CN111044928A - Lithium battery health state estimation method - Google Patents
Lithium battery health state estimation method Download PDFInfo
- Publication number
- CN111044928A CN111044928A CN201911402258.3A CN201911402258A CN111044928A CN 111044928 A CN111044928 A CN 111044928A CN 201911402258 A CN201911402258 A CN 201911402258A CN 111044928 A CN111044928 A CN 111044928A
- Authority
- CN
- China
- Prior art keywords
- model
- lithium battery
- regression
- training
- data
- 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
Images
Classifications
-
- 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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention relates to a lithium battery health state estimation method, which comprises the following steps: selecting battery capacity as a state variable, and extracting a plurality of characteristics according to correlation analysis to be used as input and output data of a subsequent model so as to simulate the aging process of the lithium battery; dividing the sample data into a training set and a test set, establishing a regression model based on a gradient lifting decision tree, performing parameter optimization on the regression model, and performing sample training to obtain a mixed algorithm regression training model; and (4) estimating the health state of the lithium battery under the test set by utilizing a mixed algorithm regression training model. The method has the advantages of high precision, strong generalization capability and the like, and can accurately and effectively estimate the health state of the lithium battery.
Description
Technical Field
The invention relates to the technical field of battery design, in particular to a lithium battery health state estimation method.
Background
With the continuous development of the automobile industry, people pay more and more attention to the environmental pollution caused by automobile exhaust. Electric vehicles make a contribution to solving environmental problems such as global warming due to their advantages in terms of performance, efficiency, and the like. Currently, lithium ion batteries are becoming the most widely used battery type due to their high energy density, good stability, long cycle life, and the like. However, even though a Battery Management System (BMS) has been started to manage and control the lithium battery, the advantages of the lithium battery may have some potential threats, such as safety, service life, and the like. Among these problems, how to accurately estimate the state of health (SOH) of a battery of lithium is a major problem of the BMS because the major tasks of the BMS include real-time state estimation, battery thermal management, safety control, and battery equalization, etc., and the SOH of the battery is one of the critical state parameters of the battery, which directly affects the performance of the battery. The accurate estimation of the SOH of the battery can provide a reference for reasonably planning and using an energy strategy of the BMS and effectively avoiding potential threats, and damage caused by excessive use of the battery is well avoided. Therefore, it is extremely important and meaningful to provide an accurate, efficient and reliable SOH estimation method for lithium batteries.
In recent years, various lithium battery state of health estimation methods have been proposed in succession. Tran et al used a dual extended kalman filter and ARX model to estimate the SOH of lithium batteries. However, this method requires the establishment of various battery models and has no generalization. Mo et al propose a particle swarm optimization-based Kalman filtering (PSO-KF) algorithm to predict the SOH of the lithium battery, and although a better result is obtained, the method cannot accurately predict different types of lithium batteries.
The method cannot well take the accuracy and the generalization of prediction into consideration. Depending on the characteristics of lithium batteries, data-driven methods have become the mainstream method for estimating the SOH of lithium batteries. In recent years, methods such as Support Vector Machine (SVM), Gaussian Process Regression (GPR), Extreme Learning Machine (ELM), Random Forest (RF), Artificial Neural Network (ANN), BP neural network, etc. have been introduced into the SOH prediction field of lithium batteries. Although the methods can greatly improve the accuracy of prediction, the methods still have the problems of troublesome parameter adjustment, too long training time, weak generalization ability and the like.
Disclosure of Invention
In view of this, the present invention provides a method for estimating a health state of a lithium battery, which has the advantages of high precision, strong generalization capability, and the like, and can accurately and effectively estimate the health state of the lithium battery.
The invention is realized by adopting the following scheme: a lithium battery state of health estimation method includes but is not limited to the following steps:
selecting battery capacity as a state variable, and extracting a plurality of characteristics according to correlation analysis to be used as input and output data of a subsequent model so as to simulate the aging process of the lithium battery;
dividing the sample data into a training set and a test set (preferably, 80% of the obtained samples are used as the training set, and the remaining 20% of the samples are used as the test set), establishing a regression model based on a gradient lifting decision tree, performing parameter optimization on the regression model, and performing sample training to obtain a mixed algorithm regression training model;
and (4) estimating the health state of the lithium battery under the test set by utilizing a mixed algorithm regression training model.
The invention firstly analyzes a lithium battery data set, wherein the data set comprises electric data and environmental data recorded during each charging and discharging, and the method specifically comprises the following steps: the current, voltage, time, temperature, battery capacity and other data change conditions of the lithium battery during each charging and discharging process. The data set was obtained by conducting a series of charge and discharge experiments on several types of batteries including a commercial rechargeable lithium battery 18650, which mainly included two processes of charging and discharging. The charging process is started by constant current 1.5A, the voltage at two ends of the lithium battery can be increased along with the charging process, when the voltage is increased to 4.2V, the charging is started by constant voltage 4.2V, in the constant voltage charging process, the current at two ends of the battery can be gradually reduced, when the charging current is reduced to 20mA, the charging process is ended, and information such as the voltage, the current and the temperature is recorded at certain time intervals. The discharge process is started with a constant current state of 2A until the battery voltage drops to a set value.
Further, the selecting takes the battery capacity as a state variable, extracts a plurality of features according to correlation analysis to serve as input and output data of a subsequent model so as to simulate the aging process of the lithium battery, eliminates some abnormal data in the data set, selects the health state of the lithium battery as a regression, extracts 5 features with the highest correlation from the data set according to the data correlation analysis, and finally screens 168 data samples, and specifically comprises the following steps:
step S11: charging and discharging data in a lithium battery data set are extracted, charging and discharging are regarded as a cycle, abnormal data are removed, and N (168 can be selected as N) cycle period samples are obtained;
step S12: extracting characteristics including average charge-discharge voltage, average charge-discharge temperature, average charge-discharge current and charge-discharge time from samples of each cycle period, and taking the battery capacity extracted from a discharge curve as output;
step S13: and performing correlation analysis on the extracted features and the output, selecting n (n is preferably 5) features with highest correlation as input sample data of the model, and using the output as output sample data of the model.
Further, the establishing of the regression model based on the gradient boosting decision tree specifically includes the following steps:
step S21: the model is initialized to:
where c represents the mean of the label values of all training samples, yiIndicates the i-th battery SOH label value, L (y)iC) represents a loss function, N represents the number of training samples, f0(x) Represents the initial weak learner;
step S22: during each iteration, the value of the negative gradient of the loss function at the current model is calculated for the sample and taken as an estimate of the residual:
wherein m represents the number of iterations, i represents the sample number, rmiRepresenting the residual, x, of the ith sample for the mth iterationiRepresenting the ith training sample value, f (x)i) Base functions representing the ith training sample, fm-1(x) The weak learner obtained in the (m-1) th iteration is shown; wherein a negative gradient L (y)i,f(xi) The calculation of) uses a squared loss function as follows:
L(y,f(x))＝(y-f(x))2；
step S23: using the obtained residual error as a new true value of the sample, and using the data (x)i,rim) As training data for the next tree, a new regression tree f is obtainedm(x) The corresponding leaf node region is RjmWherein j is the number of leaf nodes of the regression tree; calculating a best fit value c for leaf region jmjComprises the following steps:
step S24: updating the strong learner to obtain:
in the formula, J represents the total number of leaf nodes of the regression tree, wherein:
obtaining a final regression tree F (x):
wherein F (x) represents the final regression tree, and M represents the total number of iterations;
obtaining a final learner H (x):
in the formula (f)M(x) Strong learner, f, indicating an update when the maximum number of iterations M is reached0(x) And (3) indicating an initialized weak learner, wherein the value of H (x) is the SOH estimation result of the lithium battery.
Further, the performing parameter optimization on the regression model specifically includes: and optimizing the parameters of the regression model by a mixed optimization algorithm based on the quantum particle swarm optimization algorithm and the simplex algorithm.
Further, the performing parameter optimization on the regression model specifically includes the following steps:
step S31: carrying out primary training on the parameters of the regression model by using a quantum particle group algorithm, and calculating a fitness function according to the parameters to obtain model parameters after primary optimization;
step S32: taking the preliminarily optimized model parameters obtained by the quantum particle swarm algorithm as initial values of the simplex algorithm, and further optimizing the model parameters;
step S33: and when the preset termination condition is met or the preset iteration times are reached, finishing the optimization, and finishing the parameter optimization of the regression model.
Compared with the prior art, the invention has the following beneficial effects: according to the lithium battery health state estimation method based on the hybrid optimization algorithm and the gradient boost decision tree regression model, the characteristic sample data with high correlation is obtained through data preprocessing and correlation analysis, and the lithium battery health state estimation method based on the hybrid optimization algorithm and the gradient boost decision tree regression model has high degree and stability and is extremely high in robustness and generalization capability. The method can adopt a hybrid optimization algorithm to optimize a regression model according to different battery types, firstly, a better value is found in a global range by utilizing stronger global search capability of a quantum particle swarm algorithm (QPSO), in order to overcome the defect that the QPSO is easy to fall into local optimization, the better value obtained by the QPSO is used as an initial value of a simplex algorithm (NMS), and the optimal model parameters are obtained by optimizing by utilizing stronger local search capability of the NMS, so that the corresponding optimal training model is finally obtained, and the most accurate estimation result is obtained.
Drawings
FIG. 1 is a schematic flow chart of a method according to an embodiment of the present invention.
Fig. 2 is a diagram illustrating the variation of battery capacity for various lithium battery types according to an embodiment of the present invention.
FIG. 3 is a scatter plot of the correlation of input features with output data according to an embodiment of the present invention. Wherein F1 to F5 are scatter plots of 5 with different correlations R.
Fig. 4 is a specific flowchart of optimizing regression model parameters by the hybrid optimization algorithm according to the embodiment of the present invention.
Fig. 5 is a comparison graph of estimated results and actual values of various lithium battery types according to an embodiment of the present invention. Wherein, (a) is the result of an experiment for Battery # 5, (b) is the result of an experiment for Battery # 6, and (c) is the result of an experiment for Battery # 7.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the present embodiment provides a method for estimating a state of health of a lithium battery, including, but not limited to, the following steps:
selecting battery capacity as a state variable, and extracting a plurality of characteristics according to correlation analysis to be used as input and output data of a subsequent model so as to simulate the aging process of the lithium battery;
dividing the sample data into a training set and a test set (preferably, 80% of the obtained samples are used as the training set, and the remaining 20% of the samples are used as the test set), establishing a regression model based on a gradient lifting decision tree, performing parameter optimization on the regression model, and performing sample training to obtain a mixed algorithm regression training model;
and estimating the health state of the lithium battery under the test set by using a mixed algorithm regression training model to obtain a final estimation curve.
In this embodiment, a lithium battery data set (in this embodiment, a NASA data set is selected) is first analyzed, where the data set includes electrical data and environmental data recorded during each charging and discharging, and the data set specifically includes: the current, voltage, time, temperature, battery capacity and other data change conditions of the lithium battery during each charging and discharging process. The data set was obtained by conducting a series of charge and discharge experiments on several types of batteries including a commercial rechargeable lithium battery 18650, which mainly included two processes of charging and discharging. The charging process is started by constant current 1.5A, the voltage at two ends of the lithium battery can be increased along with the charging process, when the voltage is increased to 4.2V, the charging is started by constant voltage 4.2V, in the constant voltage charging process, the current at two ends of the battery can be gradually reduced, when the charging current is reduced to 20mA, the charging process is ended, and information such as the voltage, the current and the temperature is recorded at certain time intervals. The discharge process is started with a constant current state of 2A until the battery voltage drops to a set value.
In this embodiment, the selecting takes battery capacity as a state variable, extracts a plurality of features according to correlation analysis as input and output data of a subsequent model to simulate an aging process of a lithium battery, removes some abnormal data in a data set, selects a health state of the lithium battery as a regression quantity, extracts 5 features with the highest correlation from the data set according to the data correlation analysis, and finally screens 168 data samples, wherein a battery capacity change diagram of a plurality of lithium battery types is shown in fig. 2, a data correlation analysis scatter diagram is shown in fig. 3, wherein F1-F5 are data after data preprocessing and abnormal data removal, and the method specifically includes the following steps:
step S11: charging and discharging data in a lithium battery data set are extracted, charging and discharging are regarded as a cycle, abnormal data are removed, and N (168 can be selected as N) cycle period samples are obtained;
step S12: extracting characteristics including average charge-discharge voltage, average charge-discharge temperature, average charge-discharge current and charge-discharge time from samples of each cycle period, and taking the battery capacity extracted from a discharge curve as output;
step S13: and performing correlation analysis on the extracted features and the output, selecting n (n is preferably 5) features with highest correlation as input sample data of the model, and using the output as output sample data of the model.
In this embodiment, the establishing of the regression model based on the gradient boosting decision tree specifically includes the following steps:
step S21: the model is initialized to:
where c represents the mean of the label values of all training samples, yiIndicates the i-th battery SOH label value, L (y)iC) represents a loss function, N represents the number of training samples, f0(x) Represents the initial weak learner;
step S22: during each iteration, the value of the negative gradient of the loss function at the current model is calculated for the sample and taken as an estimate of the residual:
where m denotes the number of iterations, i tableSample number, rmiRepresenting the residual, x, of the ith sample for the mth iterationiRepresenting the ith training sample value, f (x)i) Base functions representing the ith training sample, fm-1(x) The weak learner obtained in the (m-1) th iteration is shown; wherein a negative gradient L (y)i,f(xi) The calculation of) uses a squared loss function as follows:
L(y,f(x))＝(y-f(x))2；
step S23: using the obtained residual error as a new true value of the sample, and using the data (x)i,rim) As training data for the next tree, a new regression tree f is obtainedm(x) The corresponding leaf node region is RjmWherein j is the number of leaf nodes of the regression tree; calculating a best fit value c for leaf region jmjComprises the following steps:
step S24: updating the strong learner to obtain:
in the formula, J represents the total number of leaf nodes of the regression tree, wherein:
obtaining a final regression tree F (x):
wherein F (x) represents the final regression tree, and M represents the total number of iterations;
obtaining a final learner H (x):
in the formula (f)M(x) Strong learner, f, indicating an update when the maximum number of iterations M is reached0(x) And (3) indicating an initialized weak learner, wherein the value of H (x) is the SOH estimation result of the lithium battery.
Preferably, although the regression model based on the gradient lifting decision tree has the advantages of high prediction accuracy, short time consumption and the like, the model parameters are too many, manual parameter adjustment is too troublesome, and the advantages of strong global search capability of the quantum particle swarm algorithm and strong local search capability of the simplex algorithm are utilized, in this embodiment, a hybrid optimization algorithm based on the quantum particle swarm algorithm and the simplex algorithm is designed for optimizing the parameters of the regression model, the optimization flowchart is shown in fig. 4, and in this embodiment, the parameter optimization of the regression model specifically includes: and optimizing the parameters of the regression model by a mixed optimization algorithm based on the quantum particle swarm optimization algorithm and the simplex algorithm.
In this embodiment, the performing parameter optimization on the regression model specifically includes the following steps:
step S31: carrying out primary training on the parameters of the regression model by using a quantum particle group algorithm, and calculating a fitness function according to the parameters to obtain model parameters after primary optimization;
step S32: taking the preliminarily optimized model parameters obtained by the quantum particle swarm algorithm as initial values of the simplex algorithm, and further optimizing the model parameters;
step S33: and when the preset termination condition is met or the preset iteration times are reached, finishing the optimization, and finishing the parameter optimization of the regression model.
Further, in this embodiment, the estimation accuracy of the health state of the training model is very high, the estimation results are shown in (a), (b), and (c) in fig. 5, and for different types of lithium batteries, parameters do not need to be adjusted, the training estimation can be directly performed by using the hybrid optimization algorithm and the gradient boost decision tree regression model, and the estimation results of the health state of the different types of lithium batteries are shown in table 1.
TABLE 1 estimation accuracy of the method of the present invention for different battery models
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is directed to preferred embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. However, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (5)
1. A lithium battery state of health estimation method is characterized by comprising but not limited to the following steps:
selecting battery capacity as a state variable, and extracting a plurality of characteristics according to correlation analysis to be used as input and output data of a subsequent model so as to simulate the aging process of the lithium battery;
dividing the sample data into a training set and a test set, establishing a regression model based on a gradient lifting decision tree, performing parameter optimization on the regression model, and performing sample training to obtain a mixed algorithm regression training model;
and (4) estimating the health state of the lithium battery under the test set by utilizing a mixed algorithm regression training model.
2. The method for estimating the state of health of a lithium battery as claimed in claim 1, wherein the selecting takes the battery capacity as a state variable, and a plurality of features are extracted according to the correlation analysis as input and output data of a subsequent model to simulate the aging process of the lithium battery specifically comprises the following steps:
step S11: charging and discharging data in the lithium battery data set are extracted, charging and discharging are regarded as a cycle, and abnormal data are removed to obtain N cycle period samples;
step S12: extracting characteristics including average charge-discharge voltage, average charge-discharge temperature, average charge-discharge current and charge-discharge time from samples of each cycle period, and taking the battery capacity extracted from a discharge curve as output;
step S13: and performing correlation analysis on the extracted features and the output, selecting n features with highest correlation as input sample data of the model, and taking the output as output sample data of the model.
3. The method according to claim 1, wherein the establishing of the regression model based on the gradient boosting decision tree specifically comprises the following steps:
step S21: the model is initialized to:
where c represents the mean of the label values of all training samples, yiIndicates the i-th battery SOH label value, L (y)iC) represents a loss function, N represents the number of training samples, f0(x) Represents the initial weak learner;
step S22: during each iteration, the value of the negative gradient of the loss function at the current model is calculated for the sample and taken as an estimate of the residual:
wherein m represents the number of iterations, i represents the sample number, rmiRepresenting the residual, x, of the ith sample for the mth iterationiRepresenting the ith training sample value, f (x)i) Base functions representing the ith training sample, fm-1(x) The weak learner obtained in the (m-1) th iteration is shown; wherein a negative gradient L (y)i,f(xi) The calculation of) uses a squared loss function as follows:
L(y,f(x))＝(y-f(x))2；
step S23: using the obtained residual error as a new true value of the sample, and using the data (x)i,rim) Obtaining a new tree as training data of the next treeRegression tree fm(x) The corresponding leaf node region is RjmWherein j is the number of leaf nodes of the regression tree; calculating a best fit value c for leaf region jmjComprises the following steps:
step S24: updating the strong learner to obtain:
in the formula, J represents the total number of leaf nodes of the regression tree, wherein:
obtaining a final regression tree F (x):
wherein F (x) represents the final regression tree, and M represents the total number of iterations;
obtaining a final learner H (x):
in the formula (f)M(x) Strong learner, f, indicating an update when the maximum number of iterations M is reached0(x) And (3) indicating an initialized weak learner, wherein the value of H (x) is the SOH estimation result of the lithium battery.
4. The method for estimating the state of health of a lithium battery as claimed in claim 1, wherein the performing the parameter optimization on the regression model specifically comprises: and optimizing the parameters of the regression model by a mixed optimization algorithm based on the quantum particle swarm optimization algorithm and the simplex algorithm.
5. The method for estimating the state of health of a lithium battery as claimed in claim 4, wherein the performing the parameter optimization on the regression model specifically comprises the steps of:
step S31: carrying out primary training on the parameters of the regression model by using a quantum particle group algorithm, and calculating a fitness function according to the parameters to obtain model parameters after primary optimization;
step S32: taking the preliminarily optimized model parameters obtained by the quantum particle swarm algorithm as initial values of the simplex algorithm, and further optimizing the model parameters;
step S33: and when the preset termination condition is met or the preset iteration times are reached, finishing the optimization, and finishing the parameter optimization of the regression model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911402258.3A CN111044928A (en) | 2019-12-31 | 2019-12-31 | Lithium battery health state estimation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911402258.3A CN111044928A (en) | 2019-12-31 | 2019-12-31 | Lithium battery health state estimation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111044928A true CN111044928A (en) | 2020-04-21 |
Family
ID=70242828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911402258.3A Pending CN111044928A (en) | 2019-12-31 | 2019-12-31 | Lithium battery health state estimation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111044928A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111641236A (en) * | 2020-05-27 | 2020-09-08 | 上海电享信息科技有限公司 | Dynamic threshold power battery charging voltage state judgment method based on big data AI |
| CN111965545A (en) * | 2020-07-31 | 2020-11-20 | 蜂巢能源科技有限公司 | Lithium battery self-discharge detection method, device and system |
| CN111976543A (en) * | 2020-07-20 | 2020-11-24 | 南京工程学院 | Charging and discharging control method for battery pack of electric automobile |
| CN111999649A (en) * | 2020-08-20 | 2020-11-27 | 浙江工业大学 | XGboost algorithm-based lithium battery residual life prediction method |
| CN112269134A (en) * | 2020-09-10 | 2021-01-26 | 杭州电子科技大学 | Battery SOC and SOH joint estimation method based on deep learning |
| CN112379295A (en) * | 2020-09-29 | 2021-02-19 | 合肥工业大学 | Method, system and storage medium for predicting health state of power battery |
| CN112485689A (en) * | 2020-10-26 | 2021-03-12 | 江苏慧智能源工程技术创新研究院有限公司 | Method for predicting residual cycle life of lithium battery in energy storage system based on Xgboost model |
| CN113180623A (en) * | 2021-06-01 | 2021-07-30 | 山东大学 | Sleeveless blood pressure measuring method, sleeveless blood pressure measuring system, sleeveless blood pressure measuring equipment and storage medium |
| CN113255215A (en) * | 2021-05-19 | 2021-08-13 | 四川大学 | Lithium battery health state estimation method based on voltage segments |
| CN113567875A (en) * | 2021-06-11 | 2021-10-29 | 国电南瑞科技股份有限公司 | Ternary lithium ion battery health state estimation method based on K nearest neighbor regression |
| CN113567863A (en) * | 2021-06-11 | 2021-10-29 | 北京航空航天大学 | Abnormal degraded lithium battery capacity prediction method based on quantum assimilation and data filling |
| CN113671401A (en) * | 2021-08-30 | 2021-11-19 | 武汉理工大学 | Lithium battery health state assessment method based on optimization algorithm and data driving |
| CN114014120A (en) * | 2021-12-01 | 2022-02-08 | 嘉兴市特种设备检验检测院 | Elevator braking performance prediction method and device and storage medium |
| CN114236415A (en) * | 2021-12-16 | 2022-03-25 | 湖北亿纬动力有限公司 | Power battery health state detection method, device, equipment and storage medium |
| CN114298507A (en) * | 2021-12-17 | 2022-04-08 | 欣旺达电子股份有限公司 | Lithium battery failure determination method, model generation method, device and storage medium |
| CN114295999A (en) * | 2021-12-30 | 2022-04-08 | 国网浙江省电力有限公司电力科学研究院 | Lithium ion battery SOH prediction method and system based on indirect health index |
| CN116413609A (en) * | 2023-06-08 | 2023-07-11 | 江苏正力新能电池技术有限公司 | Battery diving identification method and device, electronic equipment and storage medium |
| WO2023202098A1 (en) * | 2022-04-19 | 2023-10-26 | 深圳先进技术研究院 | Lithium battery formation stage product quality prediction method and system |
| CN117009876A (en) * | 2023-10-07 | 2023-11-07 | 长春光华学院 | Motion state quantity evaluation method based on artificial intelligence |
| CN117074957A (en) * | 2023-08-18 | 2023-11-17 | 南京林业大学 | Lithium ion battery residual service life prediction method based on digital-analog fusion |
| WO2024016496A1 (en) * | 2022-07-20 | 2024-01-25 | 东风柳州汽车有限公司 | Method and apparatus for estimating soh of lithium battery |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107291668A (en) * | 2017-07-14 | 2017-10-24 | 中南大学 | A kind of subway based on machine learning passenger flow forecasting in short-term |
| CN108896914A (en) * | 2018-05-11 | 2018-11-27 | 浙江工业大学 | A kind of modeling of gradient boosted tree and prediction technique of lithium battery health status |
| CN109031153A (en) * | 2018-10-16 | 2018-12-18 | 北京交通大学 | A kind of health status On-line Estimation method of lithium ion battery |
| CN109856545A (en) * | 2019-03-28 | 2019-06-07 | 哈尔滨学院 | The battery group residual capacity detection method and system of solar telephone |
| CN110208705A (en) * | 2019-05-09 | 2019-09-06 | 赛尔网络有限公司 | A kind of lithium battery method for predicting residual useful life and device |
-
2019
- 2019-12-31 CN CN201911402258.3A patent/CN111044928A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107291668A (en) * | 2017-07-14 | 2017-10-24 | 中南大学 | A kind of subway based on machine learning passenger flow forecasting in short-term |
| CN108896914A (en) * | 2018-05-11 | 2018-11-27 | 浙江工业大学 | A kind of modeling of gradient boosted tree and prediction technique of lithium battery health status |
| CN109031153A (en) * | 2018-10-16 | 2018-12-18 | 北京交通大学 | A kind of health status On-line Estimation method of lithium ion battery |
| CN109856545A (en) * | 2019-03-28 | 2019-06-07 | 哈尔滨学院 | The battery group residual capacity detection method and system of solar telephone |
| CN110208705A (en) * | 2019-05-09 | 2019-09-06 | 赛尔网络有限公司 | A kind of lithium battery method for predicting residual useful life and device |
Non-Patent Citations (2)
| Title |
|---|
| 王喜宾 等: "《基于优化支持向量机的个性化推荐研究》", 30 June 2017, 重庆：重庆大学出版社 * |
| 齐宏 等: "《辐射传输逆问题的智能优化理论与应用》", 31 March 2016, 哈尔滨：哈尔滨工业大学出版社 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111641236A (en) * | 2020-05-27 | 2020-09-08 | 上海电享信息科技有限公司 | Dynamic threshold power battery charging voltage state judgment method based on big data AI |
| CN111641236B (en) * | 2020-05-27 | 2023-04-14 | 上海电享信息科技有限公司 | Dynamic threshold power battery charging voltage state judgment method based on big data AI |
| CN111976543A (en) * | 2020-07-20 | 2020-11-24 | 南京工程学院 | Charging and discharging control method for battery pack of electric automobile |
| CN111976543B (en) * | 2020-07-20 | 2023-01-31 | 南京工程学院 | Charging and discharging control method for battery pack of electric automobile |
| CN111965545A (en) * | 2020-07-31 | 2020-11-20 | 蜂巢能源科技有限公司 | Lithium battery self-discharge detection method, device and system |
| CN111999649A (en) * | 2020-08-20 | 2020-11-27 | 浙江工业大学 | XGboost algorithm-based lithium battery residual life prediction method |
| CN112269134A (en) * | 2020-09-10 | 2021-01-26 | 杭州电子科技大学 | Battery SOC and SOH joint estimation method based on deep learning |
| CN112269134B (en) * | 2020-09-10 | 2022-12-02 | 杭州电子科技大学 | Battery SOC and SOH joint estimation method based on deep learning |
| CN112379295A (en) * | 2020-09-29 | 2021-02-19 | 合肥工业大学 | Method, system and storage medium for predicting health state of power battery |
| CN112379295B (en) * | 2020-09-29 | 2023-08-04 | 合肥工业大学 | Method, system and storage medium for predicting power battery health status |
| CN112485689A (en) * | 2020-10-26 | 2021-03-12 | 江苏慧智能源工程技术创新研究院有限公司 | Method for predicting residual cycle life of lithium battery in energy storage system based on Xgboost model |
| CN112485689B (en) * | 2020-10-26 | 2024-02-06 | 沃太能源股份有限公司 | Method for predicting residual cycle life of lithium battery in energy storage system based on Xgboost model |
| CN113255215A (en) * | 2021-05-19 | 2021-08-13 | 四川大学 | Lithium battery health state estimation method based on voltage segments |
| CN113180623A (en) * | 2021-06-01 | 2021-07-30 | 山东大学 | Sleeveless blood pressure measuring method, sleeveless blood pressure measuring system, sleeveless blood pressure measuring equipment and storage medium |
| CN113567863A (en) * | 2021-06-11 | 2021-10-29 | 北京航空航天大学 | Abnormal degraded lithium battery capacity prediction method based on quantum assimilation and data filling |
| CN113567875A (en) * | 2021-06-11 | 2021-10-29 | 国电南瑞科技股份有限公司 | Ternary lithium ion battery health state estimation method based on K nearest neighbor regression |
| CN113671401A (en) * | 2021-08-30 | 2021-11-19 | 武汉理工大学 | Lithium battery health state assessment method based on optimization algorithm and data driving |
| CN114014120A (en) * | 2021-12-01 | 2022-02-08 | 嘉兴市特种设备检验检测院 | Elevator braking performance prediction method and device and storage medium |
| CN114236415A (en) * | 2021-12-16 | 2022-03-25 | 湖北亿纬动力有限公司 | Power battery health state detection method, device, equipment and storage medium |
| CN114298507A (en) * | 2021-12-17 | 2022-04-08 | 欣旺达电子股份有限公司 | Lithium battery failure determination method, model generation method, device and storage medium |
| CN114295999A (en) * | 2021-12-30 | 2022-04-08 | 国网浙江省电力有限公司电力科学研究院 | Lithium ion battery SOH prediction method and system based on indirect health index |
| WO2023202098A1 (en) * | 2022-04-19 | 2023-10-26 | 深圳先进技术研究院 | Lithium battery formation stage product quality prediction method and system |
| WO2024016496A1 (en) * | 2022-07-20 | 2024-01-25 | 东风柳州汽车有限公司 | Method and apparatus for estimating soh of lithium battery |
| CN116413609A (en) * | 2023-06-08 | 2023-07-11 | 江苏正力新能电池技术有限公司 | Battery diving identification method and device, electronic equipment and storage medium |
| CN116413609B (en) * | 2023-06-08 | 2023-08-29 | 江苏正力新能电池技术有限公司 | Battery diving identification method and device, electronic equipment and storage medium |
| CN117074957A (en) * | 2023-08-18 | 2023-11-17 | 南京林业大学 | Lithium ion battery residual service life prediction method based on digital-analog fusion |
| CN117074957B (en) * | 2023-08-18 | 2024-05-24 | 南京林业大学 | Lithium ion battery residual service life prediction method based on digital-analog fusion |
| CN117009876A (en) * | 2023-10-07 | 2023-11-07 | 长春光华学院 | Motion state quantity evaluation method based on artificial intelligence |
| CN117009876B (en) * | 2023-10-07 | 2024-01-09 | 长春光华学院 | Motion state quantity evaluation method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111044928A (en) | Lithium battery health state estimation method | |
| Wang et al. | An improved feedforward-long short-term memory modeling method for the whole-life-cycle state of charge prediction of lithium-ion batteries considering current-voltage-temperature variation | |
| CN107785624B (en) | Method for evaluating performance of lithium battery | |
| CN110850298B (en) | Lithium battery SOH estimation method and system based on data driving | |
| CN109001640B (en) | Data processing method and device for power battery | |
| CN110658460B (en) | Battery life prediction method and device for battery pack | |
| CN112380630B (en) | New energy automobile battery thermal runaway risk prediction method based on Internet of vehicles data | |
| CN105093122A (en) | Strong-tracking self-adaptive-SQKF-based SOC estimation method of emergency lamp battery | |
| CN110443377B (en) | Support vector machine storage battery life prediction method based on immune algorithm optimization | |
| CN112230154A (en) | Lithium battery residual life prediction method | |
| CN113109717B (en) | Lithium battery state of charge estimation method based on characteristic curve optimization | |
| CN113777510A (en) | Lithium battery state of charge estimation method and device | |
| CN112083346A (en) | LSTM-based parallel battery pack internal current distribution estimation method and system | |
| CN113075569A (en) | Battery state of charge estimation method and device based on noise adaptive particle filtering | |
| CN108872865B (en) | Lithium battery SOC estimation method for preventing filtering divergence | |
| CN115407211B (en) | Online prediction method and system for health state of lithium battery of electric vehicle | |
| CN115792680A (en) | Retired battery health state assessment method based on Bayes deep learning | |
| CN113139570A (en) | Dam safety monitoring data completion method based on optimal hybrid valuation | |
| CN114035087B (en) | Method, device, equipment and medium for evaluating residual life of energy storage battery | |
| CN115586444A (en) | Lithium battery residual life prediction method based on VMD and BP neural network | |
| CN110232432B (en) | Lithium battery pack SOC prediction method based on artificial life model | |
| CN112698217B (en) | Battery monomer capacity estimation method based on particle swarm optimization algorithm | |
| CN117471320A (en) | Battery state of health estimation method and system based on charging fragments | |
| CN111948561B (en) | Battery life prediction method based on actual measurement big data and artificial intelligence learning algorithm | |
| CN113884915A (en) | Method and system for predicting state of charge and state of health of lithium ion battery |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200421 |