CN112084459A - Method and device for predicting battery charge-discharge cycle life, electronic terminal and storage medium - Google Patents
Method and device for predicting battery charge-discharge cycle life, electronic terminal and storage medium Download PDFInfo
- Publication number
- CN112084459A CN112084459A CN201910506083.4A CN201910506083A CN112084459A CN 112084459 A CN112084459 A CN 112084459A CN 201910506083 A CN201910506083 A CN 201910506083A CN 112084459 A CN112084459 A CN 112084459A
- Authority
- CN
- China
- Prior art keywords
- charge
- discharge cycle
- battery
- cycle life
- predicting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 55
- 239000013598 vector Substances 0.000 claims abstract description 49
- 238000000611 regression analysis Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000004590 computer program Methods 0.000 claims description 26
- 238000012360 testing method Methods 0.000 claims description 20
- 238000005259 measurement Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 238000007599 discharging Methods 0.000 claims description 13
- 230000015556 catabolic process Effects 0.000 claims description 3
- 238000006731 degradation reaction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 6
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 239000000306 component Substances 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 229910052744 lithium Inorganic materials 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000007621 cluster analysis Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 235000018185 Betula X alpestris Nutrition 0.000 description 1
- 235000018212 Betula X uliginosa Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/44—Methods for charging or discharging
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Chemical & Material Sciences (AREA)
- Electrochemistry (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Chemical & Material Sciences (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The application provides a method, a device, an electronic terminal and a storage medium for predicting the cycle life of a battery, which comprises the following steps: acquiring early charge-discharge cycle data of a battery set; extracting charge and discharge cycle characteristics of at least one battery set according to the obtained early charge and discharge cycle data, and generating charge and discharge cycle data characteristic vectors of the battery set according to the charge and discharge cycle characteristics of the battery set to form a corresponding charge and discharge cycle characteristic vector set; clustering and grouping the charge and discharge cycle data feature vector set by using a clustering analysis algorithm; and respectively establishing corresponding regression models for the one or more groups of charge-discharge cycle data feature vector subsets after clustering by using a regression analysis algorithm so as to predict the charge-discharge cycle life of the battery according to the regression model which is closest to the feature of the battery to be tested in the established regression models. The method and the device are easy to popularize for predicting the charge-discharge cycle life of the batteries of different types, reduce the software and hardware requirements of a prediction system, and are convenient to deploy and use in practical application.
Description
Technical Field
The present application relates to the field of battery charge/discharge cycle life prediction, and in particular, to a method and an apparatus for predicting battery charge/discharge cycle life, an electronic terminal, and a storage medium.
Background
Along with the popularization and promotion of new energy automobiles, the prediction of the charge-discharge cycle life of a power battery, which is one of the core components of the new energy automobile, is increasingly attracting attention and attention of power battery manufacturers, automobile manufacturers and end users. For lithium batteries, a lithium battery is considered to fail when its actual capacity drops to 80% of its rated capacity. The long charge-discharge cycle life brings great market competitiveness to new energy automobiles, and therefore the method has important significance for predicting the charge-discharge cycle life of the lithium battery.
The existing data-driven prediction technology generally adopts a particle filter algorithm to predict the service life of a battery, and initial parameter values of a particle filter model can be generally obtained through experience and can also be calculated through known life attenuation data of other batteries.
However, in the practical application process, due to the complicated physicochemical process in the lithium battery, if the initial value of the parameter needs to be accurately estimated, the experience of the user needs to be highly required. For newly designed batteries, there may be no existing battery life decay data that can be referenced. Meanwhile, in the prediction process, the prior art often needs to predict all the historical charge-discharge cycle data of the object so as to update the state of the battery itself. Under the circumstances, the obtained parameters often cannot truly reflect the actual conditions of the lithium battery, so that the final charge-discharge cycle life prediction result is not accurate enough.
Meanwhile, for the prediction target, the prior art often needs to use as much historical charge and discharge cycle data as possible, generally needs a large amount of historical data of the battery, and cannot realize accurate prediction of the cycle life through partial or early charge and discharge cycle data.
Content of application
In view of the above-mentioned shortcomings of the prior art, the present application aims to provide a method, an apparatus, an electronic terminal, and a storage medium for predicting battery charge/discharge cycle life, so as to solve the technical problem in the prior art that it is difficult to obtain an initial value of a parameter for predicting battery charge/discharge cycle life.
To achieve the above and other related objects, a first aspect of the present application provides a method for predicting a charge-discharge cycle life of a battery, comprising: acquiring early charge-discharge cycle data of a battery set; extracting at least one battery set charging and discharging characteristic according to the obtained early charging and discharging cycle data, and generating a charging and discharging cycle data characteristic vector of the battery set according to the charging and discharging cycle data characteristic vector to form a corresponding characteristic vector set; clustering and grouping the charge and discharge cycle data feature vector set by using a clustering analysis algorithm; and respectively establishing corresponding regression models for the one or more groups of the cyclic data feature vector subsets after clustering by using a regression analysis algorithm so as to predict the charge-discharge cycle life of the battery according to the regression model which is closest to the feature of the battery to be tested in the established regression models.
In some embodiments of the first aspect of the present application, the method comprises: extracting charge-discharge characteristics of a plurality of battery sets according to the obtained early charge-discharge cycle data, comprising: any one or more combinations of discharge capacity difference characteristics, discharge curve degradation characteristics, battery internal resistance characteristics, and battery charge cycle number characteristics.
The charge/discharge cycle life is the number of charge/discharge cycles that can be performed by a battery with a certain capacity, and is called a charge/discharge cycle per charge/discharge. The early charge-discharge cycle data includes a preset number of charge-discharge cycle times tested earlier in the total number of charge-discharge cycles of the test battery; the preset number is not fixed and may be determined by a specific test scenario, which is not limited in this embodiment.
In some embodiments of the first aspect of the present application, a part of the plurality of cells that have undergone a complete charge-discharge cycle test is used as a training set for establishing a regression model, and another part of the plurality of cells is used as a test set; the method comprises the following steps: acquiring a plurality of early charge-discharge cycle data of a training set; extracting at least one training set charge-discharge characteristic according to the obtained early charge-discharge cycle data to generate a charge-discharge cycle data characteristic vector set of the training set; clustering and grouping the charge and discharge cycle data feature vector set by using a clustering analysis algorithm; respectively establishing corresponding regression models for one or more groups of charge-discharge cycle data feature vector subsets after clustering by using a regression analysis algorithm; and carrying out precision test on each regression model based on the test set.
In some embodiments of the first aspect of the present application, the method comprises: acquiring actual measurement data from a battery actual measurement field; and updating the regression model according to the obtained measured data.
To achieve the above and other related objects, a second aspect of the present application provides a method for predicting a charge-discharge cycle life of a battery, comprising: obtaining and deploying a regression model for predicting the charge-discharge cycle life of the battery; obtaining and deploying a regression model for predicting the charge-discharge cycle life of the battery; and predicting the charge-discharge cycle life of the battery according to the selected regression model.
In some embodiments of the second aspect of the present application, the method comprises: collecting and uploading actual measurement data based on a battery actual measurement field for updating the regression model; and/or obtaining and deploying one or more updated regression models for predicting battery charge-discharge cycle life.
To achieve the above and other related objects, a third aspect of the present application provides a device for predicting charge-discharge cycle life of a battery, comprising: the data acquisition module is used for acquiring early charge-discharge cycle data of the battery set; the characteristic vector set generating module is used for extracting charging and discharging characteristics of at least one battery set according to the obtained early charging and discharging cycle data so as to generate a charging and discharging cycle data characteristic vector set of the battery set; the clustering module is used for clustering and grouping the charge-discharge cycle data feature vector set by utilizing a clustering analysis algorithm; and the model establishing module is used for respectively establishing corresponding regression models for the one or more groups of the characteristic vector subsets of the charge-discharge cycle data after clustering by using a regression analysis algorithm so as to predict the charge-discharge cycle life of the battery according to the regression model which is closest to the characteristics of the battery with the charge-discharge cycle life to be measured in the established regression models.
To achieve the foregoing and other related objectives, a fourth aspect of the present application provides a model acquisition and deployment module for acquiring and deploying one or more regression models for predicting charge-discharge cycle life of a battery; the model selection module is used for selecting a regression model which is closest to the characteristics of the battery with the charge-discharge cycle life to be measured from the regression models; and the life prediction module is used for predicting the charge-discharge cycle life of the battery according to the selected regression model.
To achieve the above and other related objects, a fifth aspect of the present application provides a computer readable storage medium having stored thereon a first computer program and/or a second computer program, the first computer program, when executed by a processor, implementing the prediction method provided by the first aspect of the present application, the first computer program, when executed by a processor, implementing the prediction method provided by the second aspect of the present application.
To achieve the above and other related objects, a sixth aspect of the present application provides an electronic terminal comprising: a processor and a memory; the memory is used for storing computer programs, and the processor is used for executing the computer programs stored by the memory, so that the terminal executes the prediction method provided by the first aspect of the application.
To achieve the above and other related objects, a seventh aspect of the present application provides an electronic terminal comprising: a processor and a memory; the memory is used for storing computer programs, and the processor is used for executing the computer programs stored by the memory so as to enable the terminal to execute the prediction method provided by the second aspect of the application.
As described above, the method, the apparatus, the electronic terminal, and the storage medium for predicting the charge/discharge cycle life of the battery according to the present application have the following advantageous effects: the technical scheme provided by the application does not relate to the complicated physical and chemical mechanism of the battery, and only needs to be calculated and obtained according to the historical data of the battery to be tested, so that the service life of the battery can be easily predicted by popularizing the battery to different types. Compared with other battery charge-discharge cycle life prediction technologies based on data driving, the battery charge-discharge cycle life prediction method based on the data driving only needs to use the early charge-discharge cycle data of the battery to be detected, does not need to track all the charge-discharge cycle data of the battery to be detected, can realize the prediction of the charge-discharge life of the battery, reduces the requirements on software and hardware of a battery charge-discharge cycle life prediction system, and is more convenient to deploy and use in practical application.
Drawings
Fig. 1 is a schematic flow chart illustrating a system for predicting battery charge/discharge cycle life according to an embodiment of the present disclosure.
Fig. 2 is a schematic flowchart illustrating a method for predicting a charge/discharge cycle life of a battery according to an embodiment of the present disclosure.
FIG. 3 is a diagram illustrating a regression model set according to an embodiment of the present application.
Fig. 4 is a flowchart illustrating a method for predicting a charge/discharge cycle life of a battery according to an embodiment of the present disclosure.
Fig. 5 is a flowchart illustrating a method for predicting a charge/discharge cycle life of a battery according to an embodiment of the present disclosure.
Fig. 6 is a schematic structural diagram illustrating an apparatus for predicting battery charge/discharge cycle life according to an embodiment of the present disclosure.
Fig. 7 is a schematic structural diagram illustrating an apparatus for predicting battery charge/discharge cycle life according to an embodiment of the present disclosure.
Fig. 8 is a schematic structural diagram of an electronic terminal according to an embodiment of the present application.
Fig. 9 is a schematic structural diagram of an electronic terminal according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. The present application is capable of other and different embodiments and its several details are capable of modifications and/or changes in various respects, all without departing from the spirit of the present application. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," and/or "comprising," when used in this specification, specify the presence of stated features, operations, elements, components, items, species, and/or groups, but do not preclude the presence, or addition of one or more other features, operations, elements, components, items, species, and/or groups thereof. The terms "or" and/or "as used herein are to be construed as inclusive or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: a; b; c; a and B; a and C; b and C; A. b and C ". An exception to this definition will occur only when a combination of elements, functions or operations are inherently mutually exclusive in some way.
The application provides a method and a device for predicting the charge-discharge cycle life of a battery, an electronic terminal and a storage medium, aiming at the problem that ideal parameters are difficult to obtain in the existing technology for predicting the charge-discharge cycle life of the battery. According to the technical scheme, the complicated physical and chemical mechanism of the battery is not involved, and the battery life prediction method only needs to be obtained through calculation according to the historical data of the battery to be tested, so that the battery life prediction method can be easily popularized to prediction of battery lives of different types. Compared with other battery charge-discharge cycle life prediction technologies based on data driving, the battery charge-discharge cycle life prediction method based on the data driving only needs to use the early charge-discharge cycle data of the battery to be detected, does not need to track all the charge-discharge cycle data of the battery to be detected, can realize the prediction of the charge-discharge cycle life of the battery, reduces the requirements on software and hardware of a battery charge-discharge cycle life prediction system, and is more convenient to deploy and use in practical application.
Fig. 1 shows a schematic flow chart of a system for predicting battery charge/discharge cycle life according to an embodiment of the present disclosure. The prediction system comprises a cloud end device 11 and a vehicle-mounted end device 12 which are in communication connection through a base station.
The cloud device 11 is used for establishing a regression model for predicting the charge-discharge cycle life of the battery, and the vehicle-mounted end device 12 is used for acquiring and deploying the regression model from the cloud and predicting the charge-discharge cycle life of the current battery to be tested by using the regression model. The vehicle-mounted end equipment 12 is further configured to upload battery actual measurement data acquired from an actual measurement field to the cloud end equipment 11, so that the cloud end equipment 11 updates the regression model according to the battery actual measurement data, and issues the updated regression model to the vehicle-mounted end equipment 12, so that the regression model is continuously updated, and the accuracy of battery charge-discharge cycle life prediction is improved.
The cloud device 11 may be a computer including components such as memory, a memory controller, one or more processing units (CPUs), a peripheral interface, RF circuitry, audio circuitry, speakers, a microphone, an input/output (I/O) subsystem, a display screen, other output or control devices, and external ports; the computer includes but is not limited to Personal computers such as desktop computers, notebook computers, tablet computers, smart phones, smart televisions, Personal Digital assistants (PDAs for short), and the like; the cloud device 11 may also be a server, and the server may be arranged on one or more entity servers according to various factors such as functions and loads, or may be formed by a distributed or centralized server cluster.
The vehicle-mounted end device 12 is, for example, a vehicle control terminal, and the vehicle control terminal is a front end device of a vehicle monitoring management system, also called a vehicle scheduling monitoring terminal (TCU terminal); the vehicle-mounted end device 12 may also be a vehicle-mounted controller, such as an arm (advanced RISC machines), an fpga (field Programmable Gate array), an soc (system on chip), a dsp (digital Signal processing), or an mcu (micro controller unit).
In this embodiment, in consideration of the fact that clustering of the feature vector library and construction of the regression model involved in model establishment consume more computing resources, cloud equipment is adopted to execute a task of constructing the regression model, so as to realize efficient and rapid modeling. In addition, the resources consumed by predicting the charge-discharge cycle life of the battery by using the actual measurement model and collecting actual measurement data are small, so that local vehicle-mounted end equipment is adopted for execution, and the deployment and application costs are reduced.
However, in other embodiments, the cloud device for constructing the regression model and the vehicle-mounted device for predicting the charge-discharge cycle life of the battery may be designed integrally, for example, both the cloud device and the vehicle-mounted device are disposed at the cloud end or both the cloud device and the vehicle-mounted device are disposed at the vehicle-mounted end, which is not limited in the present application.
Fig. 2 is a schematic flow chart showing a method for predicting the charge-discharge cycle life of a battery according to an embodiment of the present disclosure. The method for predicting the charge-discharge cycle life of the battery in the embodiment is applied to the cloud device and comprises steps S201 to S204.
In step S201, early charge-discharge cycle data of the battery set is acquired.
The basis for constructing the regression model is the historical charge-discharge cycle data of the battery set, which should include the complete charge-discharge cycle life cycle of the battery. The selection of the early charge-discharge cycle data interval varies with different batteries, and needs to be screened and set through experiments, and usually a group of fixed values, for example, the first 10 cycles or the first 50 cycles, may be selected to perform regression analysis, respectively, and the data interval with the highest accuracy is used to extract the early charge-discharge cycle characteristics.
In step S202, at least one battery set charge-discharge characteristic is extracted according to the obtained early charge-discharge cycle data, so as to generate a charge-discharge cycle data characteristic vector set of the battery set.
In an embodiment, the extraction of the charging and discharging curve features of the battery set not only includes a feature extraction link, but also includes a preprocessing link required by the feature extraction, including preprocessing, feature dimension reduction, normalization, and the like. Extracting charge and discharge characteristics of a plurality of battery sets according to the obtained early charge and discharge cycle data includes but is not limited to the following characteristic combinations: a discharge capacity difference characteristic, a discharge curve degradation characteristic, a battery internal resistance characteristic, or a battery charge cycle number characteristic, etc.
In step S203, clustering and grouping the charge and discharge cycle data feature vector sets by using a clustering analysis algorithm.
The cluster analysis algorithm refers to an analysis process that groups a set of physical or abstract objects into classes composed of similar objects, with the goal of collecting data for classification on a similar basis. Considering that the effect of data clustering is highly related to the distribution of the feature vector set, under the condition that the data distribution of the feature vectors is not fully known, the embodiment provides a plurality of clustering methods for evaluating the effect of feature clustering, and finally, a method with the optimal clustering effect is selected to complete feature clustering.
Specifically, the cluster analysis algorithm includes, but is not limited to: a partitional clustering algorithm, a hierarchical clustering algorithm, a fuzzy clustering algorithm, or a density-based clustering algorithm, etc.; wherein, the partition and cluster algorithm is, for example, K-means algorithm, K-center point algorithm, CLARANS algorithm, or the like; hierarchical clustering algorithms such as the DIANA algorithm, the BIRCH algorithm, and the like; fuzzy clustering algorithms such as EM algorithms; the density-based algorithm is, for example, the OPTICS algorithm, the DBSCAN algorithm, or the like. The types of the cluster analysis algorithm are many, so this embodiment does not give details to this.
In step S204, a regression analysis algorithm is used to respectively establish corresponding regression models for the one or more groups of charge-discharge cycle data feature vector subsets after clustering, so as to predict the charge-discharge cycle life of the battery according to the regression model closest to the feature of the battery to be tested for charge-discharge cycle life in the established regression models.
The regression analysis algorithm is a predictive analysis algorithm for studying the relationship between dependent variables (targets) and independent variables (predictors). And respectively carrying out regression analysis on the cycle data feature vector subsets after clustering and grouping so as to generate a corresponding regression model set and establish an incidence relation between the regression model and each feature class.
Fig. 3 is a schematic diagram of a regression model set according to an embodiment of the present application. And clustering the charge-discharge cycle data feature vector set into N subsets by using a clustering analysis algorithm, wherein the N subsets are respectively a charge-discharge cycle data feature vector subset 1 and a charge-discharge cycle data feature vector subset 2 … … charge-discharge cycle data feature vector subset N. And establishing a corresponding regression model for each charge-discharge cycle data feature vector subset by using a regression analysis algorithm, namely establishing a regression model 1 and a regression model 2 … … regression model N, wherein each charge-discharge cycle data feature vector subset corresponds to a regression model.
In one embodiment, considering that the accuracy of the regression analysis algorithm is highly related to the characteristics of the distribution of the feature data set, different types of regression analysis methods are adopted to construct a regression model system, and the final regression model is selected according to the optimal regression effect.
Specifically, the regression analysis algorithm includes, but is not limited to, the following algorithm combinations: linear Regression algorithm, Logistic Regression algorithm, polymodal Regression Polynomial Regression algorithm, Stepwise Regression algorithm, Ridge Regression algorithm, Lasso Regression algorithm, ElasticNet Regression algorithm, and the like.
In an embodiment, the method further comprises: acquiring actual measurement data from a battery actual measurement field; and updating the regression model according to the obtained measured data. That is, the early charge-discharge cycle actual measurement data of the local battery in the new energy automobile is uploaded to the cloud device for the cloud device to update the regression model.
Fig. 4 is a schematic flow chart showing a method for predicting the charge-discharge cycle life of a battery according to another embodiment of the present disclosure. In this embodiment, a part of the batteries subjected to the complete charge-discharge cycle test is used as a training set for establishing a regression model, and another part of the batteries is used as a test set; the prediction method includes steps S401 to S405.
In step S401, a plurality of early charge-discharge cycle data of the training set are acquired.
In step S402, at least one training set charge-discharge characteristic is extracted according to the obtained early charge-discharge cycle data, so as to generate a charge-discharge cycle data characteristic vector set of the training set.
In step S403, clustering and grouping the charge and discharge cycle data feature vector sets by using a clustering analysis algorithm.
In step S404, a regression analysis algorithm is used to respectively establish corresponding regression models for the one or more groups of charge-discharge cycle data feature vector subsets after clustering.
In step S405, accuracy testing is performed on each regression model based on the test set.
To facilitate understanding by those skilled in the art, the principles of the training set and the test set will now be further explained and illustrated in conjunction with the following embodiments.
In this example, a batch of cells (e.g., less than 100 cells) is selected and the cells in the batch are subjected to a complete charge-discharge cycle test until the entire life cycle of the cell is completed (the discharge capacity of the cell is less than 80% of the nominal capacity). And aiming at the batch of batteries, dividing the batch of batteries into a training set and a testing set according to a preset proportion and in a random mode.
Specifically, charging and discharging characteristics are respectively extracted from the training set and the test set, and a charging and discharging cycle data characteristic vector set of the battery of the batch is constructed. And constructing a charge-discharge cycle life prediction model of the battery based on the training set and by utilizing a regression analysis algorithm, and evaluating the accuracy of the constructed prediction model based on the test set.
Fig. 5 is a schematic flow chart showing a method for predicting the charge/discharge cycle life of a battery according to an embodiment of the present disclosure. The method for predicting the charge-discharge cycle life of the battery in the embodiment is applied to the vehicle-mounted terminal device, and includes steps S501 to S503.
In step S501, a regression model for predicting the charge-discharge cycle life of the battery is acquired and deployed.
In step S502, a regression model closest to the characteristics of the battery having the charge-discharge cycle life to be measured is selected from the plurality of regression models.
Specifically, early charge and discharge test data of the battery with the charge and discharge cycle life to be tested is obtained, and the normalized input characteristics are obtained by adopting the characteristics which are the same as those in the process of constructing the regression model, namely the preprocessing method. And selecting a regression model closest to the characteristics of the battery to be tested from the regression model set, and predicting the charge-discharge cycle life of the battery to be tested by using the regression model.
In an embodiment, the selecting a regression model closest to the characteristic of the battery to be tested from the regression model set refers to analyzing similarity between the characteristic curve of the battery to be tested and the characteristic curves of the regression models in the regression model set, and using a regression model with the highest similarity as the regression model closest to the characteristic of the battery to be tested.
Specifically, for evaluating the similarity between two characteristic curves, distance estimation based on various distance measures, such as euclidean distance, Hausdorff distance, fracer distance, or the like, similarity analysis using correlation coefficients, or the like may be used.
In step S503, the charge-discharge cycle life of the battery is predicted from the selected regression model.
In an embodiment, the method further includes collecting and uploading measured data based on a battery measured field for updating the regression model, that is, uploading the relevant feature data to the battery set historical data set, so that automatic updating of the regression model can be achieved on the cloud device and the regression model can be issued to the vehicle-mounted device.
In one embodiment, the method further comprises obtaining and deploying one or more updated regression models for predicting the charge-discharge cycle life of the battery, thereby continuously improving the accuracy of the prediction of the charge-discharge cycle life of the battery.
Fig. 6 is a schematic structural diagram of a device for predicting the charge/discharge cycle life of a battery according to an embodiment of the present disclosure. The device comprises a data acquisition module 61, a feature vector set generation module 62, a clustering module 63 and a model establishing module 64.
The data acquisition module 61 is used for acquiring early charge-discharge cycle data of the battery set; the feature vector set generating module 62 is configured to extract at least one battery set charge-discharge feature according to the obtained early charge-discharge cycle data, so as to generate a charge-discharge cycle data feature vector set of the battery set; the clustering module 63 is configured to perform clustering grouping on the charge-discharge cycle data feature vector set by using a clustering analysis algorithm; the model establishing module 64 is configured to respectively establish corresponding regression models for the one or more groups of feature vector subsets of the charge-discharge cycle data after clustering by using a regression analysis algorithm, so as to predict the charge-discharge cycle life of the battery according to the regression model closest to the feature of the battery to be tested for the charge-discharge cycle life in the established regression models.
Fig. 7 is a schematic structural diagram of a device for predicting battery charge/discharge cycle life according to another embodiment of the present disclosure. The device comprises: a model obtaining and deploying module 71, a model selecting module 72 and a life predicting module 73.
The model acquisition and deployment module 71 is configured to acquire and deploy one or more regression models for predicting the charge-discharge cycle life of the battery; the model selection module 72 is configured to select a regression model closest to the characteristics of the battery to be tested for the charge-discharge cycle life from the multiple regression models; the life prediction module 73 is configured to predict the charge-discharge cycle life of the battery based on the selected regression model.
It should be noted that the embodiment of the device for predicting the charge/discharge cycle life of the battery is similar to the embodiment of the method for predicting the charge/discharge cycle life of the battery, and thus the description thereof is omitted. It should be understood that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity or may be physically separated.
Fig. 8 is a schematic structural diagram of an electronic terminal according to an embodiment of the present application. The electronic terminal provided by this example includes a processor 81 and a memory 82, the memory 82 is connected to the processor 81 through a system bus and completes communication with each other, the memory 82 is used for storing a computer program, and the processor 81 is used for running the computer program, so that the electronic terminal executes steps S201 to S204 in the method for predicting the battery cycle life.
Fig. 9 is a schematic structural diagram of another electronic terminal according to an embodiment of the present application. The electronic terminal provided by this example includes a processor 91 and a memory 92, the memory 92 is connected to the processor 91 through a system bus and completes communication with each other, the memory 92 is used for storing a computer program, and the processor 91 is used for running the computer program, so that the electronic terminal executes steps S501 to S503 in the method for predicting the battery cycle life.
The above-mentioned system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other equipment (such as a client, a read-write library and a read-only library). The Memory may include a Random Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In an embodiment, the present application further provides a computer readable storage medium having stored thereon a first computer program and/or a second computer program, wherein the first computer program, when executed by a processor, implements steps S201 to S204 in a method for predicting battery cycle life as such, and the second computer program, when executed by a processor, implements steps S501 to S503 in a method for predicting battery cycle life as such.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
To sum up, the application provides a prediction method, a prediction device, an electronic terminal and a storage medium for battery charge-discharge cycle life, and the technical scheme provided by the application only needs to be calculated and obtained according to the historical data of the battery to be tested because the method does not relate to the complicated physical and chemical mechanism of the battery, so that the method and the device can be easily popularized to the prediction of the charge-discharge life of the batteries of different types. Compared with other battery charge-discharge cycle life prediction technologies based on data driving, the battery charge-discharge cycle life prediction method based on the data driving only needs to use the early charge-discharge cycle data of the battery to be detected, does not need to track all the charge-discharge cycle data of the battery to be detected, can realize the prediction of the charge-discharge cycle life of the battery, reduces the requirements on software and hardware of a battery charge-discharge cycle life prediction system, and is more convenient to deploy and use in practical application. Therefore, the application effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the application. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical concepts disclosed in the present application shall be covered by the claims of the present application.
Claims (12)
1. A method for predicting the charge-discharge cycle life of a battery, comprising:
acquiring early charge-discharge cycle data of a battery set;
extracting charge and discharge cycle characteristics of at least one battery set according to the obtained early charge and discharge cycle data, and generating charge and discharge cycle data characteristic vectors of the battery set according to the charge and discharge cycle characteristics so as to form a corresponding characteristic vector set;
clustering and grouping the charge and discharge cycle data feature vector set by using a clustering analysis algorithm;
and respectively establishing corresponding regression models for the one or more groups of charge-discharge cycle data feature vector subsets after clustering by using a regression analysis algorithm so as to predict the charge-discharge cycle life of the battery according to the regression model which is closest to the feature of the battery to be tested in the established regression models.
2. The method according to claim 1, characterized in that it comprises: extracting charge-discharge characteristics of a plurality of battery sets according to the obtained early charge-discharge cycle data, comprising: any one or more combinations of discharge capacity difference characteristics, discharge curve degradation characteristics, battery internal resistance characteristics, and battery charge cycle number characteristics.
3. The method according to claim 1, wherein a part of the plurality of cells subjected to the complete charge-discharge cycle test is made a training set for establishing the regression model, and another part of the plurality of cells is made a test set; the method comprises the following steps:
acquiring a plurality of early charge-discharge cycle data of a training set;
extracting at least one training set charge-discharge characteristic according to the obtained early charge-discharge cycle data to generate a charge-discharge cycle data characteristic vector set of the training set;
clustering and grouping the charge and discharge cycle data feature vector set by using a clustering analysis algorithm;
respectively establishing corresponding regression models for one or more groups of charge-discharge cycle data feature vector subsets after clustering by using a regression analysis algorithm;
and carrying out precision test on each regression model based on the test set.
4. The method of claim 1, comprising:
acquiring actual measurement data from a battery actual measurement field;
and updating the regression model according to the obtained measured data.
5. A method for predicting the charge-discharge cycle life of a battery, comprising:
obtaining and deploying a regression model for predicting the charge-discharge cycle life of the battery;
selecting a regression model closest to the characteristics of the battery with the charge-discharge cycle life to be tested from the regression models;
and predicting the charge-discharge cycle life of the battery according to the selected regression model.
6. The method of claim 5, comprising:
collecting and uploading actual measurement data based on a battery actual measurement field for updating the regression model; and/or
One or more updated regression models for predicting battery charge-discharge cycle life are obtained and deployed.
7. An apparatus for predicting a charge-discharge cycle life of a battery, comprising:
the data acquisition module is used for acquiring early charge-discharge cycle data of the battery set;
the characteristic vector set generating module is used for extracting charging and discharging characteristics of at least one battery set according to the obtained early charging and discharging cycle data so as to generate a charging and discharging cycle data characteristic vector set of the battery set;
the clustering module is used for clustering and grouping the charge-discharge cycle data feature vector set by utilizing a clustering analysis algorithm;
and the model establishing module is used for respectively establishing corresponding regression models for the one or more groups of the characteristic vector subsets of the charge-discharge cycle data after clustering by using a regression analysis algorithm so as to predict the charge-discharge cycle life of the battery according to the regression model which is closest to the characteristics of the battery with the charge-discharge cycle life to be measured in the established regression models.
8. An apparatus for predicting a charge-discharge cycle life of a battery, comprising:
the model acquisition and deployment module is used for acquiring and deploying one or more regression models for predicting the charge-discharge cycle life of the battery;
the model selection module is used for selecting a regression model which is closest to the characteristics of the battery with the charge-discharge cycle life to be measured from the regression models;
and the life prediction module is used for predicting the charge-discharge cycle life of the battery according to the selected regression model.
9. A computer-readable storage medium, on which a first computer program and/or a second computer program is stored, wherein the first computer program, when executed by a processor, implements the method for predicting battery charge-discharge cycle life according to any one of claims 1 to 4, and wherein the second computer program, when executed by a processor, implements the method for predicting battery charge-discharge cycle life according to claim 5 or 6.
10. An electronic terminal, comprising: a processor and a memory;
the memory is used for storing a computer program;
the processor is used for executing the computer program stored in the memory so as to enable the terminal to execute the method for predicting the charge and discharge cycle life of the battery according to any one of claims 1-4.
11. An electronic terminal, comprising: a processor and a memory;
the memory is used for storing a computer program;
the processor is configured to execute the computer program stored in the memory to cause the terminal to perform the method of predicting battery charge-discharge cycle life according to claim 5 or 6.
12. A system for predicting the charge-discharge cycle life of a battery, comprising an electronic terminal according to claim 10 and an electronic terminal according to claim 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910506083.4A CN112084459A (en) | 2019-06-12 | 2019-06-12 | Method and device for predicting battery charge-discharge cycle life, electronic terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910506083.4A CN112084459A (en) | 2019-06-12 | 2019-06-12 | Method and device for predicting battery charge-discharge cycle life, electronic terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112084459A true CN112084459A (en) | 2020-12-15 |
Family
ID=73734437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910506083.4A Pending CN112084459A (en) | 2019-06-12 | 2019-06-12 | Method and device for predicting battery charge-discharge cycle life, electronic terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112084459A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673157A (en) * | 2021-08-19 | 2021-11-19 | 青岛特来电新能源科技有限公司 | Training method and device for battery capacity prediction model, electronic equipment and medium |
| CN115327382A (en) * | 2022-06-28 | 2022-11-11 | 广州汽车集团股份有限公司 | Method and device for generating battery service life prediction model and vehicle |
| CN116774057A (en) * | 2023-08-18 | 2023-09-19 | 南京大全电气研究院有限公司 | Method and device for training battery life prediction model and predicting battery life |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070220340A1 (en) * | 2006-02-22 | 2007-09-20 | Whisnant Keith A | Using a genetic technique to optimize a regression model used for proactive fault monitoring |
| JP2012154839A (en) * | 2011-01-27 | 2012-08-16 | Yokogawa Electric Corp | Life prediction evaluation device and life prediction evaluation method |
| CN103389471A (en) * | 2013-07-25 | 2013-11-13 | 哈尔滨工业大学 | Cycle life indirect prediction method for lithium ion battery provided with uncertain intervals on basis of GPR (general purpose register) |
| CN103954913A (en) * | 2014-05-05 | 2014-07-30 | 哈尔滨工业大学深圳研究生院 | Predication method of electric vehicle power battery service life |
| CN106055775A (en) * | 2016-05-27 | 2016-10-26 | 哈尔滨工业大学 | Prediction method for life of secondary battery based on particle filter and mechanism model |
| US20170023649A1 (en) * | 2015-07-21 | 2017-01-26 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating state of battery |
| CN106778010A (en) * | 2016-12-29 | 2017-05-31 | 中铁十八局集团隧道工程有限公司 | TBM cutter life Forecasting Methodologies based on data-driven support vector regression |
| CN107238800A (en) * | 2017-06-12 | 2017-10-10 | 北京理工大学 | A kind of remaining probable life Forecasting Methodology of the electrokinetic cell system based on Method Using Relevance Vector Machine and particle filter |
| CN108037463A (en) * | 2017-12-15 | 2018-05-15 | 太原理工大学 | A kind of lithium ion battery life-span prediction method |
| CN108846227A (en) * | 2017-12-05 | 2018-11-20 | 北京航空航天大学 | A kind of capacity of lithium ion battery degradation prediction appraisal procedure based on random forest and capacity self- recoverage effect analysis |
| CN109190087A (en) * | 2018-08-07 | 2019-01-11 | 东莞理工学院 | A kind of remaining battery life prediction technique, device, electronic equipment and storage medium |
| CN109253826A (en) * | 2018-08-01 | 2019-01-22 | 西安交通大学 | A kind of calorimeter method for predicting residual useful life based on the fusion of more degeneration sample datas |
| CN109507535A (en) * | 2018-12-10 | 2019-03-22 | 国网河南省电力公司电力科学研究院 | Grounding net of transformer substation operation phase and service life prediction technique and device |
| CN109782192A (en) * | 2019-03-08 | 2019-05-21 | 安徽理工大学 | Lithium ion battery residual life prediction technique under different discharge-rates |
-
2019
- 2019-06-12 CN CN201910506083.4A patent/CN112084459A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070220340A1 (en) * | 2006-02-22 | 2007-09-20 | Whisnant Keith A | Using a genetic technique to optimize a regression model used for proactive fault monitoring |
| JP2012154839A (en) * | 2011-01-27 | 2012-08-16 | Yokogawa Electric Corp | Life prediction evaluation device and life prediction evaluation method |
| CN103389471A (en) * | 2013-07-25 | 2013-11-13 | 哈尔滨工业大学 | Cycle life indirect prediction method for lithium ion battery provided with uncertain intervals on basis of GPR (general purpose register) |
| CN103954913A (en) * | 2014-05-05 | 2014-07-30 | 哈尔滨工业大学深圳研究生院 | Predication method of electric vehicle power battery service life |
| US20170023649A1 (en) * | 2015-07-21 | 2017-01-26 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating state of battery |
| CN106055775A (en) * | 2016-05-27 | 2016-10-26 | 哈尔滨工业大学 | Prediction method for life of secondary battery based on particle filter and mechanism model |
| CN106778010A (en) * | 2016-12-29 | 2017-05-31 | 中铁十八局集团隧道工程有限公司 | TBM cutter life Forecasting Methodologies based on data-driven support vector regression |
| CN107238800A (en) * | 2017-06-12 | 2017-10-10 | 北京理工大学 | A kind of remaining probable life Forecasting Methodology of the electrokinetic cell system based on Method Using Relevance Vector Machine and particle filter |
| CN108846227A (en) * | 2017-12-05 | 2018-11-20 | 北京航空航天大学 | A kind of capacity of lithium ion battery degradation prediction appraisal procedure based on random forest and capacity self- recoverage effect analysis |
| CN108037463A (en) * | 2017-12-15 | 2018-05-15 | 太原理工大学 | A kind of lithium ion battery life-span prediction method |
| CN109253826A (en) * | 2018-08-01 | 2019-01-22 | 西安交通大学 | A kind of calorimeter method for predicting residual useful life based on the fusion of more degeneration sample datas |
| CN109190087A (en) * | 2018-08-07 | 2019-01-11 | 东莞理工学院 | A kind of remaining battery life prediction technique, device, electronic equipment and storage medium |
| CN109507535A (en) * | 2018-12-10 | 2019-03-22 | 国网河南省电力公司电力科学研究院 | Grounding net of transformer substation operation phase and service life prediction technique and device |
| CN109782192A (en) * | 2019-03-08 | 2019-05-21 | 安徽理工大学 | Lithium ion battery residual life prediction technique under different discharge-rates |
Non-Patent Citations (2)
| Title |
|---|
| 孟洁茹: "复杂应力条件下基于数据驱动的性能退化型产品寿命预测方法", 中国知网, no. 4, 15 April 2018 (2018-04-15) * |
| 焦东升;康栩宁;潘鸣宇;李香龙;迟忠君;: "一种动力电池容量一致性辨识方法", 电源技术, no. 07, 20 July 2016 (2016-07-20) * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673157A (en) * | 2021-08-19 | 2021-11-19 | 青岛特来电新能源科技有限公司 | Training method and device for battery capacity prediction model, electronic equipment and medium |
| CN115327382A (en) * | 2022-06-28 | 2022-11-11 | 广州汽车集团股份有限公司 | Method and device for generating battery service life prediction model and vehicle |
| CN115327382B (en) * | 2022-06-28 | 2024-02-23 | 广州汽车集团股份有限公司 | Method and device for generating battery service life prediction model and vehicle |
| CN116774057A (en) * | 2023-08-18 | 2023-09-19 | 南京大全电气研究院有限公司 | Method and device for training battery life prediction model and predicting battery life |
| CN116774057B (en) * | 2023-08-18 | 2023-11-14 | 南京大全电气研究院有限公司 | Method and device for training battery life prediction model and predicting battery life |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Prognostic health condition for lithium battery using the partial incremental capacity and Gaussian process regression | |
| CN111856287B (en) | Lithium battery health state detection method based on stacked residual causal convolutional neural network | |
| KR102439041B1 (en) | Method and apparatus for diagnosing defect of battery cell based on neural network | |
| CN112084459A (en) | Method and device for predicting battery charge-discharge cycle life, electronic terminal and storage medium | |
| CN104182630A (en) | Residual battery capacity detection method based on simplified least square support vector machine | |
| CN109613440B (en) | Battery grading method, device, equipment and storage medium | |
| JP7450741B2 (en) | Lithium battery SOC estimation method, device and computer readable storage medium | |
| CN109633448B (en) | Method and device for identifying battery health state and terminal equipment | |
| CN112180258B (en) | Method, device, medium, terminal and system for measuring average coulombic efficiency of battery | |
| CN112666480A (en) | Battery life prediction method based on charging process characteristic attention | |
| CN109768340B (en) | Method and device for estimating voltage inconsistency in battery discharge process | |
| CN111983474A (en) | Lithium ion battery life prediction method and system based on capacity decline model | |
| CN110806540B (en) | Battery cell test data processing method, device and system and storage medium | |
| Zhang et al. | State of health estimation of lithium-ion batteries based on modified flower pollination algorithm-temporal convolutional network | |
| CN116699446A (en) | Method, device, equipment and storage medium for rapidly sorting retired batteries | |
| Lyu et al. | A semiparametric clustering method for the screening of retired Li-ion batteries from electric vehicles | |
| Dong et al. | Data-driven predictive prognostic model for power batteries based on machine learning | |
| US20240038341A1 (en) | Method, system and storage medium for consistency analysis of lithium battery module | |
| CN117289167A (en) | Battery remaining life prediction method, device and medium based on multiple neural network | |
| CN116930769A (en) | Lithium battery modeling method based on bidirectional generation type antagonistic neural network | |
| CN110068409B (en) | Lithium battery stress prediction method and device | |
| CN115856646A (en) | Lithium ion battery early life prediction method based on three-dimensional voltage characteristics | |
| CN115267556A (en) | Battery life degradation analysis method, storage medium, and electronic device | |
| CN115792627A (en) | Lithium battery SOH analysis and prediction method and device, electronic equipment and storage medium | |
| Yang et al. | State of Health Estimation Based on GAN-LSTM-TL for Lithium-Ion Batteries |
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 |