CN116930769A - Lithium battery modeling method based on bidirectional generation type antagonistic neural network - Google Patents

Lithium battery modeling method based on bidirectional generation type antagonistic neural network Download PDF

Info

Publication number
CN116930769A
CN116930769A CN202310912124.6A CN202310912124A CN116930769A CN 116930769 A CN116930769 A CN 116930769A CN 202310912124 A CN202310912124 A CN 202310912124A CN 116930769 A CN116930769 A CN 116930769A
Authority
CN
China
Prior art keywords
network
battery
neural network
generation type
lithium battery
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310912124.6A
Other languages
Chinese (zh)
Inventor
吕炳霖
刘勇超
田晓
李文芳
张帝
张涛
张佳云
赵冠
程婷婷
张亚萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Marketing Service Center of State Grid Shandong Electric Power Co Ltd
Original Assignee
Marketing Service Center of State Grid Shandong Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Marketing Service Center of State Grid Shandong Electric Power Co Ltd filed Critical Marketing Service Center of State Grid Shandong Electric Power Co Ltd
Priority to CN202310912124.6A priority Critical patent/CN116930769A/en
Publication of CN116930769A publication Critical patent/CN116930769A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0475—Generative networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/094—Adversarial learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Secondary Cells (AREA)

Abstract

The invention belongs to the technical field of lithium batteries, and provides a lithium battery modeling method and a system based on a bidirectional generation type antagonistic neural network, which are used for performing charge and discharge tests on a lithium ion battery and comprise the following steps: acquiring data in a test process to form an initial training data set; constructing a bidirectional generation type countermeasure neural network, initializing network parameters, wherein the bidirectional generation type countermeasure neural network comprises a generation network G, a decoding network E and a discrimination network D; randomly selecting data in an initial training data set to perform initial training on a bidirectional generation type antagonistic neural network to obtain a trained generation network G; and taking the generated network G after initial training as a dynamic characteristic model of the lithium battery, and predicting the voltage of the battery according to the real-time operation data of the battery. According to the invention, the training data is generated by utilizing the countermeasure learning training of the GAN, and the simulation precision of the model under the working condition that the training data set is not included in the training process is expanded, so that the aim of saving the workload of the training data is fulfilled.

Description

Lithium battery modeling method based on bidirectional generation type antagonistic neural network
Technical Field
The invention belongs to the technical field of lithium batteries, and particularly relates to a lithium battery modeling method based on a bidirectional generation type antagonistic neural network.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The accurate lithium battery model has great significance for battery management technology in the field of electric automobiles or energy storage.
Current lithium battery models include the following classes:
1. and (5) an electrochemical model. Such models use a number of partial differential equations to describe the electrochemical reaction process within the cell. The method is characterized by accurately reflecting an internal reaction mechanism, and has the defects of large calculation amount and difficulty in being used for online application.
2. And (5) an equivalent circuit model. The equivalent circuit device is utilized to describe the external characteristics of the battery, and the method has the advantages of small calculated amount and high precision. The method has the defect that the model parameters change along with factors such as temperature, charge and discharge working conditions, battery aging and the like, so that the accuracy of the equivalent circuit model under complex environments and working conditions is lower.
3. Neural network model. The model simulates the input-output characteristics of the battery through a neural network, and has higher nonlinear approximation capability. The disadvantage is that a large number of early tests are required to obtain training data to train the neural network to achieve sufficient accuracy. However, a large amount of test requires huge manpower and material resources, and the cost is high.
Therefore, the lithium battery model is difficult to have in a full temperature range, a complex working condition and a full aging range, and not only can meet the precision requirement, but also has reasonable calculation complexity.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a lithium battery modeling method based on a bidirectional generation type antagonistic neural network, which has the self-generation capacity of training samples, and can generate a large number of training samples only by a small amount of test data, so that the adaptability of the network to more temperatures and working conditions is expanded.
To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
the first aspect of the invention provides a lithium battery modeling method based on a bidirectional generation type antagonistic neural network, which comprises the following steps:
performing charge and discharge tests on the lithium ion battery to obtain the voltage, current, temperature, state of charge and capacity of the battery in the test process, and forming an initial training data set;
constructing a bidirectional generation type countermeasure neural network, and initializing network parameters, wherein the bidirectional generation type countermeasure neural network comprises a generation network G, a decoding network E and a discrimination network D;
randomly selecting data in an initial training data set to perform initial training on the bidirectional generation type antagonistic neural network to obtain a trained generation network G;
taking the generated network G after initial training as a dynamic characteristic model of the lithium battery, and predicting the voltage of the battery according to the real-time operation data of the battery;
and taking the decoding network E after initial training as an OCV model of the lithium battery, and predicting the open-circuit voltage of the battery according to the real-time operation data of the battery.
A second aspect of the invention provides a computer readable storage medium having stored thereon a program which when executed by a processor implements the steps in a method of modeling a lithium battery based on a bi-directional generation type antagonistic neural network according to the first aspect of the invention.
A third aspect of the invention provides an electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, the processor implementing the steps in a method for modeling a lithium battery based on a bi-directional generation type antagonistic neural network according to the first aspect of the invention when the program is executed.
The one or more of the above technical solutions have the following beneficial effects:
(1) The high accuracy of neural networks requires a large amount of offline training data as a guarantee, which tends to consume a large amount of test cost. According to the invention, the data such as battery voltage, current, open-circuit voltage, SOC and the like under the working conditions such as different temperatures, multiplying powers and the like are generated by utilizing the GAN generating network, and the accuracy of the generated data is improved by utilizing the countermeasure learning training of the GAN, so that the coverage range of model training data is expanded, the simulation precision of the model under the non-contained working conditions is improved, and the aim of saving the workload of training data is fulfilled.
(2) Under different temperatures, working conditions and aging states, parameters of the equivalent circuit model can change, and further the model accuracy is reduced. According to the invention, the battery characteristic simulation under various environmental working conditions can be realized through the neural network, and the output precision of the model under different temperatures, charge and discharge working conditions and aging conditions is improved through the nonlinear approximation function of the neural network.
(3) According to the invention, through an online updating process, the characteristics of the battery are always followed in the running process of the battery with a long time scale, so that the purpose of following and updating the battery performance is achieved.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a flow chart of a method of a first embodiment.
Fig. 2 is a diagram of a decoding network structure of the first embodiment.
Fig. 3 is a GAN network update training flowchart of the first embodiment.
Detailed Description
Example 1
The bidirectional generation countermeasure network overall framework of the invention is shown in fig. 1, and comprises a generation network (Generator, G), a decoding network (Encoder, E) and a discrimination network (discriminant, D), wherein the generation network G is used for generating training samples, and the input vector z of the generation network G is random open circuit voltage OCV and current I, SOC information of a battery and is output as battery terminal voltage;
conventional countermeasure neural networks perform countermeasure training between the generation network and actual data to improve the data generation capability of the generation network. Unlike traditional antagonistic neural networks, the present invention utilizes a decoding network to replace the actual voltage-current data. The reason is that the battery voltage and current data under all working conditions are acquired, the workload is huge, and the open-circuit voltage OCV information of the battery is basically kept stable under different working conditions, so that a decoding network is adopted, and a small amount of actual voltage and current data is utilized to extract the OCV information of the battery.
The decoding network comprises a nonlinear autoregressive deep migration network, and the function of the decoding network is to extract the open circuit voltage OCV of the battery from the actually obtained battery voltage, current and SOC information; the judging network D is used for distinguishing whether an input sample is true (an actual sample) or false (a generated sample), through training on the BiGAN, when an equilibrium state is reached, namely, the output probability of the judging network for the generated sample and the actual sample is 0.5, the G network at the moment is a battery dynamic characteristic model after training, and the E network is an OCV model of the battery.
Specifically, the lithium battery modeling method based on the bidirectional generation type antagonistic neural network provided by the embodiment comprises the following steps:
and step 1, performing charge and discharge test on the battery to obtain initial training data.
The charge and discharge test conditions cover a plurality of environment temperatures, charge and discharge working conditions and aging conditions. Constant current charging and dynamic working condition discharging tests are carried out on the battery at different temperatures of 45 ℃, 25 ℃, 0 ℃ and-5 ℃ respectively, and battery terminal voltage and current data are recorded. Meanwhile, under different battery aging states, charge and discharge tests are carried out, battery terminal voltage and current data are recorded, and an actual sample data set D= { U, I, SOC and Q }; the data set contains information of voltage U, current I, temperature, battery state of charge SOC, battery capacity Q, respectively.
And 2, constructing a decoding network (Encoder, E).
The decoding network is composed of a nonlinear autoregressive deep migration network, the structure of which is shown in fig. 2, the network can effectively predict nonlinear time sequence information and comprises an input layer, a hidden layer and an output layer, the input information of the network is x= { U, I }, and the output E (x) is the open-circuit voltage OCV of the battery; the relationship between the network output information and the input information can be expressed as:
wherein f o And (x) and f h Output functions of the output layer and hidden layer respectively, u and y are input and output of the network respectively, i k K=1, 2,3 is the input delay,b is the network weight o And b h The output bias for the output layer and hidden layer.
Training the decoding network by using the data set obtained in the step 1, and extracting battery open-circuit voltage information from actual battery operation data by the built decoding network.
And 3, constructing a generating network (G).
The network input information is generated as z= { OCV, I, SOC }, where OCV represents battery open circuit voltage, I is battery current, and SOC represents state of charge of the battery. The output information G (z) is the battery terminal voltage Ut. The generation network adopts a general neural network structure, and comprises an input layer, a hidden layer and an output layer, wherein the G network can be expressed as:
wherein h is k K-th item representing output sample, l represents hidden layer node number, n represents input item number, { alpha } ij G β G ω ki G γ k G And weight parameters of the G network. Φ (·) is the activation function.
Step 4, constructing a judging network, and simultaneously judging the input and output information (z, G (z)) of the generating network and the input and output information (x, E (x)) of the decoding network in a bidirectional mode, namely judging the input z of the generating network and the output E (x) of the decoding network at the same time, and judging the output G (z) of the generating network and the input x of the decoding network;
the discrimination network D adopts a general neural network structure and comprises an input layer, a hidden layer and an output layer, and the D network can be expressed as:
wherein d represents the probability of whether the input sample belongs to real data or generated data, and Γ (·) is an activation function of the classification function.
And 5, formulating learning rules of the D network and the G network.
Defining error gradient functions as:
where m represents the learned lot length and r and z represent the inputs to the D and G networks, respectively. The D and G networks can minimize the loss along the gradient function by adopting a conventional ADAM optimization method, and finally reach an equilibrium state. The quality of the sample data generated by the G network is at this point the best.
And 6, online optimizing and upgrading the GAN network.
After the network initial training is completed according to the steps 1-4, the GAN network model is updated in an online operation manner according to the flow shown in fig. 3. After the battery management system is electrified, the system records battery operation data in real time, the operation data are input into a trained G network to generate model terminal voltage Ut, and when the system is electrified, whether GAN network training is updated is judged by judging the difference between the model generated voltage and the actual recorded voltage. The judgment standard is as follows:
wherein U is m Representing the model output voltage, U t Representing the actual measured voltage, n is the run data length. When the Mae value exceeds the set threshold a, steps 1-5 are run to update train the network.
Example two
An object of the present embodiment is to provide a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs steps in a method of modeling a lithium battery based on a bi-directional generation type antagonistic neural network as described in embodiment 1 of the present disclosure.
Example III
An object of the present embodiment is to provide an electronic apparatus.
An electronic device comprising a memory, a processor, and a program stored on the memory and executable on the processor, the processor implementing the steps in a method of modeling a lithium battery based on a bi-directional generation type antagonistic neural network as described in embodiment 1 of the present disclosure when the program is executed.
The steps involved in the devices of the second, third and fourth embodiments correspond to those of the first embodiment of the method, and the detailed description of the embodiments can be found in the related description section of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media including one or more sets of instructions; it should also be understood to include any medium capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any one of the methods of the present invention.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented by general-purpose computer means, alternatively they may be implemented by program code executable by computing means, whereby they may be stored in storage means for execution by computing means, or they may be made into individual integrated circuit modules separately, or a plurality of modules or steps in them may be made into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.

Claims (10)

1. The lithium battery modeling method based on the bidirectional generation type antagonistic neural network is characterized by comprising the following steps of:
performing charge and discharge tests on the lithium ion battery to obtain the voltage, current, temperature, state of charge and capacity of the battery in the test process, and forming an initial training data set;
constructing a bidirectional generation type countermeasure neural network, and initializing network parameters, wherein the bidirectional generation type countermeasure neural network comprises a generation network G, a decoding network E and a discrimination network D;
randomly selecting data in an initial training data set to perform initial training on the bidirectional generation type antagonistic neural network to obtain a trained generation network G;
taking the generated network G after initial training as a dynamic characteristic model of the lithium battery, and predicting the voltage of the battery according to the real-time operation data of the battery; and taking the decoding network E after initial training as an OCV model of the lithium battery, and predicting the open-circuit voltage of the battery according to the real-time operation data of the battery.
2. The method for modeling a lithium battery based on a bi-directional generation type antagonistic neural network according to claim 1, wherein the generation network comprises three layers of an input layer, a hidden layer and an output layer, and the generation network is:
wherein h is k Represents the kth item output sample of the generated network, i represents the number of hidden layer nodes, n represents the number of input items, { alpha }, and ij G β G ω ki G γ k G and the weight parameter of the G network is represented, and phi (·) is an activation function.
3. The method for modeling a lithium battery based on a bi-directional generation type antagonistic neural network according to claim 1, wherein the decoding network is a nonlinear autoregressive deep migration network and comprises an input layer, a hidden layer and an output layer; the output and input relation of the decoding network is as follows:
wherein f 0 And (x) and f h Respectively (U is the output function of the output layer and the hidden layer k And y k Input and output, i, respectively, of the decoding network k In order to input the delay, the delay is,b is the network weight 0 And b h The output bias for the output layer and the hidden layer, respectively.
4. The method for modeling a lithium battery based on a bidirectional generation type antagonistic neural network according to claim 1, wherein in the training process, the input of the decoding network E is x= { U, I }, namely a battery voltage U and a battery current I, and the output E (X) is a battery open-circuit voltage OCV;
generating an input z= { OCV, I, SOC } of the network G, i.e., battery open circuit voltage OCV, battery current I, and state of charge SOC of the battery; generating an output G (z) of the network G as a battery terminal voltage U t ；
The discrimination network D performs bidirectional discrimination on the input and output information (z, G (z)) of the generation network G and the input and output (x, E (x)) of the decoding network E at the same time, and determines the probability that the input sample belongs to real data or generated data.
5. The method for modeling a lithium battery based on a bi-directional generation type antagonistic neural network according to claim 4, wherein the initial training of the bi-directional generation type antagonistic neural network is performed by minimizing an error gradient function of the discrimination network D and the generation network G during the training process;
the error gradient functions of the discrimination network D and the generation network G are respectively as follows:
where m represents the learned lot length, and r and z represent inputs to the discrimination network D and the generation network G, respectively.
6. The method for modeling a lithium battery based on a bi-directional generation type antagonistic neural network according to claim 5, wherein the discrimination network D is:
wherein d represents the probability of whether the input sample belongs to real data or generated data, and Γ (·) is an activation function of the classification function.
7. The method for modeling a lithium battery based on a bi-directional generation type antagonistic neural network according to claim 1, wherein whether to update and train the GAN network is determined according to a difference between a battery voltage predicted by a dynamic characteristic model of the lithium battery and an actually measured voltage.
8. The method for modeling a lithium battery based on a bidirectional generation type antagonistic neural network according to claim 7, wherein the judgment criterion is:
wherein U is m Output voltage, U, representing dynamic characteristic model of lithium battery t Representing the actual measured voltage of the battery, n being the length of the run data;
when Mae exceeds the threshold, the GAN network is updated and trained.
9. A computer readable storage medium having a program stored thereon, which when executed by a processor, implements the steps of a method for modeling a lithium battery based on a bi-directional generation type antagonistic neural network according to any of the claims 1 to 7.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor, when executing the program, performs the steps of a method for modeling a lithium battery based on a bi-directional generation type antagonistic neural network as claimed in any one of claims 1 to 7.
CN202310912124.6A 2023-07-24 2023-07-24 Lithium battery modeling method based on bidirectional generation type antagonistic neural network Pending CN116930769A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310912124.6A CN116930769A (en) 2023-07-24 2023-07-24 Lithium battery modeling method based on bidirectional generation type antagonistic neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310912124.6A CN116930769A (en) 2023-07-24 2023-07-24 Lithium battery modeling method based on bidirectional generation type antagonistic neural network

Publications (1)

Publication Number Publication Date
CN116930769A true CN116930769A (en) 2023-10-24

Family

ID=88378690

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310912124.6A Pending CN116930769A (en) 2023-07-24 2023-07-24 Lithium battery modeling method based on bidirectional generation type antagonistic neural network

Country Status (1)

Country Link
CN (1) CN116930769A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117607756A (en) * 2024-01-18 2024-02-27 杭州布雷科电气有限公司 Fuse performance test platform based on antagonistic neural network

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117607756A (en) * 2024-01-18 2024-02-27 杭州布雷科电气有限公司 Fuse performance test platform based on antagonistic neural network
CN117607756B (en) * 2024-01-18 2024-04-05 杭州布雷科电气有限公司 Fuse performance test platform based on antagonistic neural network

Similar Documents

Publication Publication Date Title
CN108896914B (en) Gradient lifting tree modeling and prediction method for health condition of lithium battery
Zhao et al. A compact methodology via a recurrent neural network for accurate equivalent circuit type modeling of lithium-ion batteries
CN111856287B (en) Lithium battery health state detection method based on stacked residual causal convolutional neural network
Zhang et al. Intelligent state of charge estimation of battery pack based on particle swarm optimization algorithm improved radical basis function neural network
Shaheen et al. Optimal parameter identification of linear and non-linear models for Li-Ion Battery Cells
Zhang et al. State‐of‐charge estimation of lithium‐ion battery pack based on improved RBF neural networks
CN113125960A (en) Vehicle-mounted lithium ion battery charge state prediction method based on random forest model
Wang et al. Battery full life cycle management and health prognosis based on cloud service and broad learning
Li et al. A recurrent neural network with long short-term memory for state of charge estimation of lithium-ion batteries
CN116643196A (en) Battery health state estimation method integrating mechanism and data driving model
CN116930769A (en) Lithium battery modeling method based on bidirectional generation type antagonistic neural network
Hasan et al. Performance comparison of machine learning methods with distinct features to estimate battery SOC
CN113311337A (en) Lithium ion battery residual life detection method based on relevance vector regression
CN117031310A (en) Method for predicting residual service life of power battery of electric automobile
CN113093014B (en) Online collaborative estimation method and system for SOH and SOC based on impedance parameters
Liu et al. Dual particle swarm optimization based data-driven state of health estimation method for lithium-ion battery
CN110232432B (en) Lithium battery pack SOC prediction method based on artificial life model
Xu et al. A novel Drosophila‐back propagation method for the lithium‐ion battery state of charge estimation adaptive to complex working conditions
Lyu et al. State-of-charge estimation of lithium-ion batteries based on deep neural network
CN116184214A (en) Online rapid prediction method and device for service life of power battery for vehicle and storage medium
CN114764124A (en) Lithium battery SOC estimation method based on GAN and LSTM
CN114415034A (en) Lithium ion battery capacity prediction method based on internal mechanism analysis
Liu et al. Fault diagnosis of series batteries based on GWO-SVM
CN114462294A (en) Two-stage agent model auxiliary parameter estimation method and system
Hametner et al. Model based lithium ion cell ageing data analysis

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination