Energy storage equipment state monitoring method and system

Abstract

The invention discloses an energy storage equipment state monitoring method and system, and relates to the field of energy storage equipment state monitoring, and the method comprises the steps: collecting energy storage equipment data, and carrying out the preprocessing; inputting a VMD algorithm for decomposition to obtain sequence-free data; as input data of a WOA algorithm, outputting classified data; performing comparative analysis by taking envelope entropy, permutation entropy and information entropy as fitness functions, and determining classified and ordered data; and comparing with historical data, calculating to obtain correlation data, and outputting upper and lower safety margins of the energy storage equipment data by using a Bayesian estimation algorithm. According to the method, the VMD parameters are optimized through the WOA, and the Bayesian estimation method is combined, so that the error of the energy storage equipment is accurately evaluated. And through feature selection and dimension reduction, the complexity of data analysis is reduced, and the calculation efficiency is improved. Potential fault risks can be found and early warned in time, and serious influence of energy storage system faults on a power system is avoided.

Description

Technical Field

[0001] The present invention relates to the field of state monitoring of energy storage equipment, and in particular to a method and system for monitoring the state of energy storage equipment. Background Art

[0002] In the prior art, traditional energy storage equipment status monitoring methods mainly rely on single sensor monitoring and data collection, and often only involve simple analysis of basic physical parameters such as current and voltage. The main drawback of this type of method is that it is unable to effectively process complex and dynamically changing equipment data, especially when there is noise interference in the equipment operating environment, traditional filtering technology is difficult to accurately separate useful signals. In addition, the classification algorithm of the traditional method is simple and fails to fully consider the multimodal information in the signal, resulting in the inability to accurately identify subtle changes in the equipment's operating status. Due to the lack of support for multimodal data decomposition and advanced algorithms, traditional monitoring methods have shown limitations in equipment status prediction and safety assessment, especially in the dynamic adjustment of safety margins. Therefore, the existing technology is difficult to meet the monitoring needs of energy storage equipment in modern complex application scenarios. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is: how to accurately process and analyze complex dynamic data containing noise interference during the operation of energy storage equipment, realize accurate monitoring of the status of energy storage equipment, and calculate its upper and lower safety margins through intelligent algorithms to ensure the reliability and safety of equipment operation.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for monitoring the state of an energy storage device, comprising the following steps:

[0006] Collect energy storage equipment data and pre-process it;

[0007] The preprocessed data is input into the VMD algorithm for decomposition to obtain unsequenced data;

[0008] Use unsequenced data as input data of WOA algorithm and output classified data;

[0009] By comparing and analyzing envelope entropy, permutation entropy and information entropy as fitness functions, classified and ordered data can be determined;

[0010] The classified and ordered data are compared with the historical data, the Pearson correlation coefficient is used to calculate the correlation data, and the upper and lower safety margins of the energy storage equipment data are output using the Bayesian estimation algorithm.

[0011] As a preferred solution of the energy storage device status monitoring method described in the present invention, wherein: the energy storage device data is collected by setting the sampling period and data volume according to the actual operating conditions of the device, and selecting the current signal from the protection measurement circuit of the energy storage electrical system as the sample data to be decomposed;

[0012] The preprocessing is to perform noise processing on the collected data, use a median filter to eliminate random spike interference, perform normalization processing, and standardize the current signal to a uniform value range.

[0013] As a preferred solution of the energy storage device state monitoring method of the present invention, wherein: the unsequenced data is the unsequenced data about the current signal obtained by inputting the preprocessed data into the VMD algorithm for decomposition;

[0014] The VMD constrained variational model can be expressed as:

[0015]

[0016] Among them, {u k}={u1,u2,…,u k} represents the k modal quantities after decomposition, {ω k}={ω1,ω2,…,ω k} represents the center frequency of each modal component, It represents the partial derivative with respect to t, f represents the original signal function, and δ(t) represents the Dirac function.

[0017] As a preferred solution of the energy storage device state monitoring method described in the present invention, the constraint condition of the VMD constrained variational model is to make the sum of all modal components equal to the original current signal x.

[0018] As a preferred solution of the energy storage device state monitoring method described in the present invention, wherein: the output ordered data is the unordered data obtained by decomposing the VMD algorithm, which is used as the input data of the WOA algorithm to calculate the classified data about the current signal;

[0019] Initialize the parameters of the WOA algorithm and set the whale population W = (W1, W2, ..., W i ,…W j )

[0020] Among them, W represents individual whales, j represents the number of whales, and i represents the i-th whale;

[0021] Update the whale's position. The whale uses a shrinking encirclement and then a bubble net to prey. The shrinking encirclement and bubble net predation can be expressed as:

[0022]

[0023] D=|W * (t)-W(t)|

[0024] Among them, t represents the current iteration number, W represents the current position of the population, and W * represents the optimal position of the population, A and D represent coefficients, the range of A is [-a, a], a is a natural number and decreases linearly from the maximum value to the minimum value, D* represents the distance between the i-th whale and its prey, and l is a random number between [-1, 1].

[0025] As a preferred solution of the energy storage device state monitoring method described in the present invention, wherein: the classified and ordered data is the classified data output by the WOA algorithm and compared with the historical data, and the comparison and analysis is performed using envelope entropy, permutation entropy and information entropy as fitness functions;

[0026] The fitness function value is calculated through three different envelopes, and the optimal data result is selected as classified and ordered data.

[0027] As a preferred solution of the energy storage device status monitoring method described in the present invention, the upper and lower safety margins of the energy storage device data are obtained by comparing the classified and ordered data with the original current signal of the energy storage system, and using the Pearson correlation coefficient to calculate the correlation data, and the expression is:

[0028]

[0029] Among them, cov(x,y) is the covariance of the original signal x and the component signal u, σ x , σ u are the standard deviations of x and y respectively;

[0030] When selecting the mode, the two-variable correlation coefficient ρ=(ρ1, ρ2,…, ρ k ) to determine the size and select the modal quantity Y=(Y1,Y2,…,Y l )(l≤k);

[0031] The Bayesian estimation method is used to evaluate the modal quantity Y, set the prior distribution parameters, select the normal distribution as the distribution law, obtain the prior distribution probability function value p(θ) of the parameter θ, and calculate the modal quantity Y=(Y1,Y2,…,Y l )’s normal distribution probability density function value p(Y);

[0032] The likelihood function is constructed based on the prior distribution probability function p(θ) and the normal distribution probability density function p(Y), and the prior distribution probability function value p(Y|θ) is output. The expression is:

[0033]

[0034] Among them, p(Y|θ) is the value of the likelihood function;

[0035] According to the posterior distribution, the current segment data is evaluated and judged, and the Bayesian estimate of the prior distribution parameter θ is solved. The expression is:

[0036] θ * =∫θ p (θ|Y set )dθ

[0037] Set the upper and lower margins of the energy storage system current error, and use the Bayesian estimate to calculate the corresponding error judgment threshold and load determination threshold The expression is:

[0038]

[0039] Among them, Y set To set the data-correlated modal quantity corresponding to the current error margin, It is a modal quantity strongly correlated with load current data.

[0040] Another object of the present invention is to provide an energy storage device status monitoring system, which can perform in-depth analysis and classification processing on the operating data of the energy storage device through the VMD decomposition algorithm, the WOA optimization algorithm and the entropy fitness analysis, and combine the comparison of historical data, and use the Pearson correlation coefficient and the Bayesian estimation method to accurately calculate the upper and lower safety margins of the equipment status, thereby solving the problems of insufficient noise interference processing, inaccurate signal classification and unreliable safety assessment in the prior art, and greatly improving the accuracy and safety of energy storage equipment status monitoring.

[0041] In order to solve the above technical problems, the present invention provides the following technical solutions: an energy storage device status monitoring system, comprising:

[0042] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned energy storage device status monitoring method when executing the computer program.

[0043] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the energy storage device status monitoring method as described above.

[0044] Beneficial effects of the present invention: The present invention optimizes VMD parameters through WOA and combines Bayesian estimation method to achieve accurate evaluation of energy storage device errors. Real-time data collection and processing are carried out to achieve online monitoring and rapid response of energy storage device status. Through feature selection and dimensionality reduction, the complexity of data analysis is reduced and the calculation efficiency is improved. Potential failure risks are discovered and warned in time to avoid serious impact of energy storage system failure on the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0046] Figure 1 An overall flow chart of the energy storage device status monitoring method provided by the first embodiment of the present invention;

[0047] Figure 2 The change of penalty factor values ​​of three fitness functions corresponding to three envelopes in the energy storage device state monitoring method provided by the first embodiment of the present invention;

[0048] Figure 3 Modal decomposition changes of three fitness functions corresponding to three envelopes in the energy storage device state monitoring method provided by the first embodiment of the present invention;

[0049] Figure 4 Current error data of a protection measurement loop in the energy storage device state monitoring method provided by the third embodiment of the present invention;

[0050] Figure 5 This is a diagram of error current evaluation results in the energy storage device state monitoring method provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0052] Example 1, reference Figure 1 In one embodiment of the present invention, a method for monitoring the state of an energy storage device is provided, comprising: Figure 1As shown, when processing the non-stationary and error-fluctuating current data collected by the protection measurement circuit in the energy storage electrical system, the present invention adopts the advanced method of variational mode decomposition (VMD). VMD, by virtue of its adaptability and non-recursiveness, can effectively decompose complex and nonlinear time series and convert them into multiple relatively stable subsequences with different frequency scales. The specific steps of applying VMD to process such current signals are:

[0053] First, historical current data x is selected from the protection measurement circuit of the energy storage electrical system as the sample data to be decomposed. These data contain errors and fluctuations, showing non-stationary characteristics.

[0054] In order to decompose the original current signal x into multiple modal components with center frequency and limited bandwidth, and ensure that these modal components can accurately reconstruct the original signal under certain conditions (such as the minimum sum of bandwidth), by minimizing the sum of the estimated bandwidths of each modal component, each modal component obtained by decomposition has a single frequency component and a smaller bandwidth as much as possible, thereby improving the accuracy and practicality of the decomposition and constructing a constrained variational model of VMD. The VMD constrained variational model can be expressed as:

[0055]

[0056] Where: {u k}={u1,u2,…,u k} represents the k modal quantities after decomposition; {ω k}={ω1,ω2,…,ω k} represents the center frequency of each modal component; represents the partial derivative with respect to t; f represents the original signal function; δ(t) represents the Dirac function. The constraint condition is to ensure that the sum of all modal components is equal to the original current signal x, that is, to keep the integrity of the signal intact.

[0057] It should be further explained that the VMD algorithm splits the collected current signal into non-sequential data, such as current amplitude data, current effective value data, current high-frequency signal data, current medium-frequency signal data, current low-frequency signal data, current maximum value data during the sampling time, current minimum value data during the sampling time, current average value data during the sampling time, current DC component data and other data.

[0058] The present invention adopts the whale optimization algorithm (WOA) to optimize the number of parameter modes k of VMD to improve the decomposition effect. The specific process is:

[0059] 1) Initialize the parameters of the WOA algorithm:

[0060] Assume the whale population W = (W1, W2, ..., W i ,…W j ).

[0061] Where: W represents the individual whale, j represents the number of whales, i represents the i-th whale, the number of decomposed modes k ranges from [2, 10], and the maximum number of iterations is 50.

[0062] 2) Update whale position:

[0063] The whales preyed with a bubble net after a contraction and encirclement. The contraction and encirclement and bubble net predation can be expressed as:

[0064]

[0065] Where: t represents the current number of iterations, W represents the current position of the population, and W * represents the optimal position of the population, A and D represent coefficients, the range of A is [-a, a], and a gradually decreases linearly from 2 to 0 during the iteration process; D = |W * (t)-W(t)|; D* represents the distance between the ith whale and its prey, and l is a random number between [-1, 1].

[0066] 3) Update the optimization results:

[0067] In the field of optimization, when WOA is used to optimize the model of the current signal x, envelope entropy, permutation entropy and information entropy are selected as fitness functions for comparative analysis. The signal x is used as input and multiple iterations are performed until the maximum number of iterations is reached. The characteristics of these three entropy metrics are used to guide the WOA algorithm to search for the optimal parameter set. The optimization results of the three fitness functions are shown in Table 1. The changes in parameter k during the iteration process are shown in Table 1. Figure 2 , Figure 3 shown.

[0068] Table 1 Optimization results of different fitness functions

[0069]

[0070] Depend on Figure 2 It can be seen that the penalty factor α values ​​of envelope entropy and permutation entropy can converge to 104 and 113 respectively, but the information entropy α value does not converge when it reaches the upper limit of 2000, so the information entropy is not applicable in the present invention; Figure 3 It can be seen that the envelope entropy decomposition mode k is the least, only 6, while the permutation entropy k requires 9. The envelope entropy can characterize the information of the original signal with fewer modes. Therefore, the present invention selects envelope entropy as the fitness function in WOA-VMD to perform modal decomposition and evaluation on subsequent online samples.

[0071] It should be further explained that the collected current signal can be decomposed into several data through the VMD algorithm. Through experiments, it is known that the envelope entropy decomposition mode k is the least, only 6, while the permutation entropy k requires 9. Therefore, in the present invention, 6 will be used as units to form a corresponding set of component signal data.

[0072] The original current signal x of the energy storage system is decomposed into the component signal data {u k}={u1,u2,…,u k} Expressed by Pearson correlation coefficient (PCC):

[0073]

[0074] Among them, cov(x,y) is the covariance of the original signal x and the component signal u, σ x , σ u are the standard deviations of x and y respectively.

[0075] When selecting the mode, the correlation coefficient of the two variables calculated previously should be ρ = (ρ1, ρ2, ..., ρ k ) is used to determine the correlation between the two variables. The correlation coefficients of the two variables are shown in Table 2.

[0076] Table 2 Correlation between two variables under different coefficients

[0077] Correlation coefficient Correlation between two variables 0.8-1 Very strong correlation 0.6-0.8 Strong correlation 0.4-0.6 Moderately related 0.2-0.4 Weak correlation 0-0.2 Very weak or no correlation

[0078] Among them, 0.6 is the minimum value of the coefficient in the strong correlation, so the present invention sets 0.6 as the minimum selection threshold. After judging the correlation coefficient threshold, the strongly correlated modal quantity Y=(Y1, Y2, ..., Y l )(l≤k).

[0079] In order to calculate the modal quantity Y=(Y1,Y2,…,Y l ) for accurate evaluation, the present invention adopts the Bayesian estimation method, the steps are:

[0080] 1) Set the prior distribution parameter as θ, select the normal distribution as its distribution law, obtain the prior distribution probability function value p(θ) of the parameter θ, and calculate the modal quantity Y=(Y1,Y2,…,Y l ) is the normal distribution probability density function value p(Y).

[0081] 2) Construct the likelihood function based on the prior distribution probability function p(θ) and the normal distribution probability density function p(Y). Select a suitable distribution as its distribution law and obtain the prior distribution probability function value p(Y|θ) of the parameter, which can be expressed as:

[0082]

[0083] Where: p(Y|θ) is the value of the likelihood function.

[0084] 3) According to the posterior distribution, the data in this section is evaluated and judged, and the Bayesian estimate of the test distribution parameter θ is solved, which can be expressed as:

[0085] θ * =∫θp(θ|Y set )dθ (5)

[0087] Set the upper and lower margins of the energy storage system current error, and use the Bayesian estimate to calculate the corresponding error judgment threshold and load determination threshold The expression is:

[0088]

[0089] Among them, Y set To set the data-correlated modal quantity corresponding to the current error margin, It is a modal quantity strongly correlated with load current data.

[0090] Embodiment 2 is an embodiment of the present invention, which provides a system for monitoring the state of an energy storage device, including: a data acquisition and preprocessing module, a VMD algorithm module, a WOA algorithm module, an entropy fitness analysis module, and a correlation calculation and Bayesian estimation module;

[0091] The data acquisition and preprocessing module sets the sampling period and data volume according to the actual operating conditions of the equipment, selects the current signal from the protection measurement circuit of the energy storage electrical system as the sample data to be decomposed, and performs denoising and normalization preprocessing;

[0092] The VMD algorithm module decomposes the preprocessed data to obtain non-sequential current signal data;

[0093] The equipment control module sends control instructions to the new energy equipment based on the calculation results of the control algorithm module, so that the equipment can operate according to the optimized strategy;

[0094] The WOA algorithm module receives the unsequenced data decomposed by the VMD algorithm as input, processes it through the whale optimization algorithm, and outputs classified data;

[0095] The entropy fitness analysis module uses envelope entropy, permutation entropy and information entropy as fitness functions to compare and analyze the data output by the WOA algorithm, and selects the optimal classification result by calculating the entropy value;

[0096] The correlation calculation and Bayesian estimation module calculates the correlation of data through the Pearson correlation coefficient and uses the Bayesian estimation method to output the upper and lower safety margins of the energy storage device status.

[0097] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0098] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0099] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0100] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0101] Example 3, reference Figure 4-5 This is another embodiment of the present invention. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments. This embodiment experiments the existing traditional method and the method of this embodiment respectively.

[0102] The case data of the present invention comes from a 100MW / 100MWh lithium iron phosphate battery energy storage power station, and the CT measurement device n=1000 data are collected as a sample. In order to verify the accuracy of the method of the present invention in the error state assessment of the protection measurement loop, this case adds 5% random error to the 500th to 1000th sample interval. Figure 4 shown.

[0103] The corresponding Bayesian estimation 2% error threshold is calculated to be 1.165. For the previously extracted feature quantities, 20 groups of sample data are used as a window to calculate the Bayesian estimation value within a window. The results of 50 groups of windows are as follows: Figure 5 As shown, under normal circumstances, the calculated Bayesian estimation value does not exceed the threshold; when the current error exceeds 2%, the calculated result is higher than the threshold.

[0104] Reference Figure 5is the evaluation result of the window data with a time length of 20. When exploring the relationship between the accuracy of the error current data evaluation of the method of the present invention and the selected window length, the Bayesian estimation method, as a reasoning framework based on probability statistics, shows its superiority in processing large data sets with uncertainty and complexity. This method allows accurate inference of unknown parameters (such as the true distribution or characteristics of the error current) under the condition of given observed data (i.e., the error current data in the window).

[0105] From the perspective of big data processing, as the window length increases, that is, the amount of observed data increases, Bayesian estimation can make better use of this information to construct a more sophisticated posterior distribution. As a new understanding of unknown parameters, the accuracy of the posterior distribution is significantly improved because more data points help to more comprehensively capture the inherent laws and characteristics of the error current data. Therefore, when the window length is 100, the evaluation accuracy reaches 100%, indicating that a large amount of data plays a significant role in improving the accuracy of Bayesian estimation.

[0106] On the other hand, when the window length is shortened to 10, although the evaluation accuracy remains at a high level (98%), this also reveals the impact of reduced data volume on estimation accuracy. Although the Bayesian method itself has a certain degree of robustness and can make reasonable inferences under limited data, the lack of data will still increase the uncertainty of the estimation results.

[0107] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for monitoring the state of an energy storage device, characterized in that: include: Collect energy storage equipment data and pre-process it; The preprocessed data is input into the VMD algorithm for decomposition to obtain unsequenced data; Use unsequenced data as input data of WOA algorithm and output classified data; By comparing and analyzing envelope entropy, permutation entropy and information entropy as fitness functions, classified and ordered data can be determined; The classified and ordered data are compared with the historical data, the Pearson correlation coefficient is used to calculate the correlation data, and the upper and lower safety margins of the energy storage equipment data are output using the Bayesian estimation algorithm.

2. The energy storage device status monitoring method according to claim 1, characterized in that: The energy storage device data is collected by setting the sampling period and data volume according to the actual operating conditions of the device, and selecting the current signal from the protection measurement circuit of the energy storage electrical system as the sample data to be decomposed; The preprocessing is to perform noise processing on the collected data, use a median filter to eliminate random spike interference, perform normalization processing, and standardize the current signal to a uniform value range.

3. The energy storage device status monitoring method according to claim 2, characterized in that: The non-sequential data is obtained by inputting the pre-processed data into the VMD algorithm for decomposition, and is non-sequential data about the current signal; The VMD constrained variational model can be expressed as: Among them, {u k }={u1,u2,…,u k } represents the k modal quantities after decomposition, {ω k }={ω1,ω2,…,ω k } represents the center frequency of each modal component, It represents the partial derivative with respect to t, f represents the original signal function, and δ(t) represents the Dirac function.

4. The energy storage device status monitoring method according to claim 3, characterized in that: The constraint condition of the VMD constrained variational model is to make the sum of all modal components equal to the original current signal x.

5. The method for monitoring the state of an energy storage device according to claim 4, characterized in that: The output ordered data is the unordered data obtained by decomposing the VMD algorithm, and is used as the input data of the WOA algorithm to calculate the classified data about the current signal; Initialize the parameters of the WOA algorithm and set the whale population W = (W1, W2, ..., W i ,…W j ) Among them, W represents individual whales, j represents the number of whales, and i represents the i-th whale; Update the whale's position. The whale uses a shrinking encirclement and then a bubble net to prey. The shrinking encirclement and bubble net predation can be expressed as: D=|W * (t)-W(t)| Among them, t represents the current iteration number, W represents the current position of the population, and W * represents the optimal position of the population, A and D represent coefficients, the range of A is [-a, a], a is a natural number and decreases linearly from the maximum value to the minimum value, D* represents the distance between the i-th whale and its prey, and l is a random number between [-1, 1].

6. The energy storage device status monitoring method according to claim 5, characterized in that: The classified and ordered data is the classified data output by the WOA algorithm, which is compared with the historical data, and the comparison and analysis is performed using envelope entropy, permutation entropy and information entropy as fitness functions; The fitness function value is calculated through three different envelopes, and the optimal data result is selected as classified and ordered data.

7. The method for monitoring the state of an energy storage device according to claim 6, characterized in that: The upper and lower safety margins of the energy storage device data are obtained by comparing the classified and ordered data with the original current signal of the energy storage system, and using the Pearson correlation coefficient to calculate the correlation data, which is expressed as: Among them, cov(x,y) is the covariance of the original signal x and the component signal u, σ x , σ u are the standard deviations of x and y respectively; When selecting the mode, the correlation coefficient of the two variables ρ = (ρ1, ρ2, ..., ρ k ) to determine the size and select the modal quantity Y=(Y1,Y2,…,Y l )(l≤k); The Bayesian estimation method is used to evaluate the modal quantity Y, set the prior distribution parameters, select the normal distribution as the distribution law, obtain the prior distribution probability function value p(θ) of the parameter θ, and calculate the modal quantity Y=(Y1,Y2,…,Y l )’s normal distribution probability density function value p(Y); The likelihood function is constructed based on the prior distribution probability function p(θ) and the normal distribution probability density function p(Y), and the prior distribution probability function value p(Y|θ) is output. The expression is: Among them, p(Y|θ) is the value of the likelihood function; According to the posterior distribution, the current segment data is evaluated and judged, and the Bayesian estimate of the prior distribution parameter θ is solved. The expression is: i * =∫θp(θ|Y set )dθ Set the upper and lower margins of the energy storage system current error, and use the Bayesian estimate to calculate the corresponding error judgment threshold and load determination threshold The expression is: Among them, Y set To set the data-correlated modal quantity corresponding to the current error margin, It is a modal quantity strongly correlated with load current data.

8. A system using the energy storage device status monitoring method according to any one of claims 1 to 7, characterized in that: It includes data acquisition and preprocessing module, VMD algorithm module, WOA algorithm module, entropy fitness analysis module, and correlation calculation and Bayesian estimation module; The data acquisition and preprocessing module sets the sampling period and data volume according to the actual operating conditions of the equipment, selects the current signal from the protection measurement circuit of the energy storage electrical system as the sample data to be decomposed, and performs denoising and normalization preprocessing; The VMD algorithm module decomposes the preprocessed data to obtain non-sequential current signal data; The device control module sends control instructions to the new energy device according to the calculation results of the control algorithm module, so that the device operates according to the optimized strategy; The WOA algorithm module receives the unsequenced data decomposed by the VMD algorithm as input, processes it through the whale optimization algorithm, and outputs classified data; The entropy fitness analysis module uses envelope entropy, permutation entropy and information entropy as fitness functions to compare and analyze the data output by the WOA algorithm, and selects the optimal classification result by calculating the entropy value; The correlation calculation and Bayesian estimation module calculates the correlation of data through the Pearson correlation coefficient, and uses the Bayesian estimation method to output the upper and lower safety margins of the energy storage device state.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the energy storage device status monitoring method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the energy storage device status monitoring method described in any one of claims 1 to 7 are implemented.

Images