CN117214762A - Lithium battery remaining life prediction method, device, equipment and storage medium - Google Patents
Lithium battery remaining life prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117214762A CN117214762A CN202311412905.5A CN202311412905A CN117214762A CN 117214762 A CN117214762 A CN 117214762A CN 202311412905 A CN202311412905 A CN 202311412905A CN 117214762 A CN117214762 A CN 117214762A
- Authority
- CN
- China
- Prior art keywords
- life
- lithium battery
- support vector
- vector machine
- machine model
- 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
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 98
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012706 support-vector machine Methods 0.000 claims abstract description 101
- 238000012360 testing method Methods 0.000 claims abstract description 25
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000002790 cross-validation Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 24
- 238000012795 verification Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 14
- 230000015556 catabolic process Effects 0.000 claims description 10
- 238000006731 degradation reaction Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000007600 charging Methods 0.000 description 1
- 238000010280 constant potential charging Methods 0.000 description 1
- 238000010277 constant-current charging Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000003487 electrochemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- 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
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The application discloses a method, a device, equipment and a storage medium for predicting the residual life of a lithium battery, wherein full life test data are obtained by obtaining residual life data of the lithium battery to be tested in different charge and discharge periods; constructing a support vector machine model according to the life test data; screening out the optimal penalty factor and kernel function parameter of the support vector machine model by adopting a K-fold cross validation method; optimizing the support vector machine model by using a Kalman algorithm to obtain an updated equation of the residual life; and inputting the operation data of the lithium battery to be tested into the optimized support vector machine model for life prediction, and outputting the residual life. The application can stably and accurately calculate the residual life of the lithium battery.
Description
Technical Field
The present application relates to the field of battery detection technologies, and in particular, to a method, an apparatus, a device, and a storage medium for predicting a remaining life of a lithium battery.
Background
The life or remaining service life of a battery is defined as the remaining operating period from the current time to the time the battery reaches its service life, typically set to an operating time corresponding to a 20% capacity fade. Accurate prediction of remaining life is critical to intelligent prediction and health management of batteries.
The life prediction method of the battery can be mainly divided into a prediction method based on an equivalent circuit model and a data-driven prediction method. The prediction method based on the equivalent circuit model approximates parameters in the model by simulating the battery process. But battery degradation is dynamic and nonlinear. This makes it difficult to monitor the internal state of the battery because the operating conditions (such as temperature and power) are constantly changing. In addition, the accuracy of prediction requires multiple parameters and complex calculations due to uncertainty factors, requires a large amount of data, and also depends on impedance data, so the prediction accuracy is low. The data-driven life prediction method does not require electrochemical reactions or accurate system information. The data driving method is simple in calculation and suitable for a nonlinear system. Therefore, the data driving method is widely used for the remaining life prediction of lithium batteries. However, the traditional data driving method excessively depends on the individual degradation state data of the battery in the modeling process, and when the individual difference of the battery is large, the residual life prediction result is not stable enough. Therefore, a method for stably and accurately calculating the remaining life of a battery is needed.
Disclosure of Invention
In view of the above drawbacks, the present application provides a method, apparatus, device and storage medium for predicting the remaining life of a lithium battery, which can calculate the remaining life of the lithium battery stably and accurately.
The embodiment of the application provides a method for predicting the residual life of a lithium battery, which comprises the following steps:
obtaining residual life data of the lithium battery to be tested in different charge and discharge periods to obtain full life test data;
constructing a support vector machine model according to the life test data;
screening out the optimal penalty factor and kernel function parameter of the support vector machine model by adopting a K-fold cross validation method;
optimizing the support vector machine model by using a Kalman algorithm to obtain an updated equation of the residual life;
and inputting the operation data of the lithium battery to be tested into the optimized support vector machine model for life prediction, and outputting the residual life.
As a preferable scheme, the remaining service life rul=l+1-i of the lithium battery to be tested in each charge-discharge cycle;
wherein L is the total charge-discharge cycle number of the battery which is experienced from the initial degradation to the failure, and i is the current charge-discharge cycle number of the battery.
Preferably, the constructing a support vector machine model according to the life test data specifically includes:
with nth charge-discharge cyclet n And taking the residual life of the battery at the moment as an input variable of the support vector machine, and taking the residual life index as an output variable of the support vector machine to construct the support vector machine model.
As an improvement of the previous embodiment, the residual lifetime prior prediction value RUL in the support vector machine model n - ＝E[RUL n ∣x n-1 ,x n-2 ,…,x 1 ,S]；
Residual life posterior predictive value RUL in support vector machine model n + ＝E[RUL n ∣x n ,x n-1 ,…,x 1 ,S]；
Mean square error of residual life posterior predictive value in the support vector machine modelMean square error of residual life priori predicted value in the support vector machine model>
Wherein RUL - n T of the nth charge-discharge cycle of the lithium battery to be tested n Time-of-day residual life priori prediction value RUL + n T of the nth charge-discharge cycle of the lithium battery to be tested n Time residual life posterior predictive value, x n T of the nth charge-discharge cycle of the lithium battery to be tested n The remaining life index value S at the time is the full life data.
Preferably, the filtering out the optimal penalty factor and kernel function parameter of the support vector machine model by using a K-fold cross validation method specifically includes:
dividing the original data into K groups, wherein each time, one subset is not repeatedly extracted from the original data to serve as a verification set, and the rest K-1 groups of subset data are combined together to serve as a training set;
respectively training the support vector machine model by using K groups of data to obtain K trained models, and cross-verifying the performance index of the support vector machine model by using the average number of the accuracy of the K trained model verification sets as K folds;
and selecting the optimal penalty factors and kernel function parameters in the performance indexes to output.
Preferably, the optimizing the support vector machine model by using a kalman algorithm obtains an updated equation of the remaining life, which specifically includes:
calculating t of the lithium battery to be tested in the nth charge-discharge cycle according to the support vector machine model n A residual life priori predicted value and a mean square error thereof at the moment;
estimating t according to the residual life priori predicted value and the mean square error thereof n The remaining life state index value of the lithium battery to be tested is obtained at the moment;
correcting the position of the lithium battery to be detected at t according to the residual life index value n A residual life priori predicted value at moment and a mean square error thereof are obtained, and t of the lithium battery to be detected in the nth charge and discharge cycle is obtained n And determining a residual life posterior predicted value and a mean square error thereof at the moment, and determining an updating equation of the residual life.
The embodiment of the application provides a lithium battery remaining life prediction device, which comprises:
the data acquisition module is used for acquiring residual life data of the lithium battery to be tested in different charge and discharge cycles to obtain full life test data;
the model construction module is used for constructing a support vector machine model according to the life test data;
the screening module is used for screening out the optimal penalty factors and kernel function parameters of the support vector machine model by adopting a K-fold cross validation method;
the updating module is used for optimizing the support vector machine model by using a Kalman algorithm to obtain an updating equation of the residual life;
and the prediction module is used for inputting the operation data of the lithium battery to be detected into the optimized support vector machine model to perform life prediction and outputting the residual life.
Preferably, the remaining life rul=l+1-i of the lithium battery to be tested in each charge-discharge cycle;
wherein L is the total charge-discharge cycle number of the battery which is experienced from the initial degradation to the failure, and i is the current charge-discharge cycle number of the battery.
As a preferred solution, the model building module is specifically configured to:
t in nth charge-discharge cycle n And taking the residual life of the battery at the moment as an input variable of the support vector machine, and taking the residual life index as an output variable of the support vector machine to construct the support vector machine model.
Further, the residual life priori prediction value RUL in the support vector machine model n - ＝E[RUL n ∣x n-1 ,x n-2 ,…,x 1 ,S]；
Residual life posterior predictive value RUL in support vector machine model n + ＝E[RUL n ∣x n ,x n-1 ,…,x 1 ,S]；
Mean square error of residual life posterior predictive value in the support vector machine modelMean square error of residual life priori predicted value in the support vector machine model>
Wherein RUL - n T of the nth charge-discharge cycle of the lithium battery to be tested n Time-of-day residual life priori prediction value RUL + n T of the nth charge-discharge cycle of the lithium battery to be tested n Time residual life posterior predictive value, x n T of the nth charge-discharge cycle of the lithium battery to be tested n The remaining life index value S at the time is the full life data.
Preferably, the screening module is specifically configured to:
dividing the original data into K groups, wherein each time, one subset is not repeatedly extracted from the original data to serve as a verification set, and the rest K-1 groups of subset data are combined together to serve as a training set;
respectively training the support vector machine model by using K groups of data to obtain K trained models, and cross-verifying the performance index of the support vector machine model by using the average number of the accuracy of the K trained model verification sets as K folds;
and selecting the optimal penalty factors and kernel function parameters in the performance indexes to output.
Preferably, the updating module is specifically configured to:
calculating t of the lithium battery to be tested in the nth charge-discharge cycle according to the support vector machine model n A residual life priori predicted value and a mean square error thereof at the moment;
estimating t according to the residual life priori predicted value and the mean square error thereof n The remaining life state index value of the lithium battery to be tested is obtained at the moment;
correcting the position of the lithium battery to be detected at t according to the residual life index value n A residual life priori predicted value at moment and a mean square error thereof are obtained, and t of the lithium battery to be detected in the nth charge and discharge cycle is obtained n And determining a residual life posterior predicted value and a mean square error thereof at the moment, and determining an updating equation of the residual life.
The embodiment of the application also provides a terminal device, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the lithium battery remaining life prediction method according to any one of the above embodiments.
The embodiment of the application also provides a computer readable storage medium, which comprises a stored computer program, wherein the computer program controls equipment where the computer readable storage medium is located to execute the lithium battery remaining life prediction method according to any one of the above embodiments when running.
According to the method, the device, the equipment and the storage medium for predicting the residual life of the lithium battery, provided by the application, the full life test data are obtained by obtaining the residual life data of the lithium battery to be tested in different charge and discharge cycles; constructing a support vector machine model according to the life test data; screening out the optimal penalty factor and kernel function parameter of the support vector machine model by adopting a K-fold cross validation method; optimizing the support vector machine model by using a Kalman algorithm to obtain an updated equation of the residual life; and inputting the operation data of the lithium battery to be tested into the optimized support vector machine model for life prediction, and outputting the residual life. The application can stably and accurately calculate the residual life of the lithium battery.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting remaining life of a lithium battery according to an embodiment of the present application;
fig. 2 is a schematic diagram of a K-fold cross-validation method according to an embodiment of the present application;
FIG. 3 is a flow chart of a remaining lifetime updating process provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of a verification result provided by an embodiment of the present application;
fig. 5 is a schematic structural diagram of a lithium battery remaining life prediction apparatus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, a flow chart of a method for predicting remaining life of a lithium battery according to an embodiment of the present application is provided, and the method includes steps S1 to S5:
s1, obtaining residual life data of a lithium battery to be tested in different charge and discharge periods to obtain full life test data;
s2, constructing a support vector machine model according to the life test data;
s3, screening out the optimal penalty factors and kernel function parameters of the support vector machine model by adopting a K-fold cross validation method;
s4, optimizing the support vector machine model by using a Kalman algorithm to obtain an update equation of the residual life;
s5, inputting the lithium battery operation data to be predicted into the optimized support vector machine model for life prediction, and outputting the residual life.
When the embodiment is implemented, full life test data of the lithium battery to be tested, namely remaining life data of the battery in different charge and discharge cycles, are obtained and used as a training set of a life prediction algorithm.
And constructing a support vector machine model by using the full life cycle test data of the lithium battery to be tested.
And screening out the optimal penalty factor and kernel function parameter of the support vector machine model by using a K-fold cross validation method.
And optimizing the support vector machine model by using a Kalman algorithm to obtain an updated equation of the residual life.
And inputting the operation data of the lithium battery to be tested into the optimized SVM residual life prediction model to perform life prediction, and outputting the residual life of the lithium battery to be tested.
The application combines a support vector machine and a nonlinear Kalman filter, wherein the support vector machine model uses the existing life-cycle test data, and an update equation of the nonlinear Kalman filter state is established based on the existing life-cycle test data. The time update equation takes into account the degradation characteristic construction of the lithium battery. The initial remaining life value and its variance are set, and the remaining life estimation value at each time and the confidence interval of a certain confidence level are calculated by stepwise iteration. The calculation model effectively utilizes the full life test data of the existing and similar batteries and the real-time state degradation data of the predicted battery to realize the prediction of the residual life, and can calculate the residual life of the lithium battery stably and accurately.
In yet another embodiment provided by the present application, the remaining lifetime rul=l+1-i of the lithium battery to be tested in each charge-discharge cycle;
wherein L is the total charge-discharge cycle number of the battery which is experienced from the initial degradation to the failure, and i is the current charge-discharge cycle number of the battery.
When the embodiment is implemented, full life test data of the lithium battery, namely remaining life data of the battery in different charge and discharge cycles, are obtained and used as a training set of a life prediction algorithm.
In the charging process, first constant current charging is performed, the current is set to a constant value, and the voltage is raised to the maximum upper limit. The voltage is kept at a constant value, which is called constant voltage charging. When the voltage is kept at a constant value, the current drops to a certain threshold value.
In the discharging process, the battery is firstly discharged at a constant current with a specific current value until the voltages of different lithium batteries are respectively reduced to specific voltage values.
The remaining life of the battery in each charge-discharge cycle is calculated as follows:
RUL＝L+1-i
wherein L is the total charge-discharge cycle number of the battery which is experienced from the initial degradation to the failure, and i is the current charge-discharge cycle number of the battery.
In yet another embodiment of the present application, the step S2 specifically includes:
t in nth charge-discharge cycle n And taking the residual life of the battery at the moment as an input variable of the support vector machine, and taking the residual life index as an output variable of the support vector machine to construct the support vector machine model.
In the embodiment, the support vector machine model is constructed according to the life cycle test data of the lithium battery to be tested by the nth charge-discharge cycle, namely t n Time of day battery remaining life RUL n As an input variable of a support vector machine, the residual life index x is used n And constructing the support vector machine model as an output variable of the support vector machine.
In a further embodiment of the present application, the residual lifetime prior predictor RUL in the support vector machine model n - ＝E[RUL n ∣x n-1 ,x n-2 ,…,x 1 ,S]；
Residual life posterior predictive value RUL in support vector machine model n + ＝E[RUL n ∣x n ,x n-1 ,…,x 1 ,S]；
Mean square error of residual life posterior predictive value in the support vector machine modelMean square error of residual life priori predicted value in the support vector machine model>
Wherein RUL - n T of the nth charge-discharge cycle of the lithium battery to be tested n Time-of-day residual life priori prediction value RUL + n T of the nth charge-discharge cycle of the lithium battery to be tested n Time residual life posterior predictive value, x n T of the nth charge-discharge cycle of the lithium battery to be tested n The remaining life index value S at the time is the full life data.
In the embodiment, t is n The battery residual life RULn at the moment is taken as an input variable of a support vector machine and is used as a residual life index x n And determining the support vector machine model as an output variable of the support vector machine.
The residual life priori prediction value RUL in the support vector machine model n - ＝E[RUL n ∣x n-1 ,x n-2 ,…,x 1 ,S]；
Residual life posterior predictive value RUL in support vector machine model n + ＝E[RUL n ∣x n ,x n-1 ,…,x 1 ,S]；
Mean square error of residual life posterior predictive value in the support vector machine modelResidual life in the support vector machine model is firstMean square error of the experimental prediction value ∈ ->
Wherein RUL - n T of the nth charge-discharge cycle of the lithium battery to be tested n Time-of-day residual life priori prediction value RUL + n T of the nth charge-discharge cycle of the lithium battery to be tested n Time residual life posterior predictive value, x n T of the nth charge-discharge cycle of the lithium battery to be tested n The remaining life index value S at the time is the full life data.
In yet another embodiment of the present application, the step S3 specifically includes:
dividing the original data into K groups, wherein each time, one subset is not repeatedly extracted from the original data to serve as a verification set, and the rest K-1 groups of subset data are combined together to serve as a training set;
respectively training the support vector machine model by using K groups of data to obtain K trained models, and cross-verifying the performance index of the support vector machine model by using the average number of the accuracy of the K trained model verification sets as K folds;
and selecting the optimal penalty factors and kernel function parameters in the performance indexes to output.
In the implementation of this embodiment, referring to fig. 2, which is a schematic diagram of a K-fold cross validation method provided by the embodiment of the present application, the K-fold cross validation method is used to screen out an optimal penalty factor c and a kernel function parameter γ of a support vector machine, and the specific process includes:
the raw data is divided into K groups, one subset is not repeatedly extracted from the K groups as a verification set at a time, and the remaining K-1 group subset data are combined together as a training set.
And respectively training the vector machine by using the K groups of data to obtain K models, and taking the average number of the accuracy of the K model verification sets as the performance index of the K-fold cross verification support vector machine prediction model.
And selecting the collocation of the penalty factors and the kernel function parameters with the best performance indexes as the optimal model parameters of the support vector machine, and determining the optimal penalty factors and the kernel function parameters of the support vector machine model.
In yet another embodiment of the present application, the step S4 specifically includes:
calculating t of the lithium battery to be tested in the nth charge-discharge cycle according to the support vector machine model n A residual life priori predicted value and a mean square error thereof at the moment;
estimating t according to the residual life priori predicted value and the mean square error thereof n The remaining life state index value of the lithium battery to be tested is obtained at the moment;
correcting the position of the lithium battery to be detected at t according to the residual life index value n A residual life priori predicted value at moment and a mean square error thereof are obtained, and t of the lithium battery to be detected in the nth charge and discharge cycle is obtained n And determining a residual life posterior predicted value and a mean square error thereof at the moment, and determining an updating equation of the residual life.
In the implementation of this embodiment, referring to fig. 3, a flow chart of a remaining lifetime updating process provided in the embodiment of the present application is shown, where the remaining lifetime updating process includes the following steps:
calculating t of the lithium battery to be tested in the nth charge-discharge cycle according to the support vector machine model n Time-of-day remaining life priori prediction value RUL - n And its mean square error sum P - n 。
According to the residual life priori prediction value RUL - n And its mean square error sum P - n Estimating t n Remaining life state index value x of lithium battery to be measured at moment n 。
According to t n Time remaining life state index value x n Correcting residual life priori prediction value RUL - n And its mean square error sum P - n Obtain data S and t based on the whole life n Residual life posterior predictive value RUL of moment residual life state index value + n And its mean square error sum P + n An updated equation for the remaining life is determined.
The method is verified by utilizing the accelerated aging data of the lithium battery in the NASA database, referring to fig. 4, which is a schematic diagram of a verification result provided by the embodiment of the application, based on the aging result of the lithium battery shown in fig. 4, the difference between the predicted value obtained by prediction based on the upper limit and the lower limit and the actual value is smaller, and the predicted value method can accurately predict the residual life of the battery in the degradation stage.
The embodiment of the application also provides a device for predicting the remaining life of a lithium battery, referring to fig. 5, which is a schematic structural diagram of the device for predicting the remaining life of a lithium battery, provided by the embodiment of the application, wherein the device comprises:
the data acquisition module is used for acquiring residual life data of the lithium battery to be tested in different charge and discharge cycles to obtain full life test data;
the model construction module is used for constructing a support vector machine model according to the life test data;
the screening module is used for screening out the optimal penalty factors and kernel function parameters of the support vector machine model by adopting a K-fold cross validation method;
the updating module is used for optimizing the support vector machine model by using a Kalman algorithm to obtain an updating equation of the residual life;
and the prediction module is used for inputting the operation data of the lithium battery to be detected into the optimized support vector machine model to perform life prediction and outputting the residual life.
It should be noted that, the lithium battery remaining life prediction device provided in the embodiment of the present application can execute the lithium battery remaining life prediction method described in any embodiment of the foregoing embodiments, and specific functions of the lithium battery remaining life prediction device are not described herein.
Referring to fig. 6, a schematic structural diagram of a terminal device according to an embodiment of the present application is provided. The terminal device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a lithium battery remaining life prediction program. The processor executes the computer program to implement the steps in the above embodiments of the method for predicting remaining life of lithium batteries, for example, steps S1 to S5 shown in fig. 1. Alternatively, the processor may implement the functions of the modules in the above-described device embodiments when executing the computer program.
The computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor to accomplish the present application, for example. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program in the terminal device. For example, the computer program may be divided into modules, and specific functions of each module are not described herein.
The terminal equipment can be computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The terminal device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of a terminal device and does not constitute a limitation of the terminal device, and may include more or less components than illustrated, or may combine certain components, or different components, e.g., the terminal device may further include an input-output device, a network access device, a bus, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the terminal device, and which connects various parts of the entire terminal device using various interfaces and lines.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the terminal device by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
Wherein the terminal device integrated modules/units may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as stand alone products. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code, which may be in the form of code, object code, executable files, or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
While the foregoing is directed to the preferred embodiments of the present application, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the application, such changes and modifications are also intended to be within the scope of the application.
Claims (10)
1. A method for predicting remaining life of a lithium battery, the method comprising:
obtaining residual life data of the lithium battery to be tested in different charge and discharge periods to obtain full life test data;
constructing a support vector machine model according to the life test data;
screening out the optimal penalty factor and kernel function parameter of the support vector machine model by adopting a K-fold cross validation method;
optimizing the support vector machine model by using a Kalman algorithm to obtain an updated equation of the residual life;
and inputting the operation data of the lithium battery to be tested into the optimized support vector machine model for life prediction, and outputting the residual life.
2. The method for predicting the remaining life of a lithium battery according to claim 1, wherein the remaining life rul=l+1-i of the lithium battery to be measured in each charge-discharge cycle;
wherein L is the total charge-discharge cycle number of the battery which is experienced from the initial degradation to the failure, and i is the current charge-discharge cycle number of the battery.
3. The method for predicting the remaining life of a lithium battery according to claim 1, wherein the constructing a support vector machine model according to the full life test data comprises:
t in nth charge-discharge cycle n And taking the residual life of the battery at the moment as an input variable of the support vector machine, and taking the residual life index as an output variable of the support vector machine to construct the support vector machine model.
4. The method for predicting remaining life of lithium battery as claimed in claim 3, wherein the remaining life priori predicted value RUL in the support vector machine model n - ＝E[RUL n ∣x n-1 ,x n-2 ,…,x 1 ,S]；
Residual life posterior predictive value RUL in support vector machine model n + ＝E[RUL n ∣x n ,x n-1 ,…,x 1 ,S]；
Mean square error of residual life posterior predictive value in the support vector machine modelMean square error of residual life priori predicted value in the support vector machine model>
Wherein RUL - n T of the nth charge-discharge cycle of the lithium battery to be tested n Time-of-day residual life priori prediction value RUL + n T of the nth charge-discharge cycle of the lithium battery to be tested n Time residual life posterior predictive value, x n T of the nth charge-discharge cycle of the lithium battery to be tested n The remaining life index value S at the time is the full life data.
5. The method for predicting the remaining life of a lithium battery according to claim 1, wherein the method for screening out the optimal penalty factor and the kernel function parameter of the support vector machine model by using a K-fold cross validation method is specifically as follows:
dividing the original data into K groups, wherein each time, one subset is not repeatedly extracted from the original data to serve as a verification set, and the rest K-1 groups of subset data are combined together to serve as a training set;
respectively training the support vector machine model by using K groups of data to obtain K trained models, and cross-verifying the performance index of the support vector machine model by using the average number of the accuracy of the K trained model verification sets as K folds;
and selecting the optimal penalty factors and kernel function parameters in the performance indexes to output.
6. The method for predicting the remaining life of a lithium battery according to claim 4, wherein the optimizing the support vector machine model by using a kalman algorithm to obtain an updated equation of the remaining life comprises:
calculating t of the lithium battery to be tested in the nth charge-discharge cycle according to the support vector machine model n A residual life priori predicted value and a mean square error thereof at the moment;
estimating t according to the residual life priori predicted value and the mean square error thereof n The remaining life state index value of the lithium battery to be tested is obtained at the moment;
correcting the position of the lithium battery to be detected at t according to the residual life index value n A residual life priori predicted value at moment and a mean square error thereof are obtained, and t of the lithium battery to be detected in the nth charge and discharge cycle is obtained n And determining a residual life posterior predicted value and a mean square error thereof at the moment, and determining an updating equation of the residual life.
7. A lithium battery remaining life prediction apparatus, characterized by comprising:
the data acquisition module is used for acquiring residual life data of the lithium battery to be tested in different charge and discharge cycles to obtain full life test data;
the model construction module is used for constructing a support vector machine model according to the life test data;
the screening module is used for screening out the optimal penalty factors and kernel function parameters of the support vector machine model by adopting a K-fold cross validation method;
the updating module is used for optimizing the support vector machine model by using a Kalman algorithm to obtain an updating equation of the residual life;
and the prediction module is used for inputting the operation data of the lithium battery to be detected into the optimized support vector machine model to perform life prediction and outputting the residual life.
8. The lithium battery remaining life prediction apparatus according to claim 7, wherein the screening module is specifically configured to:
dividing the original data into K groups, wherein each time, one subset is not repeatedly extracted from the original data to serve as a verification set, and the rest K-1 groups of subset data are combined together to serve as a training set;
respectively training the support vector machine model by using K groups of data to obtain K trained models, and cross-verifying the performance index of the support vector machine model by using the average number of the accuracy of the K trained model verification sets as K folds;
and selecting the optimal penalty factors and kernel function parameters in the performance indexes to output.
9. A terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the lithium battery remaining life prediction method according to any one of claims 1 to 6 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the lithium battery remaining life prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311412905.5A CN117214762A (en) | 2023-10-27 | 2023-10-27 | Lithium battery remaining life prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311412905.5A CN117214762A (en) | 2023-10-27 | 2023-10-27 | Lithium battery remaining life prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117214762A true CN117214762A (en) | 2023-12-12 |
Family
ID=89035597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311412905.5A Pending CN117214762A (en) | 2023-10-27 | 2023-10-27 | Lithium battery remaining life prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117214762A (en) |
-
2023
- 2023-10-27 CN CN202311412905.5A patent/CN117214762A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lucu et al. | A critical review on self-adaptive Li-ion battery ageing models | |
| CN107480028B (en) | Method and device for acquiring usable residual time of disk | |
| CN109001640B (en) | Data processing method and device for power battery | |
| WO2020137114A1 (en) | Training device, estimation device, training method, estimation method, training program, and estimation program | |
| CN114705990B (en) | Method and system for estimating state of charge of battery cluster, electronic device and storage medium | |
| JP2023520970A (en) | Lithium battery SOC estimation method, apparatus, and computer-readable storage medium | |
| CN110658460A (en) | Battery life prediction method and device for battery pack | |
| CN115684947A (en) | Battery model construction method and battery degradation prediction device | |
| CN115236519A (en) | Lithium battery health state prediction method and device based on hidden Markov model | |
| Venugopal et al. | Analysis of optimal machine learning approach for battery life estimation of Li-ion cell | |
| CN110456283B (en) | Method and device for acquiring internal resistance parameters of battery cell | |
| CN117289167A (en) | Battery remaining life prediction method, device and medium based on multiple neural network | |
| CN115149123B (en) | Lithium battery module consistency analysis method and system and storage medium | |
| CN117214762A (en) | Lithium battery remaining life prediction method, device, equipment and storage medium | |
| CN113782092B (en) | Method and device for generating lifetime prediction model and storage medium | |
| CN116125279A (en) | Method, device, equipment and storage medium for determining battery health state | |
| CN115525394A (en) | Method and device for adjusting number of containers | |
| CN110928634B (en) | Data processing method, device and equipment | |
| CN110134575B (en) | Method and device for calculating service capacity of server cluster | |
| CN117441108A (en) | Analysis device, prediction device, analysis method, prediction method, and program | |
| CN112669893B (en) | Method, system, device and equipment for determining read voltage to be used | |
| CN116593904B (en) | Model training method and method for predicting battery SOH and battery RUL | |
| CN117007997A (en) | Battery health state determining method, device, battery management system and storage medium | |
| US20230088429A1 (en) | Processing device, processing method, and program | |
| CN116365639A (en) | Outdoor power supply electric quantity estimation method, device, equipment and storage medium |
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 |