CN116087787A - Battery fault judging method and system based on principal component analysis method - Google Patents
Battery fault judging method and system based on principal component analysis method Download PDFInfo
- Publication number
- CN116087787A CN116087787A CN202310067811.2A CN202310067811A CN116087787A CN 116087787 A CN116087787 A CN 116087787A CN 202310067811 A CN202310067811 A CN 202310067811A CN 116087787 A CN116087787 A CN 116087787A
- Authority
- CN
- China
- Prior art keywords
- battery
- principal component
- matrix
- fault
- component analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Secondary Cells (AREA)
Abstract
The present disclosure provides a method and a system for judging battery faults based on a principal component analysis method, wherein the method comprises the steps of obtaining historical operation data of a non-faulty battery, and constructing a data matrix based on the historical operation data of the non-faulty battery; constructing a principal component analysis model, wherein the principal component analysis model obtains a covariance matrix based on an input data matrix, and then carries out singular value decomposition on the covariance matrix so as to output projection matrices of principal components and residual components; acquiring real-time operation data of a target battery, and calculating to obtain Hotelling statistics, square prediction errors and corresponding control limit values of the target battery based on the real-time operation data, the projection matrix of main components and residual components and the significance level; judging whether the target battery fails or not based on the Hotelling statistics, the square prediction error and the corresponding control limit value; and if the target battery fails, determining the battery failure position. According to the method disclosed by the invention, the battery fault and the fault occurrence position can be judged more accurately.
Description
Technical Field
The disclosure relates to the field of intelligent fault diagnosis of battery energy storage systems, in particular to a method and a system for judging battery faults based on a principal component analysis method.
Background
Global climate warming, environmental destruction is due to excessive use of traditional fossil energy such as coal, and various countries have been apprehended about the necessity of energy transformation, and carbon emission is reduced by strongly developing and utilizing green low-carbon energy. In order to promote energy transformation, electrochemical energy storage has been widely popularized in recent years as an important means for improving energy utilization rate. Among them, the battery, especially lithium ion battery, becomes the first choice of electrochemical energy storage by virtue of its high energy density and no memory effect. The energy storage lithium battery is very critical to the safe operation of the energy storage power station, and is very important for timely overhauling and maintaining the energy storage lithium battery, predicting the real-time potential faults of the lithium ion battery and timely judging the fault types.
Existing fault diagnosis methods can be classified into model-based methods and data-driven methods according to different principles. The fault diagnosis research technology of the battery energy storage system has a great deal of theoretical basis and practical experience, and along with the increase of global battery energy storage, particularly lithium battery energy storage demands, the battery energy storage system is developing towards integration and light weight, and the fault technology of the battery energy storage system is also rapidly developed. However, these existing fault diagnosis techniques have lower sensitivity in small fault diagnosis.
Disclosure of Invention
The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art.
Therefore, a first object of the present disclosure is to provide a method for determining a battery fault based on a principal component analysis method, which is mainly aimed at determining a battery fault and a fault occurrence position more accurately, and improving sensitivity of small fault diagnosis.
A second object of the present disclosure is to provide a battery failure determination system based on a principal component analysis method.
A third object of the present disclosure is to propose a battery failure judgment apparatus based on a principal component analysis method.
A fourth object of the present disclosure is to propose a non-transitory computer readable storage medium.
To achieve the above object, an embodiment of a first aspect of the present disclosure provides a method for determining a battery failure based on a principal component analysis method, including:
acquiring historical operation data of a non-fault battery, and constructing a data matrix based on the historical operation data of the non-fault battery;
constructing a principal component analysis model, wherein the principal component analysis model obtains a covariance matrix based on an input data matrix, and then carries out singular value decomposition on the covariance matrix so as to output a principal component projection matrix and a residual component projection matrix;
Acquiring real-time operation data of a target battery, and calculating to obtain Hotelling statistics, square prediction errors and corresponding control limit values of the target battery based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level;
judging whether the target battery fails or not based on the Hotelling statistics, square prediction errors and corresponding control limit values;
and if the target battery fails, determining a battery failure position based on the Hotelling statistics and the square prediction error.
In one embodiment of the present disclosure, the determining a battery fault location based on the hotelin statistic and the squared prediction error includes: decomposing the Hotelling statistics to obtain single battery Hotelling statistics of the target battery; decomposing the square prediction error to obtain the square prediction error of each battery cell in the target battery; and determining a battery fault location based on the battery cell Hotelling statistic and the battery cell square prediction error.
In one embodiment of the present disclosure, the control limits include a hollin statistic control limit and a square prediction error control limit, and the determining whether the target battery is malfunctioning based on the hollin statistic, square prediction error, and corresponding control limits includes: and if the Hotelling statistic is smaller than or equal to the Hotelling statistic control limit value and the square prediction error is smaller than or equal to the square prediction error control limit value, the target battery has no fault, otherwise, the target battery has fault.
In one embodiment of the present disclosure, the calculating, based on the real-time operation data, the principal component projection matrix, the residual component projection matrix, and the significance level, to obtain the hollin statistic, the square prediction error, and the corresponding control limit value of the target battery includes: calculating to obtain Hotelling statistics of the target battery based on the real-time operation data and the principal component projection matrix; calculating to obtain a square prediction error of the target battery based on the real-time operation data and the residual component projection matrix; and calculating a Hotelling statistic control limit value and a square prediction error control limit value based on the significance level.
In one embodiment of the present disclosure, the performing singular value decomposition on the covariance matrix to output a principal component projection matrix and a residual component projection matrix includes: singular value decomposition is carried out on the covariance matrix, so that a target matrix is obtained; obtaining the principal component projection matrix based on the feature vector of the preset column number of the target matrix; and obtaining the residual component projection matrix based on the characteristic vector of the residual column number except the preset column number in the target matrix.
In one embodiment of the present disclosure, further comprising: updating the historical operation data of the fault-free battery by using the operation data of the fault-free target battery, so as to update a data matrix; the updated data matrix is input to the principal component analysis model to output a new principal component projection matrix and a remaining component projection matrix.
To achieve the above object, a second aspect of the present disclosure provides a battery fault determination system based on a principal component analysis method, including:
the acquisition module is used for acquiring historical operation data of the fault-free battery and real-time operation data of the target battery;
the modeling module is used for constructing a data matrix based on the historical operation data of the fault-free battery and constructing a principal component analysis model, wherein the principal component analysis model obtains a covariance matrix based on the input data matrix, and then performs singular value decomposition on the covariance matrix so as to output a principal component projection matrix and a residual component projection matrix;
the calculation module is used for calculating the Hotelling statistic, the square prediction error and the corresponding control limit value of the target battery based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level;
The first judging module is used for judging whether the target battery fails or not based on the Hotelling statistics, the square prediction error and the corresponding control limit value;
and the second judging module is used for determining the battery fault position based on the Hotelling statistics and the square prediction error if the target battery fails.
In one embodiment of the disclosure, the battery fault determination system further includes an updating module for updating fault-free battery historical operating data using the operating data of the target battery when fault-free; the modeling module updates a data matrix based on the updated fault-free battery historical operating data and inputs the updated data matrix into the principal component analysis model to output a new principal component projection matrix and a remaining component projection matrix.
To achieve the above object, a third aspect embodiment of the present disclosure further provides a battery failure judgment apparatus based on a principal component analysis method, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for determining battery failure based on the principal component analysis method set forth in the first aspect of the present disclosure.
To achieve the above object, a fourth aspect embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the battery failure determination method based on the principal component analysis method proposed by the first aspect embodiment of the present disclosure.
In one or more embodiments of the present disclosure, obtaining fault-free battery historical operating data, and constructing a data matrix based on the fault-free battery historical operating data; constructing a principal component analysis model, wherein the principal component analysis model obtains a covariance matrix based on an input data matrix, and then carries out singular value decomposition on the covariance matrix so as to output a principal component projection matrix and a residual component projection matrix; acquiring real-time operation data of a target battery, and calculating based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level to obtain Hotelling statistics, square prediction errors and corresponding control limit values of the target battery; judging whether the target battery fails or not based on the Hotelling statistics, the square prediction error and the corresponding control limit value; if the target battery fails, determining a battery failure location based on the Hotelling statistics and the square prediction error. In this case, the principal component analysis model is used to obtain a principal component projection matrix and a residual component projection matrix based on the non-faulty battery historical operation data, and then the holcolin statistic, the square prediction error and the corresponding control limit value of the target battery are calculated based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level, so as to determine whether the target battery is faulty or not and the location of the fault. Therefore, the battery fault and the fault occurrence position can be judged more accurately, and the sensitivity of small fault diagnosis is improved.
Additional aspects and advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a schematic flow chart of a method for determining a battery fault based on a principal component analysis method according to an embodiment of the present disclosure;
fig. 2 is a flowchart illustrating another method for determining battery failure based on a principal component analysis method according to an embodiment of the present disclosure;
FIG. 3 shows a block diagram of a battery fault determination system based on a principal component analysis method provided by an embodiment of the present disclosure;
fig. 4 is a block diagram of a principal component analysis-based battery failure determination apparatus for implementing a principal component analysis-based battery failure determination method of an embodiment of the present disclosure.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present disclosure. Rather, they are merely examples of apparatus and methods consistent with aspects of embodiments of the present disclosure as detailed in the accompanying claims.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, the meaning of "a plurality" is at least two, such as two, three, etc., unless explicitly specified otherwise. It should also be understood that the term "and/or" as used in this disclosure refers to and encompasses any or all possible combinations of one or more of the associated listed items.
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.
The present disclosure provides a method and a system for judging a battery fault based on a principal component analysis method, and is mainly aimed at more accurately judging a battery fault and a fault occurrence position, thereby improving sensitivity of small fault diagnosis.
In a first embodiment, fig. 1 is a schematic flow chart of a method for determining a battery fault based on a principal component analysis method according to an embodiment of the disclosure.
As shown in fig. 1, specifically, the method for determining a battery failure based on the principal component analysis method includes:
step S11, acquiring historical operation data of the non-fault battery, and constructing a data matrix based on the historical operation data of the non-fault battery.
In step S11, the battery for which the battery failure determination method is directed may be, but is not limited to, a lithium ion battery.
In step S11, the non-failure battery history operation data may be various kinds of operation data such as current and voltage when the stored battery is operated without failure.
In step S11, the battery includes a plurality of battery cells, so the non-failure battery history operation data includes various kinds of operation data such as current and voltage at the time of non-failure operation of each battery cell.
In step S11, a corresponding data matrix is constructed using any of the operation data, and for example, a data matrix corresponding to the battery current may be selected from the current during the non-failure operation of each battery cell, and a data matrix corresponding to the battery voltage may be selected from the voltage during the non-failure operation of each battery cell. The data matrix corresponding to various operation data can be sent to the subsequent step to judge the battery fault.
In step S11, taking as an example a data matrix corresponding to the battery voltage constituted by the voltages at the time of the non-faulty operation of each battery cell, a data matrix constituted based on the non-faulty battery history operation data may be represented by a symbol Z. The data matrix Z satisfies Z εR N×m . Wherein R represents a real matrix. Each element in the real matrix is the voltage of the battery. m represents the number of cells (i.e., the number of variables), and N represents the total number of voltages detected by each cell (i.e., the number of samples per variable). The voltage can be collected according to a preset time interval when the voltage is detected, and the preset time interval can be determined according to different types of batteries and different actual working conditions.
And S12, constructing a principal component analysis model, wherein the principal component analysis model obtains a covariance matrix based on the input data matrix, and then performing singular value decomposition on the covariance matrix so as to output a principal component projection matrix and a residual component projection matrix.
In step S12, a principal component analysis model is constructed using principal component analysis (Principal Component Analysis, PCA). And obtaining a covariance matrix of the input data matrix through the principal component analysis model, and further obtaining a principal component projection matrix and a residual component projection matrix of the covariance matrix.
Specifically, in step S12, a covariance matrix is obtained based on the input data matrix by formula (1). The formula (1) is:
wherein C is Z Represents covariance matrix, N represents the number of samples per variable, Z represents data matrix, Z T Representing the transpose of the data matrix.
In step S12, in order to eliminate the order-of-magnitude difference between various variable data and avoid causing great influence on the subsequent principal component analysis, before obtaining the covariance matrix based on the input data matrix, normalization processing is performed on the data matrix so that the sample mean value of each variable is 0, and then the covariance matrix of the normalized data matrix is obtained by calculation.
In step S12, singular value decomposition is performed on the covariance matrix to output a principal component projection matrix and a residual component projection matrix, including: singular value decomposition is carried out on the covariance matrix, so that a target matrix is obtained; obtaining a principal component projection matrix based on the feature vector of the preset column number of the target matrix; and obtaining a residual component projection matrix based on the characteristic vector of the residual column number except the preset column number in the target matrix.
Specifically, singular value decomposition (Singular Value Decomposition, SVD) is performed on the covariance matrix obtained by the formula (1) by the formula (2), the formula (2) being:
in the formula, U is E R m×m ，∑∈R m×m ，V∈R m×m . Matrix U is unitary matrix, V * Is the transposed conjugate of unitary matrix V. Due to covariance matrix C Z Symmetric and positive, thus obtaining a target matrix P based on the unitary matrix U, the target matrix P satisfying p=u=v * When the diagonal matrix ∈a satisfies ∈Σ, the covariance matrix C Z Can be converted into formula (3):
C Z ＝P∧P T (3)
wherein each column of the matrix P is a eigenvector of the covariance matrix, and the diagonal matrix Λ is represented by the following formula (4):
∧＝diag(λ 1 ，...，λ m ) (4)
in the formula, diag represents constructing a diagonal matrix，λ 1 ，...，λ m The diagonal values representing the diagonal matrix a. Wherein the diagonal value lambda 1 ，...，λ m Is the eigenvalue of the covariance matrix ordered in descending order.
The projection matrix of the principal component (Principal Component, PC) of the covariance matrix can be obtained by selecting the feature vector of the preset column number from the target matrix P. The preset number of columns may be represented by symbol γ. The preset number of columns γ may be obtained by the cumulative variance percentage (Cumulative Variance Percentage, CVP) method. Principal component projection matrix P, which is the projection matrix of principal components of the covariance matrix pc ，P pc ∈R m×γ 。
Based on the above, the number of columns of the matrix U is m, so the number of columns of the target matrix P is m, the number of columns of the eigenvectors of the remaining columns except the preset number of columns in the target matrix P is m-gamma, and the eigenvectors of the remaining columns m-gamma except the preset number of columns gamma are selected from the target matrix P to obtain the projection matrix of the remaining components of the covariance matrix, namely the projection matrix P of the remaining components of the covariance matrix res ，P res ∈R m×(m-γ) 。
Based on the preset column number gamma, the front gamma eigenvalues can be selected from the diagonal matrix lambda, so as to obtain a principal component projection matrix P pc Main diagonal matrix lambda in corresponding diagonal matrix pc ，∧ pc ∈R γ×γ . Based on the remaining column number m-gamma, the remaining m-gamma eigenvalues can be selected from the diagonal matrix lambda to obtain a remaining component projection matrix P res The remaining focus matrix Λ in the corresponding diagonal matrix res 。∧ res ∈R (m-γ)×(m-γ) 。
In summary, in step S12, the principal component analysis model outputs a principal component projection matrix P based on the input data matrix pc And a residual component projection matrix P res And also outputs a main diagonal matrix ∈ pc And a residual focusing matrix ∈ res 。
In step S12, the matrix P is projected based on the principal component pc Main diagonal matrix ∈ pc Projection matrix P of residual components res Residual focusingMatrix ∈ res Covariance matrix C can be obtained Z Conversion to formula (5):
in addition, in step S12, the data matrix Z may be projected to two orthogonal subspaces by using the PCA method to obtain a principal subspace and a residual component subspace, in other words, the principal component projection matrix P output by the principal component analysis model may be used pc And a residual component projection matrix P res A main component space and a remaining component space are obtained. I.e. principal component space S pc Denoted as S pc ＝span{P pc Residual molecular space S res Denoted as S res ＝span{P res }. In the main component space S, the orthogonality of the two subspaces is taken into account pc And the remainder into component space S res The projections of (a) can be represented as formula (6) and formula (7), respectively:
wherein P is T pc Is P pc Transpose of P T res Is P res Is a transpose of (a).
Is a main component space S pc Is (i.e. the principal component matrix of the data matrix Z),>
is the residual molecular space S res I.e. the remaining component matrix of the data matrix Z).
The expression of the data matrix Z shown in the formula (8) can be obtained based on the formula (6) and the formula (7):
further decomposing the data matrix Z to obtain formula (9):
wherein T is pc ＝ZP pc ，T res ＝ZP res ，
As a scoring matrix, due to Singular Value Decomposition (SVD), therefore +.>
Are orthogonal to each other. Score matrix->
Is the projected data matrix Z. Wherein T is pc Contains main measurement information, T res Including the remaining information of the data matrix Z. Thereby, the matrix P is projected by the principal component pc And a residual component projection matrix P res The space of the data matrix Z can be converted into a dimension-reducing space by selecting a principal component projection matrix P pc The number of preset columns γ (also called degrees of freedom) of the data to be processed can be reduced.
And S13, acquiring real-time operation data of the target battery, and calculating based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level to obtain Hotelling statistics, square prediction errors and corresponding control limit values of the target battery.
In step S13, the acquired real-time operation data of the target battery may be represented by the symbol z A And (3) representing. z A ∈R m . m representsNumber of battery cells. Based on real-time operation data z A And the principal component analysis model of step S12 is output by Hotelling' S T 2 (Hotelling statistics) and SPE (square prediction error) as monitoring statistics for fault analysis of target battery, wherein Hotelling's T 2 Representing systematic variations in cell data, SPE represents random or unknown variations in measurements.
In step S13, the control limits include a hollin statistic control limit and a square prediction error control limit.
In step S13, the holtrelin statistic, the square prediction error and the corresponding control limit value of the target battery are calculated based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level, and the method includes: calculating to obtain Hotelling statistics of the target battery based on the real-time operation data and the principal component projection matrix; calculating to obtain a square prediction error of the target battery based on the real-time operation data and the residual component projection matrix; and calculating a Hotelling statistic control limit value and a square prediction error control limit value based on the significance level.
In step S13, hotelling' S T is calculated 2 (Hotelling statistics) and SPE (square prediction error), run data z in real time A Normalization was performed and the mean value of the data was made 0.
In step S13, the holtrelin statistic of the target battery is calculated by equation (10):
wherein T is 2 Hotelling statistics, z, for a target cell A T Is z A P of (2) T pc Is P pc Is to be used in the present invention,
is a main diagonal matrix ∈ pc Is a matrix of inverse of (a).
In step S13, the square prediction error of the target battery is calculated by the formula (11):
in the formula, SPE is the square prediction error of the target battery, P T res Is P res I represents the identity matrix.
Hotelling's T in the formulae (10) and (11) 2 (Hotelling statistics) data z can be run in real-time from PCA model space A Given by the mahalanobis distance of SPE (square prediction error) from the quadratic orthogonal distance to the PCA model space.
In step S13, a Hotelling statistics control limit (i.e., hotelling' S T) is calculated based on the significance level 2 Control limit of (a) and square prediction error control limit (control limit of SPE).
Specifically, for significance level α, hotelling's T 2 The control limit value of (2) is represented by the following formula (12):
in the method, in the process of the invention,
for the Hotelling statistics control limit, N is the number of cells (i.e., the number of samples per variable), γ is the number of preset columns (i.e., the degree of freedom), F α (γ, N- γ) is the critical value of F distribution. The critical value satisfies the formula (13):
in the method, in the process of the invention,
and->
Is χ with degrees of freedom of γ and N- γ, respectively 2 Distribution (chi-square distribution), the level of significance alpha is typically set between 90% and 95%.
The control limit value of the SPE control limit value is represented by the following formula (14):
in the method, in the process of the invention,
is the control limit value of SPE, in which theta 1 ，θ 2 ，h 0 Calculated by using (15)
In the method, in the process of the invention,
represented by lambda j To the power of k, k=1, 2,3, k=1, θ can be calculated 1 θ can be calculated when k=2 2 θ can be calculated when k=3 3 ，λ j The j-th eigenvalue of the diagonal matrix ∈, j being [ gamma+1, m]。
C under normal distribution corresponding to significance level alpha α Calculated by formula (16):
where erfc represents the complementary error function.
And step S14, judging whether the target battery fails or not based on the Hotelling statistics, the square prediction error and the corresponding control limit value.
In step S14, determining whether the target battery is malfunctioning based on the holtrelin statistic, the square prediction error, and the corresponding control limit includes: if the Hotelling statistic is smaller than or equal to the Hotelling statistic control limit value and the square prediction error is smaller than or equal to the square prediction error control limit value, the target battery has no fault, otherwise, the target battery has fault.
That is, it is determined whether or not the formula (17) satisfies:
If equation (17) is satisfied, the target battery is not faulty, and if at least one of the Hotelling statistics and the square prediction error is not satisfied (i.e., at least one exceeds the corresponding control limit), the target battery is faulty.
And step S15, if the target battery fails, determining the battery failure position based on the Hotelling statistics and the square prediction error.
In step S15, determining a battery fault location based on the hotelin statistics and the squared prediction error, comprising: decomposing the Hotelling statistics to obtain single-battery Hotelling statistics of each target battery; decomposing the square prediction error to obtain the square prediction error of each battery cell in the target battery; and determining a battery fault location based on the battery cell Hotelling statistics and the battery cell square prediction error.
In step S15, the fault location may be located by analyzing the contribution of each variable (i.e., each cell) to the SPE. The variable contributing the most is considered the variable most affected by the fault. The SPE statistics are decomposed into sums of contributions to it from the individual variables by equation (18):
wherein SPE (SPE) i Representing target cell z A Square prediction error of the i-th cell of (c).
i is 1 to m.
In step S15, the fault location can be located by analyzing the contributions of each variable to the Hotelling statistics. The equation for decomposing to obtain the cell-to-cell Hotelling statistics in the target cell can be obtained by analogy with equation (18).
In step S15, a battery fault location is determined based on the cell hollin statistic and the cell square prediction error. Specifically, the maximum value of the square prediction error of each battery cell is screened out, and SPE i The battery cell corresponding to the maximum value fails, and in addition, the battery cell corresponding to the maximum value of the Hotelling statistic of the battery cell fails.
Fig. 2 is a flowchart illustrating another method for determining battery failure based on a principal component analysis according to an embodiment of the present disclosure. In some embodiments, as shown in fig. 2, the battery fault determination method based on the principal component analysis includes: calculating a PCA model using the operational data of the non-faulty battery; calculating statistics and control limit values of the target battery; judging whether the statistics meet the conditions, if so, the target battery has no fault, and if not, the target battery fault is subjected to fault location. The operation data of the non-fault battery is the historical operation data of the non-fault battery in the step S11. The calculation of the PCA model using the operation data of the non-faulty battery can be specifically referred to the above-described related descriptions of step S11 and step S12. The statistics of the target battery include the holtrelin statistics and the square prediction error, and the calculation of the statistics and the control limit of the target battery may be specifically described with reference to step S13. The judgment as to whether the statistic satisfies the condition may be specifically described with reference to the above-described related description of step S14. If not, the fault location of the target battery fault may be specifically described with reference to step S15.
In some embodiments, as shown in fig. 2, the battery fault determination method based on the principal component analysis method further includes adaptively updating model data. The model data is the output data of the PCA model.
Specifically, considering that the battery system is not always steady-state, since there is a change in battery parameters (e.g., a change caused by temperature, state of charge (SoC), or aging), the PCA model will change, and therefore, the battery failure determination method based on the principal component analysis method further includes: and adopting a recursion method to adaptively update the principal component analysis model data. The process of adaptive updating by adopting the recursion method comprises the following steps: updating the historical operation data of the fault-free battery by using the operation data of the fault-free target battery, so as to update a data matrix; the updated data matrix is input into the principal component analysis model to output a new principal component projection matrix and a remaining component projection matrix. In this case, since the adaptive method has high robustness to parameter variation, the adaptive method is adopted to update the input data of the PCA model with a new fault-free sample to obtain a new principal component projection matrix and a remaining component projection matrix, thereby improving the accuracy of fault diagnosis. Wherein a forgetting factor may be used at each update to limit the impact of the old model on the update.
In the battery fault judging method based on the principal component analysis method, disclosed by the embodiment of the invention, the historical operation data of the non-fault battery is obtained, and a data matrix is constructed based on the historical operation data of the non-fault battery; constructing a principal component analysis model, wherein the principal component analysis model obtains a covariance matrix based on an input data matrix, and then carries out singular value decomposition on the covariance matrix so as to output a principal component projection matrix and a residual component projection matrix; acquiring real-time operation data of a target battery, and calculating based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level to obtain Hotelling statistics, square prediction errors and corresponding control limit values of the target battery; judging whether the target battery fails or not based on the Hotelling statistics, the square prediction error and the corresponding control limit value; if the target battery fails, determining a battery failure location based on the Hotelling statistics and the square prediction error. In this case, the principal component projection matrix and the residual component projection matrix are obtained based on the non-faulty battery history operation data using the principal component analysis model, and then the Hotelling statistics, the square prediction error, and the correlation of the target battery are calculated based on the real-time operation data, the principal component projection matrix, the residual component projection matrix, and the significance level And (3) controlling the limit value so as to determine whether the target battery fails and the position of the failure. Therefore, the battery fault and the fault occurrence position can be judged more accurately, and the sensitivity of small fault diagnosis is improved. The method of the present disclosure detects and locates faults by statistic evaluation based on principal component analysis by first principal component analysis of operational data of a fault-free battery system by a PCA model, then acquiring operational data of a battery operating in real time, calculating two statistics (i.e., hotelling statistics and square prediction errors) for monitoring, and analyzing a single battery cell signal versus Hotelling's T 2 And SPE to diagnose battery failure and failure occurrence location. The method of the present disclosure also employs a recursive approach to adaptively update the principal component analysis model. In summary, the method based on the disclosure can diagnose the battery fault and the fault occurrence position. The method improves the detectability of small faults, has higher sensitivity, and has higher robustness to parameter changes.
The following are system embodiments of the present disclosure that may be used to perform method embodiments of the present disclosure. For details not disclosed in the embodiments of the disclosed system, please refer to the embodiments of the disclosed method.
Fig. 3 shows a block diagram of a battery fault determination system based on a principal component analysis method provided in an embodiment of the present disclosure. Referring to fig. 3, the battery fault determining system 10 based on the principal component analysis method includes an obtaining module 11, a modeling module 12, a calculating module 13, a first determining module 14 and a second determining module 15, wherein:
an acquisition module 11 for acquiring historical operation data of the fault-free battery and real-time operation data of the target battery;
the modeling module 12 is configured to construct a data matrix based on the historical operating data of the fault-free battery, and construct a principal component analysis model, where the principal component analysis model obtains a covariance matrix based on the input data matrix, and then performs singular value decomposition on the covariance matrix to output a principal component projection matrix and a residual component projection matrix;
the calculation module 13 is used for calculating to obtain the Hotelling statistic, the square prediction error and the corresponding control limit value of the target battery based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level;
a first judging module 14, configured to judge whether the target battery fails based on the holtrelin statistic, the square prediction error and the corresponding control limit;
A second judging module 15 is configured to determine a battery fault location based on the holtrelin statistic and the square prediction error if the target battery fails.
Optionally, the second judging module 15 is specifically configured to: decomposing the Hotelling statistics to obtain single-battery Hotelling statistics of each target battery; decomposing the square prediction error to obtain the square prediction error of each battery cell in the target battery; and determining a battery fault location based on the battery cell Hotelling statistics and the battery cell square prediction error.
Optionally, the control limits include a Hotelling statistics control limit and a square prediction error control limit.
Optionally, the first judging module 14 is specifically configured to: if the Hotelling statistic is smaller than or equal to the Hotelling statistic control limit value and the square prediction error is smaller than or equal to the square prediction error control limit value, the target battery has no fault, otherwise, the target battery has fault.
Optionally, the computing module 13 is specifically configured to: calculating to obtain Hotelling statistics of the target battery based on the real-time operation data and the principal component projection matrix; calculating to obtain a square prediction error of the target battery based on the real-time operation data and the residual component projection matrix; and calculating a Hotelling statistic control limit value and a square prediction error control limit value based on the significance level.
Optionally, the modeling module 12 is specifically configured to: singular value decomposition is performed on the covariance matrix to output a principal component projection matrix and a residual component projection matrix, comprising: singular value decomposition is carried out on the covariance matrix, so that a target matrix is obtained; obtaining a principal component projection matrix based on the feature vector of the preset column number of the target matrix; and obtaining a residual component projection matrix based on the characteristic vector of the residual column number except the preset column number in the target matrix.
Optionally, the battery fault judging system 10 based on the principal component analysis method further includes an updating module for updating the fault-free battery history operation data using the operation data when the target battery is fault-free; the modeling module updates the data matrix based on the updated fault-free battery historical operating data and inputs the updated data matrix into the principal component analysis model to output a new principal component projection matrix and a remaining component projection matrix.
It should be noted that the foregoing explanation of the embodiment of the method for determining a battery failure based on the principal component analysis method is also applicable to the system for determining a battery failure based on the principal component analysis method of this embodiment, and is not described herein.
In the battery fault judging system based on the principal component analysis method of the embodiment of the disclosure, the acquiring module is used for acquiring historical operating data of the fault-free battery and real-time operating data of the target battery; the modeling module is used for constructing a data matrix based on the historical operation data of the fault-free battery and constructing a principal component analysis model, wherein the principal component analysis model obtains a covariance matrix based on the input data matrix, and then performs singular value decomposition on the covariance matrix so as to output a principal component projection matrix and a residual component projection matrix; the calculation module is used for calculating the Hotelling statistic, the square prediction error and the corresponding control limit value of the target battery based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level; the first judging module is used for judging whether the target battery fails or not based on the Hotelling statistics, the square prediction error and the corresponding control limit value; and the second judging module is used for determining the fault position of the battery based on the Hotelling statistics and the square prediction error if the target battery fails. In this case, the principal component analysis model is used to obtain principal component projection matrices and residual component projection matrices based on the non-faulty battery historical operation data, and then the Hotler statistics, square prediction errors and corresponding control limits of the target battery are calculated based on the real-time operation data, the principal component projection matrices, the residual component projection matrices and the significance level, thereby determining whether the target battery is faulty and emitting The location of the failure. Therefore, the battery fault and the fault occurrence position can be judged more accurately, and the sensitivity of small fault diagnosis is improved. The system of the present disclosure detects and locates faults by statistic evaluation based on principal component analysis by first principal component analysis of operational data of a fault-free battery system by a PCA model, then acquiring operational data of a battery operating in real time, calculating two statistics (i.e., hotelling statistics and square prediction errors) for monitoring, and analyzing a single battery cell signal versus Hotelling's T 2 And SPE to diagnose battery failure and failure occurrence location. The system of the present disclosure also employs a recursive approach to adaptively update the principal component analysis model. In summary, the system based on the disclosure is capable of diagnosing battery faults and fault occurrence positions. The system improves the detectability of small faults, has higher sensitivity, and the adaptive method has higher robustness to parameter changes.
According to embodiments of the present disclosure, the present disclosure also provides a battery failure determination apparatus based on a principal component analysis method, a readable storage medium, and a computer program product.
Fig. 4 is a block diagram of a principal component analysis-based battery failure determination apparatus for implementing a principal component analysis-based battery failure determination method of an embodiment of the present disclosure. The principal component analysis-based battery fault determination device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The battery failure determination apparatus based on the principal component analysis method may also represent various forms of mobile devices such as personal digital processing, cellular phones, smart phones, wearable electronic devices, and other similar computing devices. The components, connections and relationships of components, and functions of components shown in this disclosure are exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed in this disclosure.
As shown in fig. 4, the battery failure determination device 20 based on the principal component analysis method includes a calculation unit 21 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 22 or a computer program loaded from a storage unit 28 into a Random Access Memory (RAM) 23. In the RAM 23, various programs and data required for the operation of the battery failure determination apparatus 20 based on the principal component analysis method may also be stored. The computing unit 21, the ROM 22 and the RAM 23 are connected to each other via a bus 24. An input/output (I/O) interface 25 is also connected to bus 24.
A plurality of components in the battery failure determination apparatus 20 based on the principal component analysis method are connected to the I/O interface 25, including: an input unit 26 such as a keyboard, a mouse, etc.; an output unit 27 such as various types of displays, speakers, and the like; a storage unit 28, such as a magnetic disk, an optical disk, or the like, the storage unit 28 being communicatively connected to the computing unit 21; and a communication unit 29 such as a network card, modem, wireless communication transceiver, etc. The communication unit 29 allows the battery failure judgment device 20 based on the principal component analysis to exchange information/data with other electronic devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 21 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 21 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 21 performs the respective methods and processes described above, for example, performs a battery failure judgment method based on a principal component analysis method. For example, in some embodiments, the battery fault determination method based on principal component analysis may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 28. In some embodiments, part or all of the computer program may be loaded and/or installed on the battery failure determination device 20 based on the principal component analysis method via the ROM22 and/or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the computing unit 21, one or more steps of the above-described battery failure determination method based on the principal component analysis method may be performed. Alternatively, in other embodiments, the computing unit 21 may be configured to perform the battery failure determination method based on the principal component analysis method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described above in this disclosure may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or principal component analysis-based battery fault determination device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or electronic device, or any suitable combination of the preceding. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage electronic device, a magnetic storage electronic device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present disclosure may be performed in parallel, sequentially, or in a different order, so long as the desired result of the technical solution of the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (10)
1. A battery failure judgment method based on a principal component analysis method, characterized by comprising:
acquiring historical operation data of a non-fault battery, and constructing a data matrix based on the historical operation data of the non-fault battery;
constructing a principal component analysis model, wherein the principal component analysis model obtains a covariance matrix based on an input data matrix, and then carries out singular value decomposition on the covariance matrix so as to output a principal component projection matrix and a residual component projection matrix;
Acquiring real-time operation data of a target battery, and calculating to obtain Hotelling statistics, square prediction errors and corresponding control limit values of the target battery based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level;
judging whether the target battery fails or not based on the Hotelling statistics, square prediction errors and corresponding control limit values;
and if the target battery fails, determining a battery failure position based on the Hotelling statistics and the square prediction error.
2. The method of claim 1, wherein said determining a battery fault location based on said holtelin statistic and said square prediction error comprises:
decomposing the Hotelling statistics to obtain single battery Hotelling statistics of the target battery;
decomposing the square prediction error to obtain the square prediction error of each battery cell in the target battery;
and determining a battery fault location based on the battery cell Hotelling statistic and the battery cell square prediction error.
3. The method of claim 2, wherein the control limits include a hollin statistic control limit and a square prediction error control limit, and the determining whether the target battery is faulty based on the hollin statistic, a square prediction error, and the corresponding control limit comprises:
And if the Hotelling statistic is smaller than or equal to the Hotelling statistic control limit value and the square prediction error is smaller than or equal to the square prediction error control limit value, the target battery has no fault, otherwise, the target battery has fault.
4. The method for determining a failure of a battery based on principal component analysis according to claim 3, wherein the calculating based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level to obtain the holtrelin statistic, the square prediction error and the corresponding control limit value of the target battery includes:
calculating to obtain Hotelling statistics of the target battery based on the real-time operation data and the principal component projection matrix;
calculating to obtain a square prediction error of the target battery based on the real-time operation data and the residual component projection matrix;
and calculating a Hotelling statistic control limit value and a square prediction error control limit value based on the significance level.
5. The battery fault determination method based on principal component analysis according to claim 1, wherein the performing singular value decomposition on the covariance matrix to output a principal component projection matrix and a residual component projection matrix comprises:
Singular value decomposition is carried out on the covariance matrix, so that a target matrix is obtained;
obtaining the principal component projection matrix based on the feature vector of the preset column number of the target matrix;
and obtaining the residual component projection matrix based on the characteristic vector of the residual column number except the preset column number in the target matrix.
6. The method for determining a failure of a battery based on principal component analysis according to claim 1, further comprising:
updating the historical operation data of the fault-free battery by using the operation data of the fault-free target battery, so as to update a data matrix;
the updated data matrix is input to the principal component analysis model to output a new principal component projection matrix and a remaining component projection matrix.
7. A battery failure judgment system based on a principal component analysis method, comprising:
the acquisition module is used for acquiring historical operation data of the fault-free battery and real-time operation data of the target battery;
the modeling module is used for constructing a data matrix based on the historical operation data of the fault-free battery and constructing a principal component analysis model, wherein the principal component analysis model obtains a covariance matrix based on the input data matrix, and then performs singular value decomposition on the covariance matrix so as to output a principal component projection matrix and a residual component projection matrix;
The calculation module is used for calculating the Hotelling statistic, the square prediction error and the corresponding control limit value of the target battery based on the real-time operation data, the principal component projection matrix, the residual component projection matrix and the significance level;
the first judging module is used for judging whether the target battery fails or not based on the Hotelling statistics, the square prediction error and the corresponding control limit value;
and the second judging module is used for determining the battery fault position based on the Hotelling statistics and the square prediction error if the target battery fails.
8. The battery fault determination system based on the principal component analysis of claim 7, further comprising an update module for updating fault-free battery history operation data using operation data when the target battery is fault-free; the modeling module updates a data matrix based on the updated fault-free battery historical operating data and inputs the updated data matrix into the principal component analysis model to output a new principal component projection matrix and a remaining component projection matrix.
9. A battery failure judgment apparatus based on a principal component analysis method, characterized by comprising:
At least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the principal component analysis-based battery fault determination method of any one of claims 1-6.
10. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the battery failure determination method based on the principal component analysis method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310067811.2A CN116087787A (en) | 2023-01-18 | 2023-01-18 | Battery fault judging method and system based on principal component analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310067811.2A CN116087787A (en) | 2023-01-18 | 2023-01-18 | Battery fault judging method and system based on principal component analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116087787A true CN116087787A (en) | 2023-05-09 |
Family
ID=86207987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310067811.2A Pending CN116087787A (en) | 2023-01-18 | 2023-01-18 | Battery fault judging method and system based on principal component analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116087787A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116627116A (en) * | 2023-07-26 | 2023-08-22 | 沈阳仪表科学研究院有限公司 | Process industry fault positioning method and system and electronic equipment |
| CN117289142A (en) * | 2023-11-24 | 2023-12-26 | 国网天津市电力公司电力科学研究院 | Method and device for detecting internal short circuit fault of lithium ion energy storage power station battery |
| CN117630679A (en) * | 2023-11-30 | 2024-03-01 | 湖北工业大学 | Battery fault diagnosis method and system |
| CN117783886A (en) * | 2024-02-23 | 2024-03-29 | 武汉船用电力推进装置研究所(中国船舶集团有限公司第七一二研究所) | Power battery abnormal state identification method and device, electronic equipment and storage medium |
| CN117783886B (en) * | 2024-02-23 | 2024-05-31 | 武汉船用电力推进装置研究所(中国船舶集团有限公司第七一二研究所) | Power battery abnormal state identification method and device, electronic equipment and storage medium |
-
2023
- 2023-01-18 CN CN202310067811.2A patent/CN116087787A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116627116A (en) * | 2023-07-26 | 2023-08-22 | 沈阳仪表科学研究院有限公司 | Process industry fault positioning method and system and electronic equipment |
| CN116627116B (en) * | 2023-07-26 | 2023-10-20 | 沈阳仪表科学研究院有限公司 | Process industry fault positioning method and system and electronic equipment |
| CN117289142A (en) * | 2023-11-24 | 2023-12-26 | 国网天津市电力公司电力科学研究院 | Method and device for detecting internal short circuit fault of lithium ion energy storage power station battery |
| CN117289142B (en) * | 2023-11-24 | 2024-03-19 | 国网天津市电力公司电力科学研究院 | Method and device for detecting internal short circuit fault of lithium ion energy storage power station battery |
| CN117630679A (en) * | 2023-11-30 | 2024-03-01 | 湖北工业大学 | Battery fault diagnosis method and system |
| CN117783886A (en) * | 2024-02-23 | 2024-03-29 | 武汉船用电力推进装置研究所(中国船舶集团有限公司第七一二研究所) | Power battery abnormal state identification method and device, electronic equipment and storage medium |
| CN117783886B (en) * | 2024-02-23 | 2024-05-31 | 武汉船用电力推进装置研究所(中国船舶集团有限公司第七一二研究所) | Power battery abnormal state identification method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| James et al. | Intelligent time-adaptive transient stability assessment system | |
| CN116087787A (en) | Battery fault judging method and system based on principal component analysis method | |
| US20180046902A1 (en) | Enhanced restricted boltzmann machine with prognosibility regularization for prognostics and health assessment | |
| US20160239592A1 (en) | Data-driven battery aging model using statistical analysis and artificial intelligence | |
| Kim et al. | Impedance-based capacity estimation for lithium-ion batteries using generative adversarial network | |
| CN109740859A (en) | Transformer condition evaluation and system based on Principal Component Analysis and support vector machines | |
| WO2023184824A1 (en) | Method and system for estimating state of charge of battery cluster, electronic device, and storage medium | |
| Niu et al. | Lebesgue sampling based deep belief network for lithium-ion battery diagnosis and prognosis | |
| CN110570544A (en) | method, device, equipment and storage medium for identifying faults of aircraft fuel system | |
| WO2022143903A1 (en) | Safety evaluation method and system for vehicle battery, and device and readable storage medium | |
| CN113837596A (en) | Fault determination method and device, electronic equipment and storage medium | |
| Lyu et al. | RUL prediction of lithium-ion battery in early-cycle stage based on similar sample fusion under Lebesgue sampling framework | |
| Schwartz et al. | An unsupervised approach for health index building and for similarity-based remaining useful life estimation | |
| CN117407795A (en) | Battery safety prediction method and device, electronic equipment and storage medium | |
| CN115544803B (en) | Transformer residual life prediction method, device, equipment and storage medium | |
| CN116522594A (en) | Time self-adaptive transient stability prediction method and device based on convolutional neural network | |
| CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method | |
| US20220243347A1 (en) | Determination method and determination apparatus for conversion efficiency of hydrogen production by wind-solar hybrid electrolysis of water | |
| CN113933718B (en) | Retired battery capacity sorting method, retired battery capacity sorting device, retired battery capacity sorting equipment and storage medium | |
| CN115640542A (en) | Intelligent electric energy meter state evaluation method and evaluation device based on Bayesian theory | |
| Chen et al. | A data mining method for extracting key factors of distribution network reliability | |
| Hu et al. | Health factor analysis and remaining useful life prediction for batteries based on a cross-cycle health factor clustering framework | |
| CN117556331B (en) | AI-enhancement-based air compressor maintenance decision method and system | |
| CN115616437B (en) | Intelligent debugging control method and system for EPC special power supply | |
| CN116956197B (en) | Deep learning-based energy facility fault prediction method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |