Battery micro short circuit diagnosis method and system based on correlation independent component analysis

Abstract

The invention belongs to the technical field of battery fault diagnosis, and provides a battery micro short circuit diagnosis method and system based on correlation independent component analysis, and the method comprises the steps: obtaining a real-time cycle correction correlation coefficient of each single battery and a battery correction correlation coefficient matrix of a time window in a normal operation state of the battery; based on the correction correlation coefficient matrix, correlation independent component analysis of each single battery is carried out, and a battery micro-short circuit fault diagnosis model is constructed; evaluating the obtained real-time cyclic correction correlation coefficient of each single battery on line according to the fault diagnosis model, and calculating a diagnosis statistic square prediction error; and when the obtained diagnosis statistic square prediction error exceeds a preset control threshold value, determining that the battery has a micro-short-circuit fault, calculating a contribution value and a contribution mean value of the real-time cyclic correction correlation coefficient of each single battery to the diagnosis statistic square prediction error, positioning the micro-short-circuit fault of the battery, determining the single battery in short circuit, and determining that the battery has the micro-short-circuit fault. And battery micro-short-circuit diagnosis is completed.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery fault diagnosis, and in particular relates to a battery micro-short circuit diagnosis method and system based on correlation independent component analysis. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In order to improve the grid's ability to absorb renewable energy power generation, a large number of energy storage systems have been installed and put into use; lithium-ion batteries with advantages such as high energy / power density, long service life, and low pollution have been widely used in energy storage systems. However, in recent years, fires and explosions caused by lithium-ion battery failures have occurred frequently, and the safety threat posed by lithium-ion batteries has become a prominent problem that needs to be solved urgently. Therefore, efficient and accurate fault diagnosis of lithium-ion battery systems is crucial. Among them, short-circuit faults may generate a lot of heat, which is an important cause of thermal runaway and is the most noteworthy battery system fault. However, early micro-short-circuit faults are difficult to detect and locate quickly and accurately due to their small degree of failure.

[0004] However, the existing energy storage system early micro-short circuit fault diagnosis technology often has the following defects: the model-based micro-short circuit diagnosis method has high requirements on the accuracy of the model and is easily affected by interference and noise in practical applications; the traditional short-circuit fault diagnosis method based on upper and lower voltage thresholds can only detect the fault when the short-circuit fault in the power energy storage develops from an early soft short circuit to a hard short circuit. In addition, this method often cannot take into account the inconsistency of each monomer in the battery system in terms of charge state, aging degree, internal resistance, etc., and only relies on a single fixed voltage control threshold for fault monitoring and diagnosis, which cannot detect early faults and has a high missed diagnosis rate; at the same time, the data-driven diagnosis method based on single correlation analysis has a large delay and poor sensitivity to early short-circuit faults, and cannot achieve real-time detection and positioning of early micro-short circuit faults of batteries in power energy storage systems. Summary of the invention

[0005] To solve the above problems, the present invention proposes a battery micro-short circuit diagnosis method and system based on correlation independent component analysis, which uses a cyclic correction correlation coefficient to preprocess the voltage measurement value, and constructs a battery micro-short circuit fault diagnosis model by combining the correction correlation coefficient matrix and independent component analysis. The battery micro-short circuit fault diagnosis model is evaluated based on the obtained real-time cyclic correction correlation coefficient to achieve rapid and accurate detection and positioning of battery micro-short circuit faults.

[0006] According to some embodiments, a first solution of the present invention provides a battery micro-short circuit diagnosis method based on correlation independent component analysis, which adopts the following technical solution:

[0007] A battery micro-short circuit diagnosis method based on correlation independent component analysis, comprising:

[0008] Obtain the real-time cycle correction correlation coefficient of each single battery and the battery correction correlation coefficient matrix of the time window in the normal operating state of the battery;

[0009] Based on the obtained correction correlation coefficient matrix, the correlation independent component analysis of each single battery is carried out to build a battery micro-short circuit fault diagnosis model;

[0010] The real-time cycle correction correlation coefficient of each single battery obtained by online evaluation of the constructed fault diagnosis model is calculated to calculate the square prediction error of the diagnosis statistic;

[0011] When the obtained square prediction error of the diagnostic statistic exceeds the preset control threshold, the battery has a micro-short circuit fault. The contribution value and the contribution mean of the real-time cycle correction correlation coefficient of each single battery to the square prediction error of the diagnostic statistic are calculated to locate the battery micro-short circuit fault, determine the short-circuited single battery, and complete the battery micro-short circuit diagnosis.

[0012] As a further technical limitation, when the battery is in normal operation, the voltage changes of each single cell are consistent, and the cyclic correction correlation coefficient can be used to pre-process the voltage, that is, in, represents the vector composed of w consecutive sampled voltages of the ith battery, w represents the length of the sliding time window, cov represents the calculation of the covariance between two vectors, σ represents the calculation of the standard deviation operation, and f represents the square wave correction function.

[0013] As a further technical limitation, in the process of performing independent component analysis of the correlation of each single cell based on the obtained correction correlation coefficient matrix, the obtained correction correlation coefficient matrix is ​​subjected to whitening processing of principal component analysis to obtain an orthogonal matrix; the obtained orthogonal matrix is ​​solved to obtain a demixing matrix, the Euclidean norm of each row in the obtained demixing matrix is ​​calculated, and the number of principal components is determined using the cumulative Euclidean norm percentage.

[0014] Furthermore, according to the determined number of principal elements, row vectors consistent with the determined number of principal elements are selected in the demixing matrix to form a main demixing matrix, and the construction of the battery micro-short circuit fault diagnosis model is completed according to the obtained main demixing matrix.

[0015] As a further technical limitation, in the process of locating the battery micro-short circuit fault, the contribution value of the real-time cycle-corrected correlation coefficient of each single cell to the obtained diagnostic statistic square prediction error and the contribution mean of the obtained contribution value are obtained respectively; when the contribution values ​​of the real-time cycle-corrected correlation coefficients of two adjacent single cells to the obtained diagnostic statistic square prediction error are both greater than the obtained contribution mean, it is judged that a micro-short circuit fault occurs between the two adjacent single cells according to the cross-adjacent positioning method, and the battery micro-short circuit fault is located.

[0016] As a further technical limitation, when the obtained diagnostic statistic square prediction error does not exceed a preset control threshold, the real-time cycle correction correlation coefficient of the single cell is re-acquired to perform an online evaluation of the real-time cycle correction correlation coefficient of the single cell.

[0017] According to some embodiments, the second solution of the present invention provides a battery micro-short circuit diagnosis system based on correlation independent component analysis, which adopts the following technical solution:

[0018] A battery micro-short circuit diagnosis system based on correlation independent component analysis, comprising:

[0019] An acquisition module, which is configured to acquire the real-time cycle correction correlation coefficient of each single battery and the battery correction correlation coefficient matrix of the time window under the normal operating state of the battery;

[0020] A construction module, which is configured to perform correlation independent component analysis of each single battery based on the obtained correction correlation coefficient matrix, and construct a battery micro-short circuit fault diagnosis model;

[0021] A calculation module configured to calculate a real-time cycle correction correlation coefficient of each single battery obtained by online evaluation according to the constructed fault diagnosis model, and calculate a square prediction error of a diagnosis statistic;

[0022] The diagnostic module is configured to calculate the contribution value and contribution mean of the real-time cycle correction correlation coefficient of each single cell to the square prediction error of the diagnostic statistic when the square prediction error of the obtained diagnostic statistic exceeds a preset control threshold, locate the battery micro-short circuit fault, determine the single cell with short circuit, and complete the battery micro-short circuit diagnosis.

[0023] According to some embodiments, a third solution of the present invention provides a computer-readable storage medium, which adopts the following technical solution:

[0024] A computer-readable storage medium stores a program, which, when executed by a processor, implements the steps of a battery micro-short circuit diagnosis method based on correlation independent component analysis as described in the first embodiment of the present invention.

[0025] According to some embodiments, a fourth solution of the present invention provides an electronic device, which adopts the following technical solution:

[0026] An electronic device comprises a memory, a processor and a program stored in the memory and running on the processor, wherein when the processor executes the program, the steps in the battery micro-short circuit diagnosis method based on correlation independent component analysis as described in the first scheme of the present invention are implemented.

[0027] According to some embodiments, a fifth solution of the present invention provides a computer program product, which adopts the following technical solution:

[0028] A computer program product includes software code, wherein the program in the software code executes the steps in the battery micro-short circuit diagnosis method based on correlation independent component analysis as described in the first embodiment of the present invention.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The present invention adopts cyclic correction correlation coefficient to preprocess the voltage measurement value, so as to achieve strong robustness against the inconsistency, interference and noise of battery cells; the diagnosis model is constructed by combining the correction correlation coefficient matrix and independent component analysis, and the principal component subspace is determined by cumulative Euclidean norm percentage; the correction correlation coefficient vector calculated in real time is evaluated, and the rapid and accurate detection and positioning of early micro-short circuit faults are achieved based on the square prediction error and contribution value. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0032] Figure 1 This is a flow chart of a battery micro-short circuit diagnosis method based on correlation independent component analysis in Embodiment 1 of the present invention;

[0033] Figure 2 This is a schematic diagram of a battery micro-short circuit diagnosis method based on correlation independent component analysis in Embodiment 1 of the present invention;

[0034] Figure 3 This is a schematic diagram of a measured voltage curve in Embodiment 1 of the present invention;

[0035] Figure 4 This is a schematic diagram of the correlation coefficient diagnosis result in the first embodiment of the present invention;

[0036] Figure 5 Schematic diagram of micro short circuit fault detection based on SPE in Embodiment 1 of the present invention;

[0037] Figure 6 This is a schematic diagram of micro short circuit fault location based on contribution value in Embodiment 1 of the present invention;

[0038] Figure 7 This is a structural block diagram of a battery micro-short circuit diagnosis system based on correlation independent component analysis in Example 2 of the present invention. DETAILED DESCRIPTION

[0039] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0040] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0041] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0042] In the present invention, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are relational words determined only for the convenience of describing the structural relationships of the various parts or elements of the present invention, and do not specifically refer to any part or element in the present invention and should not be understood as limitations on the present invention.

[0043] In the present invention, terms such as "fixed connection", "connected", "connection", etc. should be understood in a broad sense, indicating that it can be fixedly connected, integrally connected or detachably connected; it can be directly connected or indirectly connected through an intermediate medium. For relevant scientific research or technical personnel in this field, the specific meanings of the above terms in the present invention can be determined according to specific circumstances, and they cannot be understood as limitations on the present invention.

[0044] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0045] Embodiment 1

[0046] Embodiment 1 of the present invention introduces a battery micro-short circuit diagnosis method based on correlation independent component analysis.

[0047] In order to solve the problem that micro short circuit faults in current battery energy storage systems are difficult to diagnose and have high computational load, this embodiment proposes a battery micro short circuit fault diagnosis method based on correlation independent component analysis, which realizes rapid and accurate detection and positioning of battery micro short circuit faults.

[0048] like Figure 1 A battery micro-short circuit diagnosis method based on correlation independent component analysis is shown, comprising:

[0049] Obtain the real-time cycle correction correlation coefficient of each single battery and the battery correction correlation coefficient matrix of the time window in the normal operating state of the battery;

[0050] Based on the obtained correction correlation coefficient matrix, the correlation independent component analysis of each single battery is carried out to build a battery micro-short circuit fault diagnosis model;

[0051] The real-time cycle correction correlation coefficient of each single battery obtained by online evaluation of the constructed fault diagnosis model is calculated to calculate the square prediction error of the diagnosis statistic;

[0052] When the obtained square prediction error of the diagnostic statistic exceeds the preset control threshold, the battery has a micro-short circuit fault. The contribution value and the contribution mean of the real-time cycle correction correlation coefficient of each single battery to the square prediction error of the diagnostic statistic are calculated to locate the battery micro-short circuit fault, determine the short-circuited single battery, and complete the battery micro-short circuit diagnosis.

[0053] This embodiment adopts Figure 2 The architecture shown implements a battery micro-short circuit diagnosis method, that is, calculating the cyclic correction correlation coefficient between each battery cell within a time window, thereby overcoming the adverse effects of battery inconsistency, interference, noise, etc. on fault diagnosis to a certain extent; using the correction correlation coefficient matrix of the sample voltage under normal battery operation, combined with independent component analysis to build a diagnosis model, in the process of establishing the diagnosis model, the cumulative Euclidean norm percentage is used to determine the principal component space; using the constructed fault diagnosis model to evaluate the correlation coefficient vector of the battery voltage online, detecting faults based on the squared prediction error, and using the contribution value of each variable to the squared prediction error to accurately locate the battery with a micro-short circuit fault.

[0054] In this embodiment, in the battery composed of single cells connected in series, since the current flowing through all the single cells is the same, the voltage of the battery shows a similar change trend. When the energy storage battery system is in normal working state, the voltage change of each single cell is almost equal, so the cyclic correction correlation coefficient is used to pre-process the voltage, that is:

[0055]

[0056] in, represents the vector composed of w consecutive sampled voltages of the ith battery, w represents the length of the sliding time window, cov represents the calculation of the covariance between the two vectors, σ represents the calculation of the standard deviation operation, and f represents the square wave correction function, that is:

[0057]

[0058] Where a represents the amplitude of the square wave function, and T represents the period of the square wave function. In order to reduce the adverse effects of noise, interference, and inconsistency on inconsistency, the value of the sliding window length w needs to be reasonably selected. When the w value is too large, the sensitivity to faults will be reduced; and when the w value is too small, the impact of errors, noise, and interference on fault diagnosis will be amplified. In this embodiment, the length of the time window is 100. According to the value of w, the square wave function a and T parameters in this embodiment are taken as 10 and 4 respectively.

[0059] Assume that there are d cells in a series-connected battery; at sampling time k, the correlation coefficient vector x between the voltages of adjacent cells under normal circumstances is k for

[0060] x k =[x k (1,2),x k (2,3),…,x k (d-1,d),x k (d,1)] T ;

[0061] Among them, x k (i, j) represents the correlation coefficient between battery i and battery j at time k within a time window. k can be expressed as a linear combination of m unknown independent elements, namely:

[0062]

[0063] Among them, A is the unknown mixing matrix to be calculated, s k Represents a matrix containing m independent elements, where m=d.

[0064] Therefore, the correction correlation coefficient matrix at any time in the non-fault condition is:

[0065] x = As;

[0066] Among them, A∈R d×m .

[0067] x is standardized and it is assumed that the independent element has zero mean and unit variance. To establish a micro short circuit diagnosis model based on correlation independent component analysis, this embodiment first performs whitening processing to eliminate all cross-correlations between random variables.

[0068] In this embodiment, the whitening process of the matrix is ​​realized by principal component analysis, that is:

[0069] z=Λ -1 / 2 U T x = Qx;

[0070] Among them, Λ and U are obtained by eigendecomposing the covariance matrix of the sample matrix, which are the diagonal matrix composed of eigenvalues ​​and the orthogonal matrix composed of eigenvectors corresponding to the corresponding eigenvalues, respectively, and Q is the whitening matrix;

[0071] E(xx T )=UΛU T .

[0072] The sample matrix is ​​whitened, that is:

[0073] z=Qx=QAs=Bs;

[0074] I d*d =E(zz T )=ΒE(ss T )B T =BB T ;

[0075]

[0076] Where B is an orthogonal matrix, W = B T Q is the demixing matrix.

[0077] Therefore, by solving the orthogonal matrix B, the independence between independent elements is maximized.

[0078] Since non-Gaussianity represents independence, for each column vector b i Perform random initialization and iterative calculation to make the i-th independent element The non-Gaussianity of is maximized. Negative entropy is used as a measure of non-Gaussianity, and the negative entropy approximation method is J(y) = [EG(y)-EG(v)] 2 ;

[0079] In which, it is assumed that the random variable y has a mean of zero and a variance of 1, v is a Gaussian variable with a mean of zero and a variance of 1, and G(*) is a non-quadratic function, that is, G(s)=log[cosh(s)].

[0080] The calculation steps for each column vector of the orthogonal matrix B are as follows:

[0081] 1) Initialize i=1;

[0082] 2) Randomly initialize b i ;

[0083] 3) b i ←E{zG′(b i T z)}-E{G″(b i T z)}b i ;

[0084] 4) b calculated by standard orthogonalization i ;

[0085] 5) If b i If it does not converge, return to step 3);

[0086] 6) If b i has converged, then b i The iteration ends, set i=i+1, and return to step 2) to calculate the next column vector.

[0087] Solving the orthogonal matrix B, we can get the demixing matrix W = B T Q. To obtain the main component subspace, calculate the Euclidean norm of each row of the solution mixing matrix W, and determine the number of main components according to the cumulative Euclidean norm percentage, that is:

[0088]

[0089] Among them, ‖w′ b ‖ represents the Euclidean norm of the bth row after the rows of matrix W are arranged in descending order of the Euclidean norm. When CNP reaches 0.85, it means that the main component subspace has contained the main information, so the number of main components l can be determined. After obtaining the number of main components l, the first l row vectors with the largest norm in matrix W are selected to form the main solution mixing matrix Since then, the independent component micro-short circuit fault diagnosis model based on the corrected correlation coefficient has been constructed.

[0090] In the micro-short circuit fault diagnosis process of this embodiment, the correction correlation coefficient vector x obtained by real-time sampling is rt Perform online evaluation and construct the diagnostic statistic square prediction error SPE, namely:

[0091]

[0092] in, It is composed of some columns of the matrix B, whose column indices are the same as those in W. The real-time calculated SPE is compared with the control threshold obtained through normal sample data to detect micro short circuit faults.

[0093] To reduce the computational load, the fault location strategy is executed only after the fault is detected. The contribution value of each correlation coefficient variable to SPE and the mean contribution value of all variables are calculated, that is:

[0094]

[0095] in, is the contribution value of the ith variable, is a vector The i-th element of is the contribution mean. Contribution mean Since each correlation coefficient variable is associated with two adjacent batteries, when the contribution value of two adjacent variables is greater than the contribution mean, the short circuit position can be accurately determined according to the cross-adjacent positioning method.

[0096] Case Analysis

[0097] This embodiment is experimentally verified on a battery pack consisting of six lithium-ion batteries connected in series; the rated capacity of the battery cell is 50Ah, and the parallel short-circuit resistance simulating a micro short-circuit fault is 1 ohm. The UDDS working condition is used to simulate the actual operation of the electric lithium-ion energy storage system. The voltage change curve of the whole process is as follows: Figure 3 As shown. The third battery has a short circuit fault, the time range is 820-850s, and the normal voltage sample data of 0-500s is used to build a diagnostic model, and then the subsequent real-time sampled data is diagnosed online according to the established model. In order to prove the superiority of the diagnostic method in this embodiment, the correlation coefficient method is used to diagnose the same experimental data.

[0098] After the short-circuit fault is injected at 820s, the short-circuit fault is diagnosed using the correlation coefficient method. The diagnosis results are as follows: Figure 4 As shown, the calculated correlation coefficient variable CC 2,3 and CC 3,4 The voltage is reduced to below the threshold at 824.4s and 824.5s respectively. The diagnostic delay of the whole process is 4.5s. The diagnostic method proposed in this embodiment is used to diagnose the voltage sampled in real time. The detection results are as follows: Figure 5 As shown. At 820.8s, the square prediction error SPE exceeds the threshold, thus detecting a short circuit fault. The detection delay is only 0.8s, which is much smaller than the 4.5s detection delay of the correlation coefficient, thus achieving rapid fault detection. After the fault is detected, the fault location strategy proposed in this embodiment is executed, and the fault location result is as shown in FIG. Figure 6As shown in the figure, the contribution values ​​of each variable at 820.8s are calculated. Only the contribution values ​​of x(2,3) and x(3,4) are greater than the mean. According to the staggered positioning method, the micro short circuit fault is located at the third battery.

[0099] According to the comparison of the two diagnostic methods, it can be seen that the method in this embodiment has superior performance and can achieve rapid and accurate diagnosis of early micro short circuit faults.

[0100] This embodiment uses a cyclic correction correlation coefficient to preprocess the voltage measurement value, and constructs a battery micro-short circuit fault diagnosis model by combining the correction correlation coefficient matrix and independent component analysis. An evaluation is performed based on the obtained real-time cyclic correction correlation coefficient to achieve rapid and accurate detection and positioning of battery micro-short circuit faults.

[0101] Embodiment 2

[0102] Embodiment 2 of the present invention introduces a battery micro-short circuit diagnosis system based on correlation independent component analysis.

[0103] like Figure 7 A battery micro-short circuit diagnosis system based on correlation independent component analysis is shown, comprising:

[0104] An acquisition module, which is configured to acquire the real-time cycle correction correlation coefficient of each single battery and the battery correction correlation coefficient matrix of the time window under the normal operating state of the battery;

[0105] A construction module, which is configured to perform correlation independent component analysis of each single battery based on the obtained correction correlation coefficient matrix, and construct a battery micro-short circuit fault diagnosis model;

[0106] A calculation module configured to calculate a real-time cycle correction correlation coefficient of each single battery obtained by online evaluation according to the constructed fault diagnosis model, and calculate a square prediction error of a diagnosis statistic;

[0107] The diagnostic module is configured to calculate the contribution value and contribution mean of the real-time cycle correction correlation coefficient of each single cell to the square prediction error of the diagnostic statistic when the square prediction error of the obtained diagnostic statistic exceeds a preset control threshold, locate the battery micro-short circuit fault, determine the single cell with short circuit, and complete the battery micro-short circuit diagnosis.

[0108] The detailed steps are the same as the battery micro-short circuit diagnosis method based on correlation independent component analysis provided in Example 1, and will not be repeated here.

[0109] Embodiment 3

[0110] Embodiment 3 of the present invention provides a computer-readable storage medium.

[0111] A computer-readable storage medium stores a program, which, when executed by a processor, implements the steps of a battery micro-short circuit diagnosis method based on correlation independent component analysis as described in Embodiment 1 of the present invention.

[0112] The detailed steps are the same as the battery micro-short circuit diagnosis method based on correlation independent component analysis provided in Example 1, and will not be repeated here.

[0113] Embodiment 4

[0114] A fourth embodiment of the present invention provides an electronic device.

[0115] An electronic device comprises a memory, a processor and a program stored in the memory and running on the processor, wherein when the processor executes the program, the steps in the battery micro-short circuit diagnosis method based on correlation independent component analysis as described in the first embodiment of the present invention are implemented.

[0116] The detailed steps are the same as the battery micro-short circuit diagnosis method based on correlation independent component analysis provided in Example 1, and will not be repeated here.

[0117] Embodiment 5

[0118] Embodiment 5 of the present invention provides a computer program product.

[0119] A computer program product includes software code, wherein the program in the software code executes the steps in the battery micro-short circuit diagnosis method based on correlation independent component analysis as described in Embodiment 1 of the present invention.

[0120] The detailed steps are the same as the battery micro-short circuit diagnosis method based on correlation independent component analysis provided in Example 1, and will not be repeated here.

[0121] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0122] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0125] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0126] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0127] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A battery micro-short circuit diagnosis method based on correlation independent component analysis, characterized in that: include: Obtain the real-time cycle correction correlation coefficient of each single battery and the battery correction correlation coefficient matrix of the time window in the normal operating state of the battery; Based on the obtained correction correlation coefficient matrix, the correlation independent component analysis of each single battery is carried out to build a battery micro-short circuit fault diagnosis model; The real-time cycle correction correlation coefficient of each single battery obtained by online evaluation of the constructed fault diagnosis model is calculated to calculate the square prediction error of the diagnosis statistic; When the obtained square prediction error of the diagnostic statistic exceeds the preset control threshold, the battery has a micro-short circuit fault. The contribution value and contribution mean of the real-time cycle correction correlation coefficient of each single battery to the square prediction error of the diagnostic statistic are calculated to locate the battery micro-short circuit fault and determine the single battery with short circuit.

2. A battery micro-short circuit diagnosis method based on correlation independent component analysis as claimed in claim 1, characterized in that: When the battery is in normal operation, the voltage changes of each single cell are consistent, so the cyclic correction correlation coefficient can be used to pre-process the voltage, that is, in, represents the vector composed of w consecutive sampled voltages of the ith battery, w represents the length of the sliding time window, cov represents the calculation of the covariance between two vectors, σ represents the calculation of the standard deviation operation, and f represents the square wave correction function.

3. A battery micro-short circuit diagnosis method based on correlation independent component analysis as described in claim 1, characterized in that: In the process of performing independent component analysis of the correlation of each single battery based on the obtained correction correlation coefficient matrix, the obtained correction correlation coefficient matrix is ​​subjected to whitening processing of principal component analysis to obtain an orthogonal matrix; the obtained orthogonal matrix is ​​solved to obtain a demixing matrix, the Euclidean norm of each row in the obtained demixing matrix is ​​calculated, and the number of principal components is determined by using the cumulative Euclidean norm percentage.

4. A battery micro-short circuit diagnosis method based on correlation independent component analysis as described in claim 3, characterized in that: According to the determined number of principal elements, row vectors consistent with the determined number of principal elements are selected in the demixing matrix to form a main demixing matrix, and the construction of the battery micro-short circuit fault diagnosis model is completed according to the obtained main demixing matrix.

5. A battery micro-short circuit diagnosis method based on correlation independent component analysis as described in claim 1, characterized in that: In the process of locating the battery micro-short circuit fault, the contribution value of the real-time cycle-corrected correlation coefficient of each single battery to the obtained diagnostic statistic square prediction error and the contribution mean of the obtained contribution values ​​are obtained respectively; when the contribution values ​​of the real-time cycle-corrected correlation coefficients of two adjacent single batteries to the obtained diagnostic statistic square prediction error are both greater than the obtained contribution mean, it is judged that a micro-short circuit fault occurs between the two adjacent single batteries according to the cross-adjacent positioning method, and the battery micro-short circuit fault is located.

6. A battery micro-short circuit diagnosis method based on correlation independent component analysis as claimed in claim 1, characterized in that: When the obtained diagnostic statistic square prediction error does not exceed a preset control threshold, the real-time cycle correction correlation coefficient of the single cell is re-acquired to perform online evaluation of the real-time cycle correction correlation coefficient of the single cell.

7. A battery micro-short circuit diagnosis system based on correlation independent component analysis, characterized in that: include: An acquisition module, which is configured to acquire the real-time cycle correction correlation coefficient of each single battery and the battery correction correlation coefficient matrix of the time window under the normal operating state of the battery; A construction module, which is configured to perform correlation independent component analysis of each single battery based on the obtained correction correlation coefficient matrix, and construct a battery micro-short circuit fault diagnosis model; A calculation module configured to calculate a real-time cycle correction correlation coefficient of each single battery obtained by online evaluation of the constructed fault diagnosis model, and calculate a square prediction error of a diagnosis statistic; The diagnostic module is configured to calculate the contribution value and contribution mean of the real-time cycle correction correlation coefficient of each single cell to the square prediction error of the diagnostic statistic when the square prediction error of the obtained diagnostic statistic exceeds a preset control threshold, locate the battery micro-short circuit fault, determine the single cell with short circuit, and complete the battery micro-short circuit diagnosis.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the battery micro-short circuit diagnosis method based on correlation independent component analysis as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the battery micro-short circuit diagnosis method based on correlation independent component analysis as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising software code, characterized in that The program in the software code executes the steps of the battery micro-short circuit diagnosis method based on correlation independent component analysis as described in any one of claims 1-6.

Images