A lithium battery remaining life prediction system and method based on EIS

Through the remaining life prediction system of lithium battery based on EIS, the Gaussian model is used to predict the EIS, temperature and charge state data of lithium battery, which solves the problem of poor life prediction effect of lithium battery in the prior art, and achieves a more accurate life Prediction and information storage.

CN112748351BActive Publication Date: 2024-11-26NO 27 RES INST CHINA ELECTRONICS TECH GRP
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202011612981.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-29
Publication Date
2024-11-26
Estimated Expiration
2040-12-29

AI Technical Summary

Technical Problem

The existing lithium battery residual life prediction system depends on the micro-aging mechanism, making it difficult to achieve good prediction results and lacks scalability.

Method used

Adopt the remaining life prediction system of lithium battery based on EIS, including a state acquisition module, performance analysis module, status monitoring module and information storage module. By collecting the EIS, temperature and charge state data of lithium battery, the training set and test set are established using the Gaussian model. , make remaining life prediction.

Benefits of technology

It achieves a better prediction effect of the remaining life of lithium batteries, can accurately calculate and store the remaining life information of the lithium battery, and improves the accuracy and scalability of the prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112748351B_ABST
    Figure CN112748351B_ABST
Patent Text Reader

Abstract

The present invention provides a lithium battery remaining life prediction system and method based on EIS, comprising a state acquisition module, a performance analysis module, a state monitoring module and an information storage module; the prediction system of the present invention can use the state acquisition module to collect the charge state and EIS data of the lithium battery at different temperatures, and the performance analysis module predicts the remaining life of the lithium battery based on this, and can calculate and store the remaining life information of the lithium battery on the state monitoring module and the information storage module respectively; the prediction method adopts a Gaussian model, uses historical data to establish a training set and a test set, and uses the charge state and EIS data at different temperatures to predict the remaining life of the lithium battery, which can achieve better prediction results.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of lithium batteries, and in particular to a system and method for predicting the remaining life of a lithium battery based on EIS. Background Art

[0002] Lithium batteries have become an indispensable part of modern life due to their high energy and power density performance.

[0003] A key obstacle limiting the further development of lithium-ion battery technology is the unpredictability of battery aging: it is particularly important to accurately predict the battery state of health (SoH) and remaining useful life (RUL) to inform users whether to replace the battery or avoid unexpected capacity decay.

[0004] Traditional battery prediction methods rely on modeling of microscopic aging mechanisms (such as SEI film growth, lithium plating and active mass loss, etc.), but characterizing and simulating each aging mechanism is not scalable. Currently, the more commonly used method is to use a data-driven approach for modeling and analysis, that is, to perform non-destructive measurements while the battery is running, and then directly use statistical machine learning methods to correlate the measurement results with battery health. This method generally cannot achieve good prediction results due to the difficulty of selecting data features. Summary of the invention

[0005] The purpose of the present invention is to provide a lithium battery remaining life prediction system and method based on EIS, which is used to solve the problem that the existing lithium battery remaining life prediction system relies on the microscopic aging mechanism and cannot achieve a good prediction effect.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A lithium battery remaining life prediction system based on EIS, including a state acquisition module, a performance analysis module, a state monitoring module and an information storage module;

[0008] The state acquisition module is used to collect EIS, temperature and charge state of the lithium battery;

[0009] The performance analysis module is used to predict the remaining life of the lithium battery based on the collected EIS data at different temperatures and charge states;

[0010] The state monitoring module is used to display the remaining life prediction information of the lithium battery sent by the performance analysis module;

[0011] The information storage module is used to store the EIS, temperature and charge state information of the lithium battery collected by the state collection module, and store the remaining life prediction information of the performance analysis module.

[0012] The state acquisition module includes a sensor unit, a data processing unit and a wireless transmission unit connected in sequence;

[0013] The sensor unit is used to collect EIS, temperature and charge state data of the lithium battery;

[0014] The data processing unit includes a PC104 data acquisition card and a PC104 mainboard. The PC104 data acquisition card is used to collect the EIS, temperature and charge state data of the lithium battery sent by the sensor. The PC104 mainboard runs a VxWork operating system for processing the EIS, temperature and charge state data of the lithium battery collected by the PC104 data acquisition card.

[0015] The wireless transmission unit is used to send the data processed by the PC104 mainboard to the performance analysis module through the TCP / IP protocol.

[0016] The PC104 mainboard and the PC104 data acquisition card are connected in a fastened stacking manner.

[0017] The performance analysis module includes a wireless receiving component, a wired communication component and a first industrial computer;

[0018] The wireless receiving component is used to communicate with the wireless transmission unit and receive the data sent by the status acquisition module and processed by the PC104 mainboard;

[0019] The wired communication component is used to connect the performance analysis module, the status monitoring module and the information storage module in communication;

[0020] The first industrial computer is used to predict the remaining life of the lithium battery based on the data received by the wireless receiving component and processed by the PC104 mainboard.

[0021] The state monitoring module includes a second industrial computer and a display;

[0022] The industrial computer is used to receive the status and remaining life prediction results of the lithium battery sent by the performance analysis module, and control the display to display.

[0023] The information storage module includes a first data server and a second data server. The first data server and the second data server are both integrated with a MySQL database. The first data server and the second data server are used for storage and backup, respectively.

[0024] A method for predicting the remaining life of a lithium battery based on EIS comprises the following steps:

[0025] Step 1: Collect EIS data of lithium batteries at different temperatures and charge states, and pre-process the data;

[0026] Step 2: Store and back up the EIS data of the lithium battery at different temperatures and charge states, and predict the remaining life of the lithium battery based on the above data, and store and back up the remaining life prediction information;

[0027] The method for predicting the remaining life of a lithium battery comprises the following steps:

[0028] Step 2.1: Establish a historical database, construct training samples, which are divided into training samples and test samples, and predict the remaining life of lithium batteries; specifically: the historical database includes EIS data and remaining life prediction of lithium batteries at different temperatures and charge states, and the training samples are (x 1i , x 2i , x 3i ,y 1i ,y 2i ), i = 1, 2, 3, ..., n, represents the i-th group of training samples; x 1i is the temperature of the lithium battery, x 2i is the charge state of the lithium battery at the corresponding temperature, x 3i is the EIS data at the temperature corresponding to the lithium battery, y 1i For lithium batteries, x 1i , x 2i , x 3i Remaining battery life in status - unit: hours, y 2i For lithium batteries, x 1i , x 2i , x 3i Battery health status in state - unit health status percentage;

[0029] Step 2.2: Based on the historical database, establish a Gaussian model for predicting the remaining life of lithium batteries. Specifically:

[0030] For any integer N ≥ 1 and variable X, the joint probability distribution of the corresponding process state f(X) at time t obeys the N-dimensional Gaussian distribution, and the Gaussian model is: f(t) ~ GP[m(t), k(t, t′)]; where m(t) is the mean of the Gaussian model, and k(t, t′) is the covariance function of the Gaussian model;

[0031] For n training samples: D = {(x 1i , x 2i , x 3i ,y 1i ,y 2i)|i=1,2,...n}, can be simplified to the training set D=(X,y), where X is the d-dimensional input vector x 1i , x 2i , x 3i , if X represents a d×n-dimensional input matrix and y represents an h-dimensional output vector y 1i ,y 2i ;

[0032] The test sample is (X*, y*), that is, for a new input X*, the Gaussian model is used to predict the output value y* corresponding to X* based on the training sample, and the Gaussian model is tested; a test set (X*, y*) is constructed;

[0033] The standard linear regression model with Gaussian noise is:

[0034] y=f(X)+ε;

[0035] Where: f(X) is the regression function value, ε is an independent random variable that conforms to the Gaussian distribution, with a mean of m(t) = 0 and a variance of Right now:

[0036]

[0037] The prior distribution of y in the training set is:

[0038] y~N(0,K);

[0039] Where: K = K (X, X) is the n × n order symmetric positive definite covariance matrix, that is, the covariance matrix of the training set X itself;

[0040] Then the joint Gaussian prior distribution of the training set (X, y) and the test set (X*, y*) is:

[0041]

[0042] Among them, K(X,X * ) is the covariance matrix of the test set X* and the training set X, k(X * , X * ) is the covariance matrix of the test set X* itself;

[0043] The above covariance function uses the Matern covariance function:

[0044]

[0045] Among them, the hyperparameters l, σ in the Matern covariance function f , σ nThe optimal hyperparameters are adaptively obtained by the maximum likelihood method, that is, the logarithmic marginal likelihood function of the training set is established, the partial derivative of the hyperparameters is obtained, and the conjugate gradient optimization method is used to search for the optimal solution of the hyperparameters; the form of the logarithmic marginal likelihood function is:

[0046]

[0047] Then, according to the Bayesian principle, the most likely output value corresponding to X* is predicted based on the training set, that is, given the new input X*, the input value X of the training set, and the output value y of the training set, the most likely prediction distribution P(f * |x * , x, y):

[0048]

[0049] The mean and variance of the output value y* are

[0050]

[0051]

[0052] According to the mean of the output value y* of the training set Verify that if the average relative error of the output value y* is less than 1.5%, the optimal hyperparameters at this time meet the usage requirements;

[0053] Step 2.3: Using the Gaussian model established in step 2.2, the remaining life of the lithium battery is predicted through the real-time EIS data of the lithium battery at different temperatures and charge states.

[0054] Beneficial effects of the present invention:

[0055] The present invention discloses a lithium battery remaining life prediction system and method based on EIS. The prediction system includes a state acquisition module, a performance analysis module, a state monitoring module and an information storage module. The state acquisition module can collect the charge state and EIS data of the lithium battery at different temperatures. The performance analysis module predicts the remaining life of the lithium battery based on this, and can calculate and store the remaining life information of the lithium battery on the state monitoring module and the information storage module respectively. The prediction method adopts a Gaussian model, uses historical data to establish a training set and a test set, and uses the charge state and EIS data at different temperatures to predict the remaining life of the lithium battery, which can achieve better prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 It is a structural schematic diagram of the present invention;

[0058] Figure 2 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0059] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. 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.

[0060] like Figure 1 As shown: the present invention discloses a lithium battery remaining life prediction system based on EIS, comprising a state acquisition module, a performance analysis module, a state monitoring module and an information storage module; the state acquisition module is used to collect the EIS, temperature and charge state of the lithium battery; the performance analysis module is used to predict the remaining life of the lithium battery according to the collected EIS data at different temperatures and charge states; the state monitoring module is used to display the state and remaining life prediction information of the lithium battery sent by the performance analysis module; the information storage module is used to store the EIS, temperature and charge state information of the lithium battery collected by the state acquisition module, and store the remaining life prediction information of the performance analysis module.

[0061] Preferably: the state acquisition module comprises a sensor unit, a data processing unit and a wireless transmission unit connected in sequence; the sensor unit is used to collect EIS, temperature and charge state data of the lithium battery; the data processing unit comprises a PC104 data acquisition card and a PC104 mainboard, the PC104 data acquisition card is used to collect the EIS, temperature and charge state data of the lithium battery sent by the sensor, the PC104 mainboard runs a VxWork operating system for processing the EIS, temperature and charge state data of the lithium battery collected by the PC104 data acquisition card; the wireless transmission unit is used to send the data processed by the PC104 mainboard to the performance analysis module through the TCP / IP protocol.

[0062] Preferably, the PC104 mainboard and the PC104 data acquisition card are connected in a fastened stacking manner.

[0063] Preferably: the performance analysis module includes a wireless receiving component, a wired communication component and a first industrial computer; the first industrial computer can be an industrial computer; the wireless receiving component is used to communicate with the wireless transmission unit, and receive the data sent by the status acquisition module and processed by the PC104 mainboard; the wired communication component is used to connect the performance analysis module, the status monitoring module and the information storage module; the first industrial computer is used to perform fault prediction and health management on the lithium battery according to the data received by the wireless receiving component and processed by the PC104 mainboard.

[0064] Preferably: the status monitoring module includes a second industrial computer and a display; the second industrial computer can be an industrial computer; the industrial computer is used to receive the status and remaining life prediction of the lithium battery sent by the performance analysis module, and control the display to display by means of graphics or the like.

[0065] Preferably: the information storage module includes a first data server and a second data server, both of which are integrated with a MySQL database, and the first data server and the second data server are used for storage and backup respectively; MySQL database is a relational database system, which has a distributed database management system with a client / server architecture, MySQL is fully applicable to various networks, and the database built with it can be accessed in any terminal in the local area network, therefore, data sharing can be achieved with other devices in the local area network, and it can serve as the data storage center of the whole system.

[0066] like Figure 2 As shown: A method for predicting the remaining life of a lithium battery based on EIS, comprising the following steps:

[0067] Step 1: Collect EIS data of lithium batteries at different temperatures and charge states, and pre-process the data;

[0068] Step 2: Store and back up the EIS data of the lithium battery at different temperatures and charge states, and predict the remaining life of the lithium battery based on the above data, and store and back up the remaining life prediction information;

[0069] The method for predicting the remaining life of a lithium battery comprises the following steps:

[0070] Step 2.1: Establish a historical database, construct training samples, which are divided into training samples and test samples, and predict the remaining life of lithium batteries; specifically: the historical database includes EIS data and remaining life prediction of lithium batteries at different temperatures and charge states, and the training samples are (x 1i , x 2i , x 3i ,y 1i ,y 2i ), i = 1, 2, 3, ..., n, represents the i-th group of training samples; x 1i is the temperature of the lithium battery, x 2i is the charge state of the lithium battery at the corresponding temperature, x 3i is the EIS data at the temperature corresponding to the lithium battery, y 1i For lithium batteries, x 1i , x 2i , x 3i Remaining battery life in status - unit: hours, y 2i For lithium batteries, x 1i , x 2i , x 3i Battery health status in state - unit health status percentage;

[0071] Step 2.2: Based on the historical database, establish a Gaussian model for predicting the remaining life of lithium batteries. Specifically:

[0072] For any integer N ≥ 1 and variable X, the joint probability distribution of the corresponding process state f(X) at time t obeys the N-dimensional Gaussian distribution, and the Gaussian model is: f(t) ~ GP[m(t), k(t, t′)]; where m(t) is the mean of the Gaussian model, and k(t, t′) is the covariance function of the Gaussian model;

[0073] For n training samples: D = {(x 1i , x 2i , x 3i ,y 1i ,y 2i )|i=1,2,...n}, can be simplified to the training set D=(X,y), where X is the d-dimensional input vector x 1i , x 2i , x 3i , if X represents a d×n-dimensional input matrix and y represents an h-dimensional output vector y 1i ,y 2i ;

[0074] The test sample is (X*, y*), that is, for a new input X*, the Gaussian model is used to predict the output value y* corresponding to X* based on the training sample, and the Gaussian model is tested; a test set (X*, y*) is constructed;

[0075] The standard linear regression model with Gaussian noise is:

[0076] y=f(X)+ε;

[0077] Where: f(X) is the regression function value, ε is an independent random variable that conforms to the Gaussian distribution, with a mean of m(t) = 0 and a variance of Right now:

[0078]

[0079] The prior distribution of y in the training set is:

[0080] y~N(0,K);

[0081] Where: K = K (X, X) is the n × n order symmetric positive definite covariance matrix, that is, the covariance matrix of the training set X itself;

[0082] Then the joint Gaussian prior distribution of the training set (X, y) and the test set (X*, y*) is:

[0083]

[0084] Among them, K(X,X * ) is the covariance matrix of the test set X* and the training set X, k(X * , X * ) is the covariance matrix of the test set X* itself;

[0085] The above covariance function uses the Matern covariance function:

[0086]

[0087] Among them, the hyperparameters l, σ in the Matern covariance function f , σ n The optimal hyperparameters are adaptively obtained by the maximum likelihood method, that is, the logarithmic marginal likelihood function of the training set is established, the partial derivative of the hyperparameters is obtained, and the conjugate gradient optimization method is used to search for the optimal solution of the hyperparameters; the form of the logarithmic marginal likelihood function is:

[0088]

[0089] Then, according to the Bayesian principle, the most likely output value corresponding to X* is predicted based on the training set, that is, given the new input X*, the input value X of the training set, and the output value y of the training set, the most likely prediction distribution P(f * |x * , x, y):

[0090]

[0091] The mean and variance of the output value y* are

[0092]

[0093]

[0094] According to the mean of the output value y* of the training set Verify that if the average relative error of the output value y* is less than 1.5%, the optimal hyperparameters at this time meet the usage requirements;

[0095] Step 2.3: Using the Gaussian model established in step 2.2, the remaining life of the lithium battery is predicted through the real-time EIS data of the lithium battery at different temperatures and charge states.

[0096] Compared with the prior art, the present invention has the following beneficial effects:

[0097] The present invention discloses a lithium battery remaining life prediction system and method based on EIS. The prediction system includes a state acquisition module, a performance analysis module, a state monitoring module and an information storage module. The state acquisition module can collect the charge state and EIS data of the lithium battery at different temperatures. The performance analysis module predicts the remaining life of the lithium battery based on this, and can calculate and store the remaining life information of the lithium battery on the state monitoring module and the information storage module respectively. The prediction method adopts a Gaussian model, uses historical data to establish a training set and a test set, and uses the charge state and EIS data at different temperatures to predict the remaining life of the lithium battery, which can achieve better prediction results.

[0098] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A lithium battery remaining life prediction system based on EIS, characterized by: It includes a status acquisition module, a performance analysis module, a status monitoring module and an information storage module; The state acquisition module is used to collect EIS, temperature and charge state of the lithium battery; The performance analysis module is used to predict the remaining life of the lithium battery based on the collected EIS data at different temperatures and charge states; The state monitoring module is used to display the remaining life prediction information of the lithium battery sent by the performance analysis module; The information storage module is used to store the EIS, temperature and charge state information of the lithium battery collected by the state acquisition module, and store the remaining life prediction information of the performance analysis module; The prediction steps are as follows: Step 1: Collect EIS data of lithium batteries at different temperatures and charge states, and pre-process the data; Step 2: Store and back up the EIS data of the lithium battery at different temperatures and charge states, and predict the remaining life of the lithium battery based on the above data, and store and back up the remaining life prediction information; The method for predicting the remaining life of a lithium battery comprises the following steps: Step 2.1: Establish a historical database, construct training samples, which are divided into training samples and test samples, and predict the remaining life of lithium batteries; specifically: the historical database includes EIS data and remaining life prediction of lithium batteries at different temperatures and charge states, and the training samples are (x 1i , x 2i , x 3i ,y 1i ,y 2i ), i = 1, 2, 3, ..., n, represents the i-th group of training samples; x 1i is the temperature of the lithium battery, x 2i is the charge state of the lithium battery at the corresponding temperature, x 3i is the EIS data at the temperature corresponding to the lithium battery, y 1i For lithium batteries, x 1i , x 2i , x 3i Remaining battery life in status - unit: hours, y 2i For lithium batteries, x 1i , x 2i , x 3i Battery health status in state - unit health status percentage; Step 2.2: Based on the historical database, establish a Gaussian model for predicting the remaining life of lithium batteries. Specifically: For any integer N ≥ 1 and variable X, the joint probability distribution of the corresponding process state f(X) at time t follows an N-dimensional Gaussian distribution, and the Gaussian model is: f(t)~GP[m(t),k(t,t ′ )]; where m(t) is the mean of the Gaussian model, k(t,t ′ ) is the covariance function of the Gaussian model; For n training samples: D = {(x 1i , x 2i , x 3i ,y 1i ,y 2i )|i=1,2,…n}, can be simplified to the training set D=(X,y), where X is the d-dimensional input vector x 1i , x 2i , x 3i , if X represents a d×n-dimensional input matrix, y represents an h-dimensional output vector y1 i ,y 2i ; The test sample is (X*, y*), that is, for a new input X*, the Gaussian model is used to predict the output value y* corresponding to X* based on the training sample, and the Gaussian model is tested; a test set (X*, y*) is constructed; The standard linear regression model with Gaussian noise is: y=f(X)+ε; Where: f(X) is the regression function value, ε is an independent random variable that conforms to the Gaussian distribution, with a mean of m(t) = 0 and a variance of Right now: The prior distribution of y in the training set is: y~N(0,K); Where: K = K (X, X) is the n × n order symmetric positive definite covariance matrix, that is, the covariance matrix of the training set X itself; Then the joint Gaussian prior distribution of the training set (X, y) and the test set (X*, y*) is: Among them, K(X,X * ) is the covariance matrix of the test set X* and the training set X, k(X * , X * ) is the covariance matrix of the test set X* itself; The above covariance function uses the Matern covariance function: Among them, the hyperparameters in the Matern covariance function are 1, σ f , σ n The optimal hyperparameters are adaptively obtained by the maximum likelihood method, that is, the logarithmic marginal likelihood function of the training set is established, the partial derivative of the hyperparameters is obtained, and the conjugate gradient optimization method is used to search for the optimal solution of the hyperparameters; the form of the logarithmic marginal likelihood function is: Then, according to the Bayesian principle, the most likely output value corresponding to X* is predicted based on the training set, that is, given the new input X*, the input value X of the training set, and the output value y of the training set, the most likely prediction distribution P(f*|x*, X, y) of the output value y* is inferred: The mean and variance of the output value y* are According to the mean of the output value y* of the training set Verify that if the average relative error of the output value y* is less than 1.5%, the optimal hyperparameters at this time meet the usage requirements; Step 2.3: Using the Gaussian model established in step 2.2, the remaining life of the lithium battery is predicted through the real-time EIS data of the lithium battery at different temperatures and charge states.

2. The EIS-based lithium battery remaining life prediction system according to claim 1, characterized in that: The state acquisition module includes a sensor unit, a data processing unit and a wireless transmission unit connected in sequence; The sensor unit is used to collect EIS, temperature and charge state data of the lithium battery; The data processing unit includes a PC104 data acquisition card and a PC104 mainboard. The PC104 data acquisition card is used to collect the EIS, temperature and charge state data of the lithium battery sent by the sensor. The PC104 mainboard runs a VxWork operating system for processing the EIS, temperature and charge state data of the lithium battery collected by the PC104 data acquisition card. The wireless transmission unit is used to send the data processed by the PC104 mainboard to the performance analysis module through the TCP / IP protocol.

3. The EIS-based lithium battery remaining life prediction system according to claim 2, characterized in that: The PC104 mainboard and the PC104 data acquisition card are connected in a fastened stacking manner.

4. The EIS-based lithium battery remaining life prediction system according to claim 3, characterized in that: The performance analysis module includes a wireless receiving component, a wired communication component and a first industrial computer; The wireless receiving component is used to communicate with the wireless transmission unit and receive the data sent by the status acquisition module and processed by the PC104 mainboard; The wired communication component is used to connect the performance analysis module, the status monitoring module and the information storage module in communication; The first industrial computer is used to predict the remaining life of the lithium battery based on the data received by the wireless receiving component and processed by the PC104 mainboard.

5. The EIS-based lithium battery remaining life prediction system according to claim 1, characterized in that: The state monitoring module includes a second industrial computer and a display; The industrial computer is used to receive the status and remaining life prediction results of the lithium battery sent by the performance analysis module, and control the display to display.

6. The EIS-based lithium battery remaining life prediction system according to claim 1, characterized in that: The information storage module includes a first data server and a second data server. The first data server and the second data server are both integrated with a MySQL database. The first data server and the second data server are used for storage and backup, respectively.

Citation Information

Patent Citations

  • Lithium battery residual life prediction system based on EIS

    CN214845673U

  • Method for predicting remaining service life of lithium-ion battery employing WDE-optimized LSTM network

    WO2020191800A1

  • Lithium ion battery remaining life prediction method based on wolf pack optimization LSTM network

    WO2020191801A1