Energy storage battery life prediction method, device, medium and product

Abstract

The present invention discloses a method, device, medium and product for predicting the life of an energy storage battery, and relates to the field of new energy. The method comprises: obtaining sampling data of each discharge process of multiple identical energy storage battery samples in the life cycle; constructing a sampling data matrix and extracting the characteristic vector of the sampling data matrix; taking the characteristic vector as input and the remaining number of discharges corresponding to the characteristic vector as output, determining the energy storage battery life prediction model; obtaining sampling data of the current discharge process of the target energy storage battery; inputting the characteristic vector corresponding to the sampling data of the current discharge process of the target energy storage battery into the energy storage battery life prediction model, obtaining the remaining number of discharges after the target energy storage battery completes the current discharge process, and taking the remaining number of discharges after the target energy storage battery completes the current discharge process as the life of the target energy storage battery. The present invention improves the accuracy of energy storage battery life prediction.

Description

Technical Field

[0001] The present invention relates to the field of new energy, and in particular to a method, device, medium and product for predicting the life of an energy storage battery. Background Art

[0002] As a core component of energy storage technology, energy storage batteries have broad market prospects and application potential. However, energy storage batteries also face problems and challenges such as cost, safety and cycle life. In the operation of energy storage stations, the cycle life of energy storage batteries directly affects their service life and economy, and also has a great impact on the overall operating benefits of energy storage stations.

[0003] At present, there are still many limiting factors in predicting the cycle life of energy storage batteries such as lithium-ion batteries. The battery replacement cost of energy storage stations is difficult to control, the operating efficiency is low, and the replacement and maintenance costs are high.

[0004] Among them, the remaining life of the energy storage battery refers to the number of cycles remaining when the battery capacity or energy decays to a certain specified value. It is affected by many factors such as the battery's charge and discharge power, charge and discharge depth, and ambient temperature. In the actual operation of the energy storage battery, mastering its remaining life can provide a basis for operation strategy optimization, system operation and maintenance, and economic evaluation. However, at present, both the energy storage battery management system and the monitoring system of the energy storage power station lack the corresponding remaining life prediction function. The research on the remaining life of the energy storage battery is still mainly in the laboratory. By conducting battery cycle experiments at fixed charge and discharge power and charge and discharge depth, the relationship between the battery capacity (energy) decay rate and the number of cycles is established, so as to predict the remaining life of the energy storage battery. However, in different application scenarios, the operating conditions of energy storage batteries vary greatly. Even in the same energy storage battery, the charge and discharge depth of the battery is constantly changing. At the same time, since the capacity (energy) decay of the energy storage battery is a nonlinear relationship with the charge and discharge depth, the current remaining life prediction model established in the laboratory with a fixed charge and discharge depth cannot meet the needs of engineering applications. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device, medium and product for predicting the life of an energy storage battery, which can improve the accuracy of predicting the life of an energy storage battery.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A method for predicting the life of an energy storage battery, comprising:

[0008] Obtain sampling data of each discharge process of multiple identical energy storage battery samples during their life cycle;

[0009] Constructing a sampling data matrix according to the sampling data and extracting a feature vector of the sampling data matrix;

[0010] Determine a life prediction model for an energy storage battery by taking the characteristic vector as input and the remaining number of discharges corresponding to the characteristic vector as output;

[0011] Obtain sampling data of the current discharge process of the target energy storage battery;

[0012] Calculate the characteristic vector corresponding to the sampling data of the current discharge process of the target energy storage battery, and input the corresponding characteristic vector into the energy storage battery life prediction model to obtain the remaining discharge times after the target energy storage battery completes the current discharge process, and use the remaining discharge times after the target energy storage battery completes the current discharge process as the life of the target energy storage battery.

[0013] Optionally, obtaining sampling data of each discharge process of a plurality of identical energy storage battery samples during their life cycle includes:

[0014] Acquire first sampling data of a first discharge process of a plurality of identical energy storage battery samples after leaving the factory;

[0015] Acquire second sampling data of a plurality of identical energy storage battery samples undergoing a second discharge process after completing a first discharge process and performing charging;

[0016] Obtaining Nth sampling data of a plurality of identical energy storage battery samples in an N+1th discharge process after completing an Nth discharge process and charging;

[0017] Determine whether the SOH value of each of the same energy storage battery samples after the N+1th discharge process is less than or equal to a preset life SOH value;

[0018] When the SOH value of the energy storage battery sample after the N+1th discharge process is less than or equal to the preset life SOH value, the corresponding number of discharges in the life cycle of the energy storage battery sample is N+1, and the first sampling data, the second sampling data, ..., the Nth sampling data are used as the sampling data;

[0019] When the SOH value of the energy storage battery sample after the N+1th discharge process is greater than the preset life SOH value, the discharge process after the energy storage battery sample is charged is calculated, and sampling data of the discharge process is obtained.

[0020] Optionally, constructing a sampling data matrix according to the sampling data and extracting a feature vector of the sampling data matrix specifically includes:

[0021] Discretize the sampling data of each discharge process of each energy storage battery sample to obtain discrete sampling data;

[0022] Determining the baseline sampling data of the energy storage battery sample according to the discrete sampling data;

[0023] Extracting sampling data of different parameters in a plurality of consecutive preset time periods from the reference sampling data in chronological order, and constructing a plurality of sampling data matrices;

[0024] Extract the eigenvectors of each of the sampled data matrices.

[0025] Optionally, determining the reference sampling data of the energy storage battery sample according to the discrete sampling data includes:

[0026] Obtaining discrete sampling data of each parameter at each moment, and obtaining first discrete data of each parameter at each moment;

[0027] According to the distance relationship between each discrete data in the first discrete data, the target sampling data at each moment is determined from the first discrete data; the sum of the distances between the target sampling data and the discrete data in the first discrete data other than the target sampling data is the smallest;

[0028] According to the target sampling data of each parameter at each moment, the baseline sampling data of the energy storage battery sample is determined.

[0029] Optionally, extracting the characteristic vector of each of the sampling data matrices includes:

[0030] Normalizing each of the sampling data matrices;

[0031] Calculating the covariance matrix of the normalized sampled data matrix;

[0032] A singular value decomposition algorithm is applied to the covariance matrix to obtain the eigenvectors of each of the sampling data matrices.

[0033] Optionally, the determining of the energy storage battery life prediction model using the feature vector as input and the remaining number of discharges corresponding to the feature vector as output includes:

[0034] The neural network model is trained with the feature vector as input and the remaining number of discharges corresponding to the feature vector as output to obtain a life prediction model for an energy storage battery.

[0035] Optionally, the neural network model is trained with the feature vector as input and the remaining number of discharges corresponding to the feature vector as output to obtain the energy storage battery life prediction model, including:

[0036] Applying InfoGAN to convert the feature vector into a feature image;

[0037] The characteristic image is used as input, and the remaining number of discharges corresponding to the characteristic vector is used as output, so as to train the neural network model and obtain a life prediction model for the energy storage battery.

[0038] A computer device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-mentioned energy storage battery life prediction methods.

[0039] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements any of the above-mentioned energy storage battery life prediction methods.

[0040] A computer program product comprises a computer program, which, when executed by a processor, implements any of the above-mentioned energy storage battery life prediction methods.

[0041] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0042] The present invention discloses a method, device, medium and product for predicting the life of an energy storage battery. The method obtains the sampling data of each discharge process of multiple identical energy storage battery samples in the life cycle, extracts the characteristic vector of each sampling data, takes the characteristic vector as input, and takes the remaining number of discharges corresponding to the characteristic vector as output to determine the energy storage battery life prediction model; then the sampling data of the current discharge process of the target energy storage battery obtained is input into the energy storage battery life prediction model to obtain the remaining number of discharges after the target energy storage battery completes the current discharge process, and obtains the life of the target energy storage battery. The present invention constructs an energy storage battery life prediction model by obtaining the relationship between the characteristic vector of the sampling data of each discharge process of the energy storage battery sample in the life cycle and the remaining number of discharges after the discharge process, and then applies the energy storage battery life prediction model to determine the life of the target energy storage battery, thereby improving the accuracy of energy storage battery life prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. 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 paying creative work.

[0044] Figure 1 A schematic diagram of a process flow of a method for predicting the life of an energy storage battery provided in Example 1 of the present invention;

[0045] Figure 2 This is a diagram of the internal structure of a computer device. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] The purpose of the present invention is to provide a method, device, medium and product for predicting the life of an energy storage battery, aiming to improve the accuracy of predicting the life of an energy storage battery.

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0049] Example 1

[0050] like Figure 1 As shown, the energy storage battery life prediction method in this embodiment includes:

[0051] Step S1: Acquire sampling data of each discharge process of multiple identical energy storage battery samples during their life cycle.

[0052] S1 specifically includes:

[0053] Step S11: obtaining first sampling data of a plurality of identical energy storage battery samples during the first discharge process after leaving the factory.

[0054] Step S12: obtaining second sampling data of a plurality of identical energy storage battery samples that undergo a second discharge process after completing a first discharge process and being charged.

[0055] Step S13: Obtaining Nth sampling data of a plurality of identical energy storage battery samples after completing the Nth discharge process and performing the N+1th discharge process.

[0056] Step S14: determining whether the SOH value of each of the same energy storage battery samples after the N+1th discharge process is less than or equal to a preset life SOH value.

[0057] Step S15: When the SOH value of the energy storage battery sample after the N+1th discharge process is less than or equal to the preset life SOH value, the corresponding number of discharges in the life cycle of the energy storage battery sample is N+1, and the first sampling data, the second sampling data, ..., the Nth sampling data are used as the sampling data.

[0058] Step S16: When the SOH value of the energy storage battery sample after the N+1th discharge process is greater than the preset life SOH value, the discharge process of the energy storage battery sample after the charging process is calculated, and sampling data of the discharge process is obtained.

[0059] In practical applications, first sampling data of the first discharge process of multiple identical energy storage battery samples after leaving the factory is obtained, and then second sampling data of the second discharge process is obtained, and then the discharge process is continued until the SOH value after discharge is less than or equal to the preset life SOH value. It is considered that after the current discharge process is completed, the life of the energy storage battery sample is terminated. Before the life of the energy storage battery sample is terminated, each discharge sampling data of the energy storage battery sample is recorded, thereby obtaining sampling data of each discharge process of multiple identical energy storage battery samples during their life cycle.

[0060] Exemplarily, the parameters involved in the sampled data include voltage, current, temperature, SoC, and discharge rate, etc.

[0061] Step S2: constructing a sampling data matrix according to the sampling data and extracting a eigenvector of the sampling data matrix.

[0062] S2 specifically includes:

[0063] Step S21: discretize the sampling data of each discharge process of each energy storage battery sample to obtain discrete sampling data.

[0064] Exemplarily, the sampled data of each parameter in each discharge process of each energy storage battery sample is discretized, and Fourier transform can be used to obtain the Fourier spectrum of each parameter in each discharge process.

[0065] For example: Discrete Fourier spectrum sequence of current time series , temperature series , SOC sequence , discharge rate sequence , Discrete Fourier spectrum of voltage time series . Where n represents time, N represents the total time, represents the current time series component, is the voltage time series component.

[0066] Step S22: Determine the baseline sampling data of the energy storage battery sample according to the discrete sampling data.

[0067] S22 specifically includes:

[0068] Step S221: Obtain discrete sampling data of each parameter at each moment, and obtain first discrete data of each parameter at each moment.

[0069] In practical applications, in the case of multiple discharge processes, the time is counted from the moment of discharge start. In each discharge process, each parameter has a sampled data of the discharge process at each moment. In the case of multiple discharge processes, each parameter has multiple discrete sampled data at each discharge moment. Each discharge moment refers to the energy storage battery sample from the moment of discharge start, every moment of the entire discharge process.

[0070] Step S222: determining target sampling data at each moment from the first discrete data according to the distance relationship between each discrete data in the first discrete data; the sum of the distances between the target sampling data and the discrete data in the first discrete data other than the target sampling data is the smallest.

[0071] In practical applications, the discrete sampling data corresponding to the sampling data of each discharge process of each energy storage battery sample is divided according to each moment to obtain the discrete sampling data at each moment; the distance between each discrete sampling data and other discrete sampling data in the discrete sampling data at each moment is calculated, and the target collection data at each moment is determined according to the principle of minimum distance value, thereby determining the target sampling data of each parameter at each moment.

[0072] Exemplarily, the distance may be calculated using Euclidean distance or Mahalanobis distance.

[0073] Taking Euclidean distance as an example, the distance calculation formula is:

[0074]

[0075] in, is the coordinate of one of the discrete sampling data in the x direction; is the coordinate of one of the discrete sampling data in the y direction; is the coordinate of another discrete sampling data in the x direction; is the coordinate of another discrete sampling data in the y direction; d is the distance between one discrete sampling data and another discrete sampling data.

[0076] Exemplarily, discrete sampling data of each discharge process of each energy storage battery sample is obtained respectively, and then divided into discrete sampling data after the first discharge, discrete sampling data after the second discharge, ..., discrete sampling data after the Nth discharge, where N is the total number of discharge processes in the life cycle.

[0077] Furthermore, the first target sampling data is calculated using the discrete sampling number of the first discharge process; the second target sampling data is calculated using the discrete sampling numbers of the first and second times, ..., the N-1th target sampling data is calculated using the discrete sampling numbers of the first, second, ..., N-1th times, and the Nth target sampling data is calculated using the discrete sampling numbers of the first, second, ..., N-1th times and the Nth time, to obtain the target sampling data of each parameter at each moment.

[0078] Step S223: Determine the baseline sampling data of the energy storage battery sample according to the target sampling data of each parameter at each moment.

[0079] In practical applications, the target sampling data at each moment of the energy storage battery discharge process is determined according to the target sampling data of each parameter at each moment.

[0080] Step S23: extracting sampling data of different parameters in a plurality of consecutive preset time periods from the reference sampling data in chronological order, and constructing a plurality of sampling data matrices.

[0081] In practical applications, a time period is preset, and the sampling data of different parameters in the benchmark sampling data are divided according to the preset time period to obtain multiple time periods after division. The divided time periods can be overlapping time periods or non-overlapping time periods. The divided time periods are sorted and connected in chronological order to obtain the discharge process of the parameter.

[0082] For example, if the number of data contained in each constructed time period is five, the obtained sampling data matrix is ​​in the form of:

[0083] .

[0084] Step S24: extracting the characteristic vectors of each of the sampling data matrices.

[0085] S24 includes:

[0086] Step S241: normalizing each of the sampling data matrices.

[0087] Step S242: Calculate the covariance matrix of the normalized sampling data matrix.

[0088] Step S243: applying a singular value decomposition algorithm to the covariance matrix to obtain eigenvectors of each of the sampling data matrices.

[0089] In practical applications, according to the needs of actual conditions, after the sampling data matrix is ​​normalized, the dimension of the normalized sampling data matrix is ​​reduced to improve the calculation rate.

[0090] Exemplarily, the normalized sampled data matrix is ​​reduced in dimension by applying the principal component analysis method, which can remove less important components while retaining the characteristics of the principal components, highlighting the characteristics of the data, so that a more accurate feature vector can be extracted in subsequent steps.

[0091] For example:

[0092] The mean of all data in the normalized sampling data matrix is ​​subtracted from all data in the normalized sampling data matrix, so that the distribution of all data in the normalized sampling data matrix does not change, but the coordinate axes of all data in the normalized sampling data matrix are moved.

[0093] At this time, the tolerance formula is:

[0094]

[0095] Among them, m is the number of all data in the normalized sampling data matrix, is the i-th data in the normalized sampling data matrix, is the mean of all data in the normalized sampling data matrix; is the tolerance of all data in the normalized sampled data matrix.

[0096] Find the unit vector ω with the largest variance after mapping all the data in the normalized sampled data matrix.

[0097] The specific process is:

[0098] Map all data in the normalized sampled data matrix to the defined axis , so that the mapping to the axis The variance after is the largest.

[0099] Therefore, the objectives of principal component analysis are: The value of is the largest.

[0100] Solving for the variance, we get , which is the principal component.

[0101] Step S3: Determine a life prediction model for an energy storage battery by taking the feature vector as input and the remaining number of discharges corresponding to the feature vector as output.

[0102] S3 specifically includes:

[0103] The neural network model is trained with the feature vector as input and the remaining number of discharges corresponding to the feature vector as output to obtain a life prediction model for an energy storage battery.

[0104] Furthermore, InfoGAN is applied to convert the feature vector into a feature image. The feature image is used as input, and the remaining number of discharges corresponding to the feature vector is used as output to train a neural network model to obtain a life prediction model for an energy storage battery.

[0105] Exemplarily, the neural network model may be a RNN neural network model.

[0106] Since the eigenvector is the eigenvector of the sampling data matrix, and the sampling data matrix is ​​a sampling data matrix composed of target sampling data in a preset time period, the remaining number of discharges corresponding to the eigenvector as output refers to the number of discharges from which the current eigenvector is obtained. According to the total number of discharges in the life cycle, the remaining number of discharges can be obtained.

[0107] Step S4: Acquire sampling data of the current discharge process of the target energy storage battery.

[0108] Step S5: Calculate the characteristic vector corresponding to the sampling data of the current discharge process of the target energy storage battery, and input the corresponding characteristic vector into the energy storage battery life prediction model to obtain the remaining discharge times after the target energy storage battery completes the current discharge process, and use the remaining discharge times after the target energy storage battery completes the current discharge process as the life of the target energy storage battery.

[0109] When calculating the characteristic vector corresponding to the sampling data of the current discharge process of the target energy storage battery, the discrete sampling data of the sampling data of each parameter at each time is calculated respectively, and then the target sampling data of the discrete sampling data of each parameter at each time is calculated, and then the sampling data matrix is ​​constructed according to the target sampling data, and then the characteristic vector is extracted.

[0110] Among them, the target energy storage battery is an energy storage battery that is the same as the energy storage battery sample.

[0111] Example 2

[0112] A computer device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the energy storage battery life prediction method in Example 1.

[0113] Example 3

[0114] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the energy storage battery life prediction method in Example 1.

[0115] Example 4

[0116] A computer program product includes a computer program, which implements the energy storage battery life prediction method in Example 1 when executed by a processor.

[0117] Example 5

[0118] A computer device, which may be a database, may have an internal structure as shown in Figure 2 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store pending transactions. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the energy storage battery life prediction method in Example 1 is implemented.

[0119] It should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0120] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided by the present invention may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided by the present invention may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0121] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0122] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for predicting the life of an energy storage battery, characterized in that: The method comprises: Obtain sampling data of each discharge process of multiple identical energy storage battery samples during their life cycle; Constructing a sampling data matrix according to the sampling data and extracting the characteristic vector of the sampling data matrix; specifically comprising: discretizing the sampling data of each discharge process of each energy storage battery sample to obtain discrete sampling data; determining the baseline sampling data of the energy storage battery sample according to the discrete sampling data; extracting the sampling data of different parameters in a plurality of consecutive preset time periods from the baseline sampling data in chronological order to construct a plurality of sampling data matrices; extracting the characteristic vector of each sampling data matrix; Determine a life prediction model for an energy storage battery by taking the characteristic vector as input and the remaining number of discharges corresponding to the characteristic vector as output; Obtain sampling data of the current discharge process of the target energy storage battery; Calculate the characteristic vector corresponding to the sampling data of the current discharge process of the target energy storage battery, and input the corresponding characteristic vector into the energy storage battery life prediction model to obtain the remaining discharge times after the target energy storage battery completes the current discharge process, and use the remaining discharge times after the target energy storage battery completes the current discharge process as the life of the target energy storage battery; Determining the benchmark sampling data of the energy storage battery sample according to the discrete sampling data includes: Obtaining discrete sampling data of each parameter at each moment, and obtaining first discrete data of each parameter at each moment; According to the distance relationship between each discrete data in the first discrete data, the target sampling data at each moment is determined from the first discrete data; the sum of the distances between the target sampling data and the discrete data in the first discrete data other than the target sampling data is the smallest; According to the target sampling data of each parameter at each moment, the baseline sampling data of the energy storage battery sample is determined.

2. The energy storage battery life prediction method according to claim 1, characterized in that: The method of obtaining sampling data of each discharge process of a plurality of identical energy storage battery samples during their life cycle includes: Acquire first sampling data of a first discharge process of a plurality of identical energy storage battery samples after leaving the factory; Acquire second sampling data of a plurality of identical energy storage battery samples undergoing a second discharge process after completing a first discharge process and performing charging; Obtaining Nth sampling data of a plurality of identical energy storage battery samples in an N+1th discharge process after completing an Nth discharge process and charging; Determine whether the SOH value of each of the same energy storage battery samples after the N+1th discharge process is less than or equal to a preset life SOH value; When the SOH value of the energy storage battery sample after the N+1th discharge process is less than or equal to the preset life SOH value, the corresponding number of discharges in the life cycle of the energy storage battery sample is N+1, and the first sampling data, the second sampling data, ..., the Nth sampling data are used as the sampling data; When the SOH value of the energy storage battery sample after the N+1th discharge process is greater than the preset life SOH value, the discharge process after the energy storage battery sample is charged is calculated, and sampling data of the discharge process is obtained.

3. The energy storage battery life prediction method according to claim 1, characterized in that: The step of extracting the characteristic vectors of each of the sampled data matrices comprises: Normalizing each of the sampling data matrices; Calculating the covariance matrix of the normalized sampled data matrix; A singular value decomposition algorithm is applied to the covariance matrix to obtain the eigenvectors of each of the sampling data matrices.

4. The energy storage battery life prediction method according to claim 1, characterized in that: The method of determining the life prediction model of the energy storage battery by taking the characteristic vector as input and the remaining number of discharges corresponding to the characteristic vector as output includes: The neural network model is trained with the feature vector as input and the remaining number of discharges corresponding to the feature vector as output to obtain a life prediction model for an energy storage battery.

5. The energy storage battery life prediction method according to claim 4, characterized in that: The method uses the characteristic vector as input and the remaining number of discharges corresponding to the characteristic vector as output to train the neural network model to obtain the energy storage battery life prediction model, including: Applying InfoGAN to convert the feature vector into a feature image; The characteristic image is used as input, and the remaining number of discharges corresponding to the characteristic vector is used as output, so as to train the neural network model and obtain a life prediction model for the energy storage battery.

6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the energy storage battery life prediction method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the energy storage battery life prediction method described in any one of claims 1 to 5 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the energy storage battery life prediction method described in any one of claims 1 to 5 is implemented.

Images