation manner, based on a plurality of voltage data in each rest period, an average voltage of each battery cell in the battery pack in each rest period is determined to obtain an average voltage sequence of each battery cell, including:
[0043] Based on multiple voltage data in each static period, determine the last K voltage data of each battery cell in each static period, where K is a positive integer; average the last K voltage data corresponding to each battery cell to obtain the average voltage of each battery cell in each static period; and generate an average voltage sequence of each battery cell based on the average voltage of each battery cell in each static period.
[0044] It is understandable that, because the open circuit voltage of the battery cell will still fluctuate after the discharge is completed, that is, the voltage data of each battery cell will change during the static period. In order to more accurately calculate the voltage data in a static period, this embodiment averages the last K voltage data of each static period to obtain the average voltage of each battery cell in each static period. in To represent the voltage of each battery cell during the rest period, when the number of rest periods n is 30, the average voltage sequence of each battery cell can be expressed as V i =[v i1 ,v i2 ,…,v i30 ],i=1,2,…,m; where m represents the number of cells in the battery pack.
[0045] 303. Determine the remaining power sequence of each battery cell based on the average voltage sequence of each battery cell and the preset SOC-OCV curve. The remaining power sequence is used to indicate the charge state of a single battery cell in each static period. The remaining power sequence is used to indicate the value of the remaining power corresponding to a single battery cell in multiple static periods.
[0046] It should be noted that different battery types have different corresponding SOC-OCV curves. For example, the SOC-OCV curve of lithium iron phosphate batteries has a plateau period, while the SOC-OCV curve of ternary lithium batteries does not have a plateau period. When lithium iron phosphate batteries are used in energy storage systems, the plateau period of lithium iron phosphate batteries does not affect the process of obtaining the SOC value in this application.
[0047] like Figure 4 As shown, assuming that all cells are normal at the beginning, the battery is discharged from a full state to a cut-off voltage of 2.6V, then the SOC values at this time are all near 0, and the SOC-OCV curve area that needs to be queried is not in the plateau period, and the SOC value of each cell can be obtained by checking the SOC-OCV curve; when a cell begins to have an internal short circuit, in a short period of time, the battery pack is discharged from a full state to the cut-off voltage (the cell with an internal short circuit reaches the cut-off voltage first), then the normal cell is not fully discharged (that is, the SOC is not 0), but the SOC of each normal cell is also relatively small, not greater than 20%, so the SOC-OCV curve area that needs to be queried will not reach the plateau period, and the SOC-OCV curve can still be checked to obtain the SOC value of the normal cell, and then the remaining power sequence SOC of each cell is obtained. i , SOC i =[soc i1 ,soc i2 ,…,soc in ],i=1,2,…,m; where m represents the number of cells in the battery pack and n represents the number of rest periods.
[0048] It is understandable that, for the same battery pack, the battery cells in the battery pack generally use the same type of battery cells, so the same SOC-OCV curve can be referenced.
[0049] 304. Establish a target model for each battery cell based on the remaining power sequence of each battery cell.
[0050] Specifically, a first correspondence between a plurality of remaining power of each battery cell and the number of charge and discharge cycles is obtained; a target model of each battery cell is determined based on the remaining power sequence of each battery cell and the first correspondence, and the target model is used to indicate the changing relationship between the remaining power corresponding to a single battery cell and the number of charge and discharge cycles. The first correspondence is Where x represents the number of cycles, η CEX represents the Coulomb efficiency of cell X, q x represents the remaining power of the battery cell in the xth cycle, and Q represents the capacity of a single battery cell. Then, the target model of the remaining power and the number of charge and discharge cycles can be expressed as:
[0051] SOC i =a i *x+bi ,i=1,2,…,m, where m represents the number of cells in the battery pack, a i 、b i is a constant, SOC i represents the remaining power sequence, and x represents the number of charge and discharge cycles.
[0052] 305. Perform significance detection on the target model of each battery cell to obtain significance detection results of each target model.
[0053] Specifically, based on the target model of each battery cell, the regression sum of squares and the error sum of squares corresponding to each target model are determined, wherein the regression sum of squares corresponds to the first degree of freedom, and the error sum of squares corresponds to the second degree of freedom; the ratio of each regression sum of squares to the corresponding error sum of squares is determined to obtain the variance homogeneity test value of each target model; based on the variance homogeneity test value of each target model, the assumed value corresponding to each target model is determined; based on the assumed value corresponding to each target model, it is determined whether each target model is significantly established, and the significance test result of each target model is obtained.
[0054] The regression sum of squares is The sum of squared errors is Then the variance homogeneity test value (i.e., the statistic of the F test) is Among them, the first degree of freedom df R =1, the second degree of freedom df E =n-2=28.
[0055] In a feasible implementation, determining whether each target model is significantly established based on the assumed value corresponding to each target model, and obtaining the significance detection result of each target model includes:
[0056] Determine whether the assumed value corresponding to each target model is greater than the preset value;
[0057] The target model whose assumed value is greater than the preset value is determined to be significantly established, and the target model whose assumed value is less than or equal to the preset value is determined to be insignificantly established, and the significance test results of each target model are obtained, and the significance test results are significantly established or insignificantly established.
[0058] It should be noted that the embodiment of the present application first determines the variance homogeneity test value (i.e., the statistic of the F test), and then determines the assumed value p-value based on the distribution of the statistic of the F test; and checks whether the regression equation is significantly established based on whether the assumed value is greater than a preset value.
[0059] It is understandable that in addition to the F test for significance detection, other test methods may also be used, such as U test, t test, variance analysis, etc. The F test is used as an example for illustration in the embodiments of the present application, and is not limited to this.
[0060] 306. Determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
[0061] Based on the significance test results of each target model, determine whether each battery cell in the battery pack has an internal short circuit. When the significance of a target model is established and the coulomb efficiency is less than 1, it means that the corresponding battery cell has an internal short circuit; if the insignificance of the target model is established, or the coulomb efficiency is equal to 1, it means that the corresponding battery cell does not have an internal short circuit.
[0062] If the significance test result of the target model is significant, it means that the remaining power of the normal battery cell increases linearly with the increase of the number of cycles, and the slope a i The larger the value is, the greater the leakage current of the battery cell with internal short circuit is, and the more serious the situation is. If the significance test result of the target model is not significant, the battery cell slope corresponding to the target model is almost equal to 0, indicating that there is no internal short circuit battery cell.
[0063] The embodiment of the present application analyzes each target model through a significance test to test whether the linear relationship of each target model holds. Before performing the significance test, it is also necessary to determine the statistics required for the significance test. The statistics determined vary depending on the significance test method, and are not specifically limited here.
[0064] In an embodiment of the present invention, a target model corresponding to each battery cell is established through a target detection parameter sequence corresponding to each battery cell, and the significance of the target model corresponding to each battery cell is tested to determine whether each battery cell has an internal short circuit, thereby improving the diagnostic accuracy of the short circuit in the battery pack.
[0065] See also Figure 5 , another flow chart of the short circuit diagnosis method in the battery pack provided by the embodiment of the present invention specifically includes:
[0066] 501. Obtain operating data of the battery pack, where the operating data includes the charging time of each battery cell in each charge and discharge cycle and the corresponding charging current.
[0067] It is understandable that when the target detection parameter is the charge amount, it is necessary to reacquire the operating data of the battery pack, which includes the charging time of each charge and the size of the charging current during each charging process.
[0068] 502. Determine the charge amount of each battery cell in each charge and discharge cycle based on the charging time and the corresponding charging current in each charge and discharge cycle.
[0069] For example, the charging time can be expressed as If there is an internal short circuit in the battery cell, the charge amount of the battery cell during each charge can be expressed as Q' ix , where i=1,2,…,m, m represents the number of cells, i represents the cell number, and x represents the number of charge and discharge cycles.
[0070] The first charge of the first cell is Q' 11 ;in,
[0071] Where Q represents the capacity of the battery cell, I represents the charging current, and t charge1 Indicates the charging time for the first charge, I self Indicates the self-discharge current, i.e. the leakage current. Similarly, the charge of the first cell for the second charge is expressed as Q' 12 .
[0072] 503. Determine a charge capacity sequence of each battery cell based on the charge capacity of each battery cell in each charge and discharge cycle. The charge capacity sequence is used to indicate the charge capacity of a single battery cell corresponding to different charge and discharge cycle numbers.
[0073] The charge sequence of each cell is Q' ix , Q' ix =[Q' i1 ,Q' i2 ,…,Q' ix ],i=1,2,…,m; where m represents the number of cells in the battery pack, i represents the cell number, and x represents the number of cycles.
[0074] 504. Establish a target model for each battery cell based on the charge amount sequence of each battery cell.
[0075] Specifically, a second correspondence between multiple charge capacities of each battery cell and the number of charge and discharge cycles is obtained; a target model of each battery cell is determined based on the charge capacities of each battery cell and the second correspondence, wherein the target model is used to indicate the changing relationship between the charge capacities corresponding to a single battery cell and the number of charge and discharge cycles.
[0076] Among them, the second corresponding relationship is Where x represents the number of charge and discharge cycles, η CEX Indicates the Coulombic efficiency of cell X, Q' x represents the charge capacity of a single battery cell, Q represents the capacity of a single battery cell, then the target model of charge capacity and charge and discharge cycle number can be expressed as:
[0077] Q′ i =a i *x+b i ,i=1,2,…,m, where m represents the number of cells in the battery pack, a i , bi is a constant, Q i represents the charge capacity sequence, and x represents the coulomb efficiency raised to the power of the number of charge and discharge cycles.
[0078] In a feasible implementation manner, when the charging current is constant, step 504 may also be replaced by:
[0079] Obtaining a third correspondence between multiple charging times and charge-discharge cycle numbers of each battery cell;
[0080] The target model of each battery cell is determined based on the charging time sequence of each battery cell and the third corresponding relationship. The target model is used to indicate the changing relationship between the charging time corresponding to a single battery cell and the number of charge and discharge cycles.
[0081] Among them, the third corresponding relationship is Where x represents the number of charge and discharge cycles, η CEX represents the Coulombic efficiency of cell X, T x represents the charging time of a single battery cell for the xth time, Q represents the capacity of a single battery cell, then the target model of charging time and number of charge and discharge cycles can be expressed as:
[0082] T i =a i *x+b i ,i=1,2,…,m, where m represents the number of cells in the battery pack, a i , b i is a constant, T i represents the charging time sequence, and x represents the coulomb efficiency raised to the power of the number of charge and discharge cycles.
[0083] 505. Perform significance detection on the target model of each battery cell to obtain significance detection results of each target model.
[0084] Specifically, based on the target model of each battery cell, the regression sum of squares and the error sum of squares corresponding to each target model are determined, wherein the regression sum of squares corresponds to the first degree of freedom, and the error sum of squares corresponds to the second degree of freedom; the ratio of each regression sum of squares to the corresponding error sum of squares is determined to obtain the variance homogeneity test value of each target model; based on the variance homogeneity test value of each target model, the assumed value corresponding to each target model is determined; based on the assumed value corresponding to each target model, it is determined whether each target model is significantly established, and the significance test result of each target model is obtained.
[0085] The regression sum of squares is The sum of squared errors is Then the variance homogeneity test value (i.e., the statistic of the F test) is Among them, the first degree of freedom df R =1, the second degree of freedom dfE =n-2=28.
[0086] In a feasible implementation, determining whether each target model is significantly established based on the assumed value corresponding to each target model, and obtaining the significance detection result of each target model includes:
[0087] Determine whether the assumed value corresponding to each target model is greater than the preset value;
[0088] The target model whose assumed value is greater than the preset value is determined to be significantly established, and the target model whose assumed value is less than or equal to the preset value is determined to be insignificantly established, and the significance test results of each target model are obtained, and the significance test results are significantly established or insignificantly established.
[0089] It should be noted that the embodiment of the present application first determines the variance homogeneity test value (i.e., the statistic of the F test), and then determines the assumed value p-value based on the distribution of the statistic of the F test; and checks whether the regression equation is significantly established based on whether the assumed value is greater than a preset value.
[0090] It is understandable that in addition to the F test for significance detection, other test methods may also be used, such as U test, t test, variance analysis, etc. The F test is used as an example for illustration in the embodiments of the present application, and is not limited to this.
[0091] 506. Determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
[0092] Based on the significance test results of each target model, determine whether each battery cell in the battery pack has an internal short circuit. When the significance of a target model is established and the coulomb efficiency is less than 1, it means that the corresponding battery cell has an internal short circuit; if the insignificance of the target model is established, or the coulomb efficiency is equal to 1, it means that the corresponding battery cell does not have an internal short circuit.
[0093] If the significance test result of the target model is significant, it means that the remaining power of the normal battery cell increases linearly with the increase of the number of cycles, and the slope a i The larger the value is, the greater the leakage current of the battery cell with internal short circuit is, and the more serious the situation is. If the significance test result of the target model is not significant, the battery cell slope corresponding to the target model is almost equal to 0, indicating that there is no internal short circuit battery cell.
[0094] The embodiment of the present application analyzes each target model through a significance test to test whether the linear relationship of each target model holds. Before performing the significance test, it is also necessary to determine the statistics required for the significance test. The statistics determined vary depending on the significance test method, and are not specifically limited here.
[0095] In an embodiment of the present invention, a target model corresponding to each battery cell is established through a target detection parameter sequence corresponding to each battery cell, and the significance of the target model corresponding to each battery cell is tested to determine whether each battery cell has an internal short circuit, thereby improving the diagnostic accuracy of the short circuit in the battery pack.
[0096] The above describes the method for diagnosing short circuits in a battery pack according to an embodiment of the present invention. The following describes the device for diagnosing short circuits in a battery pack according to an embodiment of the present invention. Figure 6 , an embodiment of a short circuit diagnosis device in a battery pack according to an embodiment of the present invention includes:
[0097] An acquisition module 601 is used to acquire a target detection parameter sequence of each battery cell in a battery pack, where the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell;
[0098] Establishing module 602, used to establish a target model of each battery cell based on the target detection parameter sequence of each battery cell;
[0099] A detection module 603 is used to perform a saliency detection on the target model of each battery cell to obtain a saliency detection result of each target model;
[0100] The determination module 604 is used to determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
[0101] In a feasible implementation manner, the target detection parameter is the remaining power, and the acquisition module 601 includes:
[0102] A first acquisition unit 6011 is used to acquire operation data of the battery pack, where the operation data includes a plurality of voltage data of each static period, where the static period is used to indicate the duration between two adjacent charge and discharge cycles of the battery pack;
[0103] A first determining unit 6012 is used to determine the average voltage of each battery cell in the battery pack in each static period based on the multiple voltage data in each static period, and obtain an average voltage sequence of each battery cell, wherein the average voltage sequence is used to indicate the average voltage of a single battery cell in each static period;
[0104] The second determining unit 6013 is used to determine the remaining power sequence of each battery cell based on the average voltage sequence of each battery cell and a preset SOC-OCV curve, wherein the remaining power sequence is used to indicate the charge state of a single battery cell in each static period.
[0105] In a feasible implementation manner, the first determining unit 6012 is specifically configured to:
[0106] Determine the last K voltage data of each battery cell in each static period based on the plurality of voltage data in each static period, where K is a positive integer;
[0107] The last K voltage data corresponding to each battery cell are averaged to obtain the average voltage of each battery cell in each static period;
[0108] An average voltage sequence of each battery cell is generated based on the average voltage of each battery cell in each rest period.
[0109] In a feasible implementation manner, the establishing module 602 is specifically used for:
[0110] Obtaining a first correspondence between a plurality of remaining capacities of each battery cell and the number of charge and discharge cycles;
[0111] A target model for each battery cell is determined based on the remaining power sequence of each battery cell and the first corresponding relationship, and the target model is used to indicate the changing relationship between the remaining power corresponding to a single battery cell and the number of charge and discharge cycles.
[0112] In a feasible implementation manner, the target detection parameter is the charge amount, and the acquisition module 601 further includes:
[0113] A second acquisition unit 6014 is used to acquire operating data of the battery pack, wherein the operating data includes the charging time and the corresponding charging current of each battery cell in each charge and discharge cycle;
[0114] The third determining unit 6015 is used to determine the charge amount of each battery cell in each charge and discharge cycle based on the charging time and the corresponding charging current in each charge and discharge cycle;
[0115] The fourth determining unit 6016 is used to determine a charge capacity sequence of each battery cell based on the charge capacity of each battery cell in each charge and discharge cycle, wherein the charge capacity sequence is used to indicate the charge capacity of a single battery cell corresponding to different charge and discharge cycle numbers.
[0116] In a feasible implementation manner, the establishing module 602 is further specifically used for:
[0117] Obtaining a second correspondence between multiple charge capacities of each battery cell and the number of charge and discharge cycles;
[0118] A target model for each battery cell is determined based on the charge capacity sequence of each battery cell and the second corresponding relationship, wherein the target model is used to indicate a changing relationship between the charge capacity corresponding to a single battery cell and the number of charge and discharge cycles.
[0119] In a feasible implementation manner, when the charging current is constant, the target detection parameter is the charging duration, and the establishment module 602 is specifically further used for:
[0120] Obtaining a third correspondence between multiple charging times and charge-discharge cycle numbers of each battery cell;
[0121] A target model for each battery cell is determined based on the charging time sequence of each battery cell and the third corresponding relationship, wherein the target model is used to indicate a changing relationship between the charging time corresponding to a single battery cell and the number of charge and discharge cycles.
[0122] In a feasible implementation manner, the detection module 603 specifically includes:
[0123] A fifth determining unit 6031 is used to determine a regression sum of squares and an error sum of squares corresponding to each target model based on the target model of each battery cell, wherein the regression sum of squares corresponds to the first degree of freedom, and the error sum of squares corresponds to the second degree of freedom;
[0124] A ratio determination unit 6032 is used to determine the ratio of each regression sum of squares to the corresponding error sum of squares to obtain a variance homogeneity test value of each target model;
[0125] A presumed value determination unit 6033 is used to determine the presumed value corresponding to each target model based on the variance homogeneity test value of each target model;
[0126] The significance determination unit 6034 is used to determine whether each target model is significantly established based on the assumed value corresponding to each target model, and obtain the significance detection result of each target model.
[0127] In a feasible implementation manner, the significance determination unit 6034 is specifically configured to:
[0128] Determine whether the assumed value corresponding to each target model is greater than the preset value;
[0129] The target model whose assumed value is greater than the preset value is determined to be significantly established, and the target model whose assumed value is less than or equal to the preset value is determined to be insignificantly established, and the significance detection results of each target model are obtained, and the significance detection results are significantly established or insignificantly established.
[0130] In an embodiment of the present invention, a target model corresponding to each battery cell is established through a target detection parameter sequence corresponding to each battery cell, and the significance of the target model corresponding to each battery cell is tested to determine whether each battery cell has an internal short circuit, thereby improving the diagnostic accuracy of the short circuit in the battery pack.
[0131] See also Figure 7As shown, the present invention also provides a battery management system, which includes a normal operating condition operation module 701 and an internal short circuit monitoring module 702, wherein the normal operating condition operation module 701 and the internal short circuit monitoring module 702 are electrically connected to a battery pack, respectively; the normal operating condition operation module is used to control the battery pack to operate in a normal operating condition; the internal short circuit monitoring module is used to control the battery pack to operate in an internal short circuit detection condition;
[0132] The internal short circuit monitoring module 702 includes an acquisition unit, an establishment unit, a detection unit and a determination unit, wherein the acquisition unit is used to acquire a target detection parameter sequence of each battery cell in the battery pack, and the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell;
[0133] The establishing unit is used to establish a target model for each battery cell based on the target detection parameter sequence of each battery cell;
[0134] The detection unit is used to perform saliency detection on the target model of each battery cell to obtain a saliency detection result of each target model;
[0135] The determination unit is used to determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
[0136] It should be noted that the normal operating condition operation module 701 and the internal short circuit monitoring module 702 can be operated simultaneously or asynchronously; when operating asynchronously, when a certain condition is triggered (for example, when it is detected that the initial value of the target detection parameter decreases relative to the corresponding historical value), the internal short circuit monitoring module 702 will be started and the normal operating condition operation module 701 will be stopped. In addition, the normal operating condition operation module 701 and the internal short circuit monitoring module 702 also detect the same battery pack.
[0137] See also Figure 8 As shown, the present invention also provides an energy storage system, which includes a plurality of battery packs 720, a data acquisition device 710 and a battery management system 700, wherein the data acquisition device 710 and the battery management system 700 are electrically connected to the plurality of battery packs 720, respectively, and the data acquisition device 710 and the battery management system 700 are electrically connected;
[0138] The data acquisition device 710 is used to collect the operating data of each battery pack;
[0139] The battery management system 700 includes a normal operating condition operation module and an internal short circuit monitoring module, and the normal operating condition operation module and the internal short circuit monitoring module are electrically connected to each battery pack respectively;
[0140] The normal operating condition operation module is used to control each battery pack to operate in a normal operating condition;
[0141] The internal short circuit monitoring module is used to control each battery pack to operate in an internal short circuit detection condition;
[0142] The internal short circuit monitoring module includes an acquisition unit, an establishment unit, a detection unit and a determination unit, wherein:
[0143] The acquisition unit is used to acquire a target detection parameter sequence of each battery cell in the battery pack, and the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell;
[0144] The establishing unit is used to establish a target model for each battery cell based on the target detection parameter sequence of each battery cell;
[0145] The detection unit is used to perform saliency detection on the target model of each battery cell to obtain a saliency detection result of each target model;
[0146] The determination unit is used to determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
[0147] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions. When the instructions are executed on a computer, the computer executes the steps of diagnosing a short circuit in the battery pack. The steps specifically include:
[0148] Obtain a target detection parameter sequence for each battery cell in a battery pack, the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; establish a target model for each battery cell based on the target detection parameter sequence for each battery cell; perform significance detection on the target model for each battery cell to obtain significance detection results for each target model; determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results for each target model. In an embodiment of the present invention, a target model corresponding to each battery cell is established through a target detection parameter sequence corresponding to each battery cell, and by checking the significance of the target model corresponding to each battery cell, it is determined whether each battery cell has an internal short circuit, thereby improving the accuracy of diagnosing short circuits within the battery pack.
[0149] The above-mentioned target detection parameter is the remaining power, and a target detection parameter sequence of each battery cell in the battery pack is obtained, including: obtaining the operating data of the battery pack, the operating data including multiple voltage data of each static period, and the static period is used to indicate the duration between two adjacent charge and discharge cycles of the battery pack; based on the multiple voltage data of each static period, the average voltage of each battery cell in the battery pack in each static period is determined to obtain the average voltage sequence of each battery cell, and the average voltage sequence is used to indicate the average voltage of a single battery cell in each static period; based on the average voltage sequence of each battery cell and a preset SOC-OCV curve, the remaining power sequence of each battery cell is determined, and the remaining power sequence is used to indicate the charge state of a single battery cell in each static period.
[0150] The above-mentioned method of determining the average voltage of each battery cell in the battery pack in each static period based on multiple voltage data in each static period to obtain the average voltage sequence of each battery cell includes: determining the last K voltage data of each battery cell in each static period based on multiple voltage data in each static period, where K is a positive integer; averaging the last K voltage data corresponding to each battery cell to obtain the average voltage of each battery cell in each static period; and generating the average voltage sequence of each battery cell based on the average voltage of each battery cell in each static period.
[0151] The target detection parameter is the remaining power. The target model of each battery cell is established based on the target detection parameter sequence of each battery cell, including: obtaining a first correspondence between multiple remaining powers of each battery cell and the number of charge and discharge cycles; determining the target model of each battery cell based on the remaining power sequence of each battery cell and the first correspondence, and the target model is used to indicate the changing relationship between the remaining power corresponding to a single battery cell and the number of charge and discharge cycles.
[0152] The target detection parameter is the charge capacity. The above-mentioned method of obtaining the target detection parameter sequence of each battery cell in the battery pack includes: obtaining the operating data of the battery pack, the operating data including the charging time of each battery cell in each charge and discharge cycle and the corresponding charging current; determining the charge capacity of each battery cell in each charge and discharge cycle based on the charging time and the corresponding charging current in each charge and discharge cycle; determining the charge capacity sequence of each battery cell based on the charge capacity of each battery cell in each charge and discharge cycle, the charge capacity sequence being used to indicate the corresponding charge capacity of a single battery cell in different charge and discharge cycle numbers.
[0153] The target detection parameter is the charge capacity. The target model of each battery cell is established based on the target detection parameter sequence of each battery cell, including: obtaining a second correspondence between multiple charge capacities of each battery cell and the number of charge and discharge cycles; determining the target model of each battery cell based on the charge capacity sequence of each battery cell and the second correspondence, and the target model is used to indicate the changing relationship between the charge capacity corresponding to a single battery cell and the number of charge and discharge cycles.
[0154] When the charging current is constant and the target detection parameter is the charging time, the target model of each battery cell is established based on the target detection parameter sequence of each battery cell, including: obtaining a third correspondence between multiple charging times of each battery cell and the number of charge and discharge cycles; determining the target model of each battery cell based on the charging time sequence of each battery cell and the third correspondence, the target model being used to indicate the changing relationship between the charging time corresponding to a single battery cell and the number of charge and discharge cycles.
[0155] The above-mentioned significance test is performed on the target model of each battery cell to obtain the significance test result of each target model, including: determining the regression sum of squares and error sum of squares corresponding to each target model based on the target model of each battery cell, wherein the regression sum of squares corresponds to the first degree of freedom, and the error sum of squares corresponds to the second degree of freedom; determining the ratio of each regression sum of squares to the corresponding error sum of squares to obtain the variance homogeneity test value of each target model; determining the assumed value corresponding to each target model based on the variance homogeneity test value of each target model; determining whether each target model is significantly established based on the assumed value corresponding to each target model, and obtaining the significance test result of each target model.
[0156] The above-mentioned method of determining whether each target model is significantly established based on the assumed value corresponding to each target model to obtain the significance detection result of each target model includes: judging whether the assumed value corresponding to each target model is greater than a preset value; determining the target model with the assumed value greater than the preset value as significantly established, and determining the target model with the assumed value less than or equal to the preset value as not significantly established, and obtaining the significance detection result of each target model, and the significance detection result is significantly established or not significantly established.
[0157] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0158] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0159] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.
[0160] Finally, it should be noted that the above embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.
Claims
1. A method for diagnosing short circuit in a battery pack, characterized in that: include: Obtaining a target detection parameter sequence for each battery cell in the battery pack, where the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; Establish a target model for each battery cell based on the target detection parameter sequence of each battery cell; Performing saliency detection on the target model of each battery cell to obtain saliency detection results of each target model; Based on the significance detection results of each target model, it is determined whether each battery cell in the battery pack has an internal short circuit.
2. The method for diagnosing short circuit in a battery pack according to claim 1, characterized in that: The target detection parameter is the remaining power, and the step of obtaining a target detection parameter sequence of each battery cell in the battery pack includes: Acquire operation data of the battery pack, the operation data including a plurality of voltage data of each static period, the static period being used to indicate the duration between two adjacent charge and discharge cycles of the battery pack; Determine the average voltage of each battery cell in the battery pack in each static period based on the multiple voltage data in each static period, and obtain an average voltage sequence of each battery cell, wherein the average voltage sequence is used to indicate the average voltage of a single battery cell in each static period; The remaining power sequence of each battery cell is determined based on the average voltage sequence of each battery cell and a preset SOC-OCV curve, and the remaining power sequence is used to indicate the charge state of a single battery cell in each static period.
3. The method for diagnosing short circuit in a battery pack according to claim 2, characterized in that: The step of determining the average voltage of each battery cell in the battery pack in each static period based on the plurality of voltage data in each static period to obtain an average voltage sequence of each battery cell includes: Determine the last K voltage data of each battery cell in each static period based on the plurality of voltage data in each static period, where K is a positive integer; The last K voltage data corresponding to each battery cell are averaged to obtain the average voltage of each battery cell in each static period; An average voltage sequence of each battery cell is generated based on the average voltage of each battery cell in each rest period.
4. The method for diagnosing short circuit in a battery pack according to claim 1, characterized in that: The target detection parameter is the remaining power, and the target model of each battery cell is established based on the target detection parameter sequence of each battery cell, including: Obtaining a first correspondence between a plurality of remaining capacities of each battery cell and the number of charge and discharge cycles; A target model for each battery cell is determined based on the remaining power sequence of each battery cell and the first corresponding relationship, and the target model is used to indicate the changing relationship between the remaining power corresponding to a single battery cell and the number of charge and discharge cycles.
5. The method for diagnosing short circuit in a battery pack according to claim 1, characterized in that: The target detection parameter is the charge amount, and the step of obtaining a target detection parameter sequence of each battery cell in the battery pack includes: Acquire operating data of the battery pack, the operating data including charging time and corresponding charging current of each battery cell in each charge and discharge cycle; Determine the charge amount of each battery cell in each charge and discharge cycle based on the charging time and the corresponding charging current in each charge and discharge cycle; The charge capacity sequence of each battery cell is determined based on the charge capacity of each battery cell in each charge and discharge cycle, and the charge capacity sequence is used to indicate the charge capacity corresponding to a single battery cell in different charge and discharge cycle numbers.
6. The method for diagnosing short circuit in a battery pack according to claim 1, characterized in that: The target detection parameter is the charge amount, and the target model of each battery cell is established based on the target detection parameter sequence of each battery cell, including: Obtaining a second correspondence between multiple charge capacities of each battery cell and the number of charge and discharge cycles; A target model for each battery cell is determined based on the charge capacity sequence of each battery cell and the second corresponding relationship, wherein the target model is used to indicate a changing relationship between the charge capacity corresponding to a single battery cell and the number of charge and discharge cycles.
7. The method for diagnosing short circuit in a battery pack according to claim 1, characterized in that: When the charging current is constant and the target detection parameter is the charging time, the target model of each battery cell is established based on the target detection parameter sequence of each battery cell, including: Obtaining a third correspondence between multiple charging times and charge-discharge cycle numbers of each battery cell; A target model for each battery cell is determined based on the charging time sequence of each battery cell and the third corresponding relationship, wherein the target model is used to indicate a changing relationship between the charging time corresponding to a single battery cell and the number of charge and discharge cycles.
8. The method for diagnosing short circuit in a battery pack according to any one of claims 1 to 7, characterized in that: The performing saliency detection on the target model of each battery cell to obtain the saliency detection result of each target model includes: Determine a regression sum of squares and an error sum of squares corresponding to each target model based on the target model of each battery cell, wherein the regression sum of squares corresponds to a first degree of freedom, and the error sum of squares corresponds to a second degree of freedom; Determine the ratio of each regression sum of squares to the corresponding error sum of squares to obtain the variance homogeneity test value of each target model; Determine the assumption value corresponding to each target model based on the variance homogeneity test value of each target model; Based on the assumption value corresponding to each target model, it is determined whether each target model is significantly established, and the significance detection result of each target model is obtained.
9. The method for diagnosing short circuit in a battery pack according to claim 8, characterized in that: The step of determining whether each target model is significantly established based on the assumed value corresponding to each target model, and obtaining the significance detection result of each target model, includes: Determine whether the assumed value corresponding to each target model is greater than the preset value; The target model whose assumed value is greater than the preset value is determined to be significantly established, and the target model whose assumed value is less than or equal to the preset value is determined to be insignificantly established, and the significance detection results of each target model are obtained, and the significance detection results are significantly established or insignificantly established.
10. A short circuit diagnosis device in a battery pack, characterized in that: include: An acquisition module, used to acquire a target detection parameter sequence of each battery cell in the battery pack, wherein the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; A building module is used to build a target model for each battery cell based on a target detection parameter sequence of each battery cell; A detection module is used to perform saliency detection on the target model of each battery cell to obtain saliency detection results of each target model; A determination module is used to determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
11. A battery management system, characterized in that: The battery management system comprises: A normal operating condition operation module and an internal short circuit monitoring module, wherein the normal operating condition operation module and the internal short circuit monitoring module are electrically connected to the battery pack respectively; The normal operating condition operation module is used to control the battery pack to operate in a normal operating condition; The internal short circuit monitoring module is used to control the battery pack to operate in an internal short circuit detection condition; The internal short circuit monitoring module includes an acquisition unit, an establishment unit, a detection unit and a determination unit, wherein: The acquisition unit is used to acquire a target detection parameter sequence of each battery cell in the battery pack, and the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; The establishing unit is used to establish a target model for each battery cell based on the target detection parameter sequence of each battery cell; The detection unit is used to perform saliency detection on the target model of each battery cell to obtain a saliency detection result of each target model; The determination unit is used to determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
12. An energy storage system, characterized in that: The energy storage system comprises: A plurality of battery packs, a data acquisition device and a battery management system, wherein the data acquisition device and the battery management system are electrically connected to the plurality of battery packs respectively, and the data acquisition device and the battery management system are electrically connected; The data acquisition device is used to collect the operating data of each battery pack; The battery management system includes a normal operating condition operation module and an internal short circuit monitoring module, and the normal operating condition operation module and the internal short circuit monitoring module are electrically connected to each battery pack respectively; The normal operating condition operation module is used to control each battery pack to operate in a normal operating condition; the internal short circuit monitoring module is used to control each battery pack to operate in an internal short circuit detection condition; The internal short circuit monitoring module includes an acquisition unit, an establishment unit, a detection unit and a determination unit, wherein: The acquisition unit is used to acquire a target detection parameter sequence of each battery cell in the battery pack, and the target detection parameter sequence is used to indicate multiple target detection parameters corresponding to a single battery cell; The establishing unit is used to establish a target model for each battery cell based on the target detection parameter sequence of each battery cell; The detection unit is used to perform saliency detection on the target model of each battery cell to obtain a saliency detection result of each target model; The determination unit is used to determine whether each battery cell in the battery pack has an internal short circuit based on the significance detection results of each target model.
13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, which, when executed by a processor, implement the method for diagnosing short circuits in a battery pack as described in any one of claims 1 to 9.