CN118226283B - Energy storage battery health state prediction method based on different temperatures - Google Patents
Energy storage battery health state prediction method based on different temperatures Download PDFInfo
- Publication number
- CN118226283B CN118226283B CN202410662859.2A CN202410662859A CN118226283B CN 118226283 B CN118226283 B CN 118226283B CN 202410662859 A CN202410662859 A CN 202410662859A CN 118226283 B CN118226283 B CN 118226283B
- Authority
- CN
- China
- Prior art keywords
- parameters
- health
- energy storage
- temperature
- storage battery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 87
- 238000004146 energy storage Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 238000011478 gradient descent method Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 30
- 238000006731 degradation reaction Methods 0.000 claims description 25
- 230000015556 catabolic process Effects 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 8
- 230000003862 health status Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000013101 initial test Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000005457 optimization Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000627 alternating current impedance spectroscopy Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Secondary Cells (AREA)
Abstract
The invention belongs to the field of energy storage battery health state prediction, and particularly relates to a method for predicting the health state of an energy storage battery based on different temperatures. According to the method, a series of charge and discharge cycle tests are carried out on the energy storage battery by setting an initial temperature and a temperature variable range of a test, and measured data of battery health state parameters are obtained at each set temperature. Using these data, a predictive model is created that describes the health of the battery at different temperatures, charge and discharge cycles and operating currents by defining a predictive function. The model parameters comprise electrochemical performance parameters and health state parameters, and the parameters are iteratively optimized through a gradient descent method, so that an accurate prediction model is finally obtained. By using the model, the health state of the energy storage battery at different working temperatures can be effectively predicted, and scientific basis is provided for maintenance and replacement of the battery.
Description
Technical Field
The invention belongs to the field of energy storage battery health state prediction, and particularly relates to a method for predicting the health state of an energy storage battery based on different temperatures.
Background
With the rapid development of renewable energy sources and electric vehicles, energy storage batteries are used as key energy storage components, and the performance and reliability of the energy storage batteries are crucial for the whole system. The State of Health (SoH) of a battery directly affects the service life and safety performance thereof, and thus, accurate prediction of the State of Health of the battery has become an important issue in a Battery Management System (BMS).
Existing battery state-of-health prediction methods typically rely on battery performance data under a single or several fixed operating conditions, which tend to ignore the effects of ambient temperature changes on battery performance. However, in practical applications, energy storage batteries often need to operate at varying ambient temperatures, where temperature variations can significantly affect the internal resistance, capacity, and other electrochemical properties of the battery.
In addition, existing predictive models often lack the ability to accurately describe the change in performance of a battery at different temperatures, resulting in large deviations in the predicted results from the actual battery state. This inaccuracy limits the application of predictive models in battery health management and life prediction.
The problems existing in the prior art are as follows:
Neglecting temperature variation: the prior art fails to fully consider the influence of environmental temperature changes on battery performance, resulting in inaccurate predictions of battery state of health at different temperatures.
Limitations of the predictive model: existing predictive models are typically based on simplifying assumptions and lack a detailed description of the battery's performance changes under actual operating conditions.
Deficiencies of parameter optimization: in determining model parameters, the existing methods often rely on empirical estimation or simple linear regression, and lack a systematic parameter optimization process.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a method for predicting the health state of an energy storage battery based on different temperatures.
The technical scheme of the invention is as follows:
The invention provides a method for predicting the health state of an energy storage battery based on different temperatures, which comprises the following steps:
Setting an initial test temperature and a temperature variation range, and performing charge-discharge cycle tests on the energy storage battery at different test temperatures to obtain actual measurement data of the energy storage battery health state parameters of the energy storage battery at each test temperature;
based on the measured data, establishing a prediction model of the state of health of the energy storage battery;
the prediction model of the state of health of the energy storage battery is as follows:
，
Wherein, For the operating temperature of the battery,In order to obtain the number of charge-discharge cycles,For the operating current of the battery,As the rate of degradation of the state of health,As a value of the capacity as a function of temperature and current,Is the variation value of internal resistance along with temperature;
Wherein, AndAs a function of the electrochemical performance parameter,Is a health status parameter;
the change value of the internal resistance with temperature The method comprises the following steps:
，
Wherein, At the reference temperature for the batteryThe internal resistance of the lower part of the body,For the operating temperature of the battery,As a function of the system variables,A base number that is a natural logarithm;
The variation of the capacity with temperature and current The method comprises the following steps:
，
Wherein, Is the rated capacity of the battery; is the coefficient of influence of temperature on capacity, Is the coefficient of influence of the current on the capacity,A base number that is a natural logarithm;
rate of health state degradation The method comprises the following steps:
，
Wherein, As a parameter of degradation of the state of health,In order to obtain the number of charge-discharge cycles,A base number that is a natural logarithm;
iteratively fitting the electrochemical performance parameters and the health state parameters by using a gradient descent method, and determining optimized electrochemical performance parameters and health state parameters;
And updating a prediction model by using the optimized electrochemical performance parameters and the optimized health state parameters, and predicting the health state of the energy storage battery at the predicted temperature to obtain a prediction result.
Further, the temperature variation range is less than or equal to 5 ℃.
Further, the gradient descent method is used for electrochemical performance parametersThe fitting iteration process is as follows:
Defining a loss function:
，
Wherein, As a function of the system variables,Is the firstThe temperature of the data points is such that,Is the measured internal resistance at the corresponding temperature,Is the total number of data points;
Initializing model parameters as model parameters Giving an initial value;
Calculating gradients for each model parameter Calculating an objective functionIs a partial derivative of (2) to obtain a gradient：
，
According to gradient and preset learning rateUpdating model parameters:
，
checking convergence and iteration, checking new model parameters If the convergence condition is satisfied, if the convergence condition is not satisfied, using new model parametersRepeating the iteration, and stopping the iteration if the convergence condition is met.
Further, the gradient descent method is used for electrochemical performance parametersThe fitting iteration process is as follows:
Defining a loss function:
，
Wherein, Is the total number of data points,Is the firstThe actual capacity of the data points is such that,AndCorresponding temperature and current, respectively;
Initializing parameters as AndGiving an initial value;
calculating gradient, vs. loss function Respectively aboutAndObtaining a gradient vector by calculating partial derivative:
，
，
，
Updating parameters using learning rate And the calculated gradient to update the parameters:
，
checking convergence and iteration, checking new model parameters AndIf the convergence condition is satisfied, if the convergence condition is not satisfied, a new one is usedAndRepeating the iteration, and stopping the iteration if the convergence condition is met.
Further, the gradient descent method is used for health state parametersThe fitting iteration process is as follows:
Defining a loss function:
，
Wherein, Is the total number of data points,Is the firstActual health status of the data points;
Initializing health state degradation parameters as Giving an initial value;
calculating gradient, vs. loss function With respect toObtaining a partial derivative to obtain a gradient;
，
Updating parameters using learning rate And the calculated gradient to update the health state degradation parameter：
，
Checking convergence and iteration, checking new health state degradation parametersIf the convergence condition is satisfied, if the convergence condition is not satisfied, using the new health state degradation parametersRepeating the iteration, and stopping the iteration if the convergence condition is met.
The beneficial effects of the invention are as follows: the method particularly considers the influence of temperature on the performance of the battery, enables the prediction model to adapt to the working states of the battery under different environmental temperatures, provides health state assessment for the application of the battery under variable environments, can monitor the health state of the battery in real time through the established prediction model, timely finds the degradation of the performance of the battery, and provides decision support for the maintenance and replacement of the battery. The electrochemical performance parameters and the health state parameters are subjected to iterative optimization by adopting a gradient descent method, and an optimal parameter combination can be found, so that the prediction model is more fit with the performance of an actual battery, and the reliability of prediction is further enhanced.
The accurate prediction of the state of health of the battery is helpful to make reasonable charge-discharge strategies and maintenance plans, thereby delaying the degradation of the battery performance and prolonging the service life of the battery. By predicting the state of health of the battery, unnecessary frequent replacement and excessive maintenance can be avoided, thereby reducing the maintenance cost and replacement cost of the battery.
Drawings
FIG. 1 is a flow chart of a method for predicting the state of health of an energy storage battery based on different temperatures;
FIG. 2 is a flowchart showing the steps of S100;
FIG. 3 is a flow chart of an iterative fit of electrochemical performance parameters and health parameters using a gradient descent method.
Detailed Description
The technical scheme of the invention is further described below by specific embodiments with reference to the accompanying drawings:
example 1
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.
As shown in fig. 1, the method comprises the following steps:
s100: setting an initial test temperature and a temperature variable range, and performing charge-discharge cycle tests on the energy storage battery at different test temperatures to obtain actual measurement data of the energy storage battery health state parameters of the energy storage battery at each test temperature.
S200: and establishing a prediction model of the state of health of the energy storage battery based on the measured data.
S300: and iteratively fitting the electrochemical performance parameters and the health state parameters by using a gradient descent method to determine the optimized electrochemical performance parameters and the health state parameters.
S400: and updating a prediction model by using the optimized electrochemical performance parameters and the optimized health state parameters, and predicting the health state of the energy storage battery at the predicted temperature to obtain a prediction result.
As shown in fig. 2, the specific steps of S100 include:
s110: the test conditions are determined first, that is, the initial temperature and the temperature variation range of the test are determined first, and in general, the smaller the temperature variation range is, the more accurate the feedback of the test result is. The temperature variation range is usually less than or equal to 5 ℃.
S120: and (3) testing the charge and discharge of the battery, and testing the charge and discharge of the energy storage battery at a set initial temperature.
S130: and obtaining measured data of the state of health parameters of the energy storage battery at the initial temperature.
Typically, the energy storage battery state of health parameters include: the method comprises the steps of measuring the internal resistance of an energy storage battery through alternating current impedance spectroscopy (EIS) in the charging and discharging process, and comparing the initial capacity with the final capacity to obtain the capacity loss value.
S140: the experimental temperature is gradually changed according to the set temperature variation range, and step S130 is repeated at each new temperature point.
S200: and establishing a prediction model of the state of health of the energy storage battery based on the measured data.
The model includes model parameters describing the performance change of the battery at different temperatures, namely, a prediction function is defined, and the function takes the working temperature of the battery, the number of charge and discharge cycles, the working current of the battery and the like as inputs to predict the health state of the battery.
The prediction model of the state of health of the energy storage battery is as follows:，
Wherein, For the operating temperature of the battery,In order to obtain the number of charge-discharge cycles,For the operating current of the battery,As the rate of degradation of the state of health,As a value of the capacity as a function of temperature and current,Is the variation of internal resistance with temperature.
Parameters of the prediction function fall into two categories: electrochemical performance parameters and health status parameters.
Electrochemical performance parameters describe the electrochemical performance of a battery at different temperatures, namely: And 。
The state of health parameter describes the degradation rate of the energy storage battery under different temperature conditions, i.e。
In this step, the electrochemical performance parameters are calculated as:
internal resistance with temperature ：，
Wherein,At the reference temperature for the batteryThe internal resistance of the lower part of the body,For the operating temperature of the battery,Describing the rate of change of internal resistance with temperature for system variables,Is the base of natural logarithms.
Change in capacity with temperature and current:：
，
Wherein, Is the rated capacity of the battery; is the coefficient of influence of temperature on capacity, Is the coefficient of influence of the current on the capacity,Is the base of natural logarithms.
In this step, the health status parameter, i.e. the health status degradation rateThe calculation is as follows:
Wherein, the method comprises the steps of, wherein, Is a state of health degradation parameter, is related to the use condition and manufacturing process of the battery,In order to obtain the number of charge-discharge cycles,Is the base of natural logarithms.
S300: as shown in fig. 3, the specific steps of optimizing the electrochemical performance parameters and the health parameters are determined using a gradient descent method fitting iterations to the electrochemical performance parameters and the health parameters.
Iterative pairing using gradient descentThe fitting iteration flow is as follows:
S311: a loss function is defined that measures the difference between the model predicted value and the actual observed value.
For the followingThe loss function adopts a mean square error and is used for measuring the difference between the predicted internal resistance and the actually measured internal resistance predicted by the model:
，
Wherein, As a function of the system variables,Is the firstThe temperature of the data points is such that,Is the measured internal resistance at the corresponding temperature,Is the total number of data points.
S321: initializing model parameters as model parametersAn initial value is given.
S331: calculating gradients for each model parameterCalculating an objective functionIs a partial derivative of (2) to obtain a gradientThe gradient points in the direction in which the objective function grows fastest:
。
s341: updating model parameters according to the gradient and a preset learning rate Updating model parameters:
。
S351: checking convergence and iteration, checking new model parameters If the convergence condition is satisfied, if the convergence condition is not satisfied, using new model parametersSteps S331 to S351 are repeated, and if the convergence condition is satisfied, the iteration is stopped.
Iterative pairing using gradient descentThe fitting iteration flow is as follows:
s312: defining a loss function, wherein the loss function adopts a mean square error and is used for measuring the difference between a model predicted value and an actual observed value:
，
Wherein, Is the total number of data points,Is the firstThe actual capacity of the data points is such that,AndCorresponding temperature and current, respectively.
S322: initializing parameters asAndAn initial value is given.
S332: calculating gradient, vs. loss functionRespectively aboutAndObtaining a gradient vector by calculating partial derivative:
，
，
。
S342: updating parameters using learning rate And the calculated gradient to update the parameters:
。
s352: checking convergence and iteration, checking new model parameters AndIf the convergence condition is satisfied, if the convergence condition is not satisfied, a new one is usedAndSteps S332 to S352 are repeated, and if the convergence condition is satisfied, the iteration is stopped.
Iterative pairing using gradient descentThe fitting flow is as follows:
S313: defining a loss function, wherein the loss function adopts a Mean Square Error (MSE) form and is used for measuring the difference between the health state predicted by the model and the actual observed value:
，
Wherein, Is the total number of data points,Is the firstActual health of the data points.
S323: initializing health state degradation parameters asAn initial value is given.
S333: calculating gradient, vs. loss functionWith respect toObtaining a partial derivative to obtain a gradient;
。
s343: updating parameters using learning rate And the calculated gradient to update the health state degradation parameter：
。
S353: checking convergence and iteration, checking new health state degradation parametersIf the convergence condition is satisfied, if the convergence condition is not satisfied, using the new health state degradation parametersSteps S333 to S353 are repeated, and if the convergence condition is satisfied, the iteration is stopped.
S400: and updating the prediction model by using the optimized electrochemical performance parameters and health state parameters to obtain a final prediction model. And predicting the health state of the energy storage battery at the predicted temperature by using a final prediction model to obtain a prediction result.
The step S400 is a final application link in the energy storage battery health state prediction method, and relates to integrating electrochemical performance parameters and health state parameters obtained through gradient descent method optimization into a prediction model, so that the model can accurately predict the health state of the energy storage battery at a specific temperature. After optimization and verification of the model parameters are completed, S400 uses these parameters to predict the state of health of the battery, including the rate of state of health degradationVariation of internal resistance with temperatureChanges in capacity with temperature and currentAnd finally outputting a prediction result.
The basic principles of the present application have been described above in connection with specific embodiments, but it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be construed as necessarily possessed by the various embodiments of the application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features herein.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather is to be construed as including any modifications, equivalents, and alternatives falling within the spirit and principles of the application.
Claims (5)
1. The method for predicting the health state of the energy storage battery based on different temperatures is characterized by comprising the following steps:
Setting an initial test temperature and a temperature variation range, and performing charge-discharge cycle tests on the energy storage battery at different test temperatures to obtain actual measurement data of the energy storage battery health state parameters of the energy storage battery at each test temperature;
based on the measured data, establishing a prediction model of the state of health of the energy storage battery;
the prediction model of the state of health of the energy storage battery is as follows: ，
Wherein, For the operating temperature of the battery,In order to obtain the number of charge-discharge cycles,For the operating current of the battery,As the rate of degradation of the state of health,As a value of the capacity as a function of temperature and current,Is the variation value of internal resistance along with temperature;
Wherein, AndAs a function of the electrochemical performance parameter,Is a health status parameter;
the change value of the internal resistance with temperature The method comprises the following steps:，
Wherein, At the reference temperature for the batteryThe internal resistance of the lower part of the body,For the operating temperature of the battery,As a function of the system variables,A base number that is a natural logarithm;
The variation of the capacity with temperature and current The method comprises the following steps:，
Wherein, Is the rated capacity of the battery; is the coefficient of influence of temperature on capacity, Is the influence coefficient of current on capacity;
rate of health state degradation The method comprises the following steps:，
Wherein, As a parameter of degradation of the state of health,In order to obtain the number of charge-discharge cycles,A base number that is a natural logarithm;
Fitting and iterating the electrochemical performance parameters and the health state parameters by using a gradient descent method, and determining and optimizing the electrochemical performance parameters and the health state parameters;
And updating a prediction model by using the optimized electrochemical performance parameters and the optimized health state parameters, and predicting the health state of the energy storage battery at the predicted temperature to obtain a prediction result.
2. The method for predicting the health of an energy storage battery according to claim 1, wherein the temperature variation range is less than or equal to 5 ℃.
3. The method for predicting the health of an energy storage battery based on different temperatures according to claim 1, wherein the gradient descent method is used for electrochemical performance parametersThe fitting iteration process is as follows:
Defining a loss function:
，
Wherein, As a function of the system variables,Is the firstThe temperature of the data points is such that,Is the measured internal resistance at the corresponding temperature,Is the total number of data points;
Initializing model parameters as model parameters Giving an initial value;
Calculating gradients for each model parameter Calculating an objective functionIs a partial derivative of (2) to obtain a gradient：
，
According to gradient and preset learning rateUpdating model parameters:
，
checking convergence and iteration, checking new model parameters If the convergence condition is satisfied, if the convergence condition is not satisfied, using new model parametersRepeating the iteration, and stopping the iteration if the convergence condition is met.
4. The method for predicting the health of an energy storage battery based on different temperatures according to claim 1, wherein the gradient descent method is used for electrochemical performance parametersThe fitting iteration process is as follows:
Defining a loss function:
，
Wherein, Is the total number of data points,Is the firstThe actual capacity of the data points is such that,AndCorresponding temperature and current, respectively;
Initializing parameters as AndGiving an initial value;
calculating gradient, vs. loss function Respectively aboutAndObtaining a gradient vector by calculating partial derivative:
，
，
，
Updating parameters using learning rate And the calculated gradient to update the parameters:
，
checking convergence and iteration, checking new model parameters AndIf the convergence condition is satisfied, if the convergence condition is not satisfied, a new one is usedAndRepeating the iteration, and stopping the iteration if the convergence condition is met.
5. The method for predicting the health of an energy storage battery according to claim 1, wherein the gradient descent method is used for the health parametersThe fitting iteration process is as follows:
Defining a loss function:
，
Wherein, Is the total number of data points,Is the firstActual health status of the data points;
Initializing health state degradation parameters as Giving an initial value;
calculating gradient, vs. loss function With respect toObtaining a partial derivative to obtain a gradient;
，
Updating parameters using learning rate And the calculated gradient to update the health state degradation parameter：
，
Checking convergence and iteration, checking new health state degradation parametersIf the convergence condition is satisfied, if the convergence condition is not satisfied, using the new health state degradation parametersRepeating the iteration, and stopping the iteration if the convergence condition is met.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410662859.2A CN118226283B (en) | 2024-05-27 | 2024-05-27 | Energy storage battery health state prediction method based on different temperatures |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410662859.2A CN118226283B (en) | 2024-05-27 | 2024-05-27 | Energy storage battery health state prediction method based on different temperatures |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118226283A CN118226283A (en) | 2024-06-21 |
| CN118226283B true CN118226283B (en) | 2024-07-26 |
Family
ID=91512382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410662859.2A Active CN118226283B (en) | 2024-05-27 | 2024-05-27 | Energy storage battery health state prediction method based on different temperatures |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118226283B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114692827A (en) * | 2022-03-21 | 2022-07-01 | 首都师范大学 | Electric vehicle lithium battery SOH online prediction method facing edge federal learning |
| CN114814592A (en) * | 2022-03-14 | 2022-07-29 | 湖北工业大学 | Lithium battery state of health estimation and remaining service life prediction method and equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10371753B1 (en) * | 2013-12-20 | 2019-08-06 | Hrl Laboratories, Llc | Methods for online estimation of battery capacity and state of health |
| US20220057451A1 (en) * | 2020-08-21 | 2022-02-24 | Carnegie Mellon University | System and method for estimation of battery state and health |
| CN112946499B (en) * | 2021-02-04 | 2024-02-02 | 芜湖楚睿智能科技有限公司 | Lithium battery health state and state of charge joint estimation method based on machine learning |
| CN116680983A (en) * | 2023-06-06 | 2023-09-01 | 重庆大学 | Lithium ion residual life prediction method based on improved particle filter model |
| CN117129879B (en) * | 2023-10-26 | 2024-01-26 | 国网天津市电力公司电力科学研究院 | Threshold adjustment method and battery health prediction model training method |
| CN117368784A (en) * | 2023-11-28 | 2024-01-09 | 吉林大学 | Battery health state prediction method based on feature compression |
-
2024
- 2024-05-27 CN CN202410662859.2A patent/CN118226283B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114814592A (en) * | 2022-03-14 | 2022-07-29 | 湖北工业大学 | Lithium battery state of health estimation and remaining service life prediction method and equipment |
| CN114692827A (en) * | 2022-03-21 | 2022-07-01 | 首都师范大学 | Electric vehicle lithium battery SOH online prediction method facing edge federal learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118226283A (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ding et al. | An improved Thevenin model of lithium-ion battery with high accuracy for electric vehicles | |
| Lyu et al. | Li-ion battery state of health estimation and remaining useful life prediction through a model-data-fusion method | |
| Zhang et al. | Research on electric vehicle charging safety warning model based on back propagation neural network optimized by improved gray wolf algorithm | |
| Pan et al. | State of charge estimation of lithium-ion batteries using a grey extended Kalman filter and a novel open-circuit voltage model | |
| Liu et al. | Joint estimation of battery state-of-charge and state-of-health based on a simplified pseudo-two-dimensional model | |
| Huang et al. | A model-based state-of-charge estimation method for series-connected lithium-ion battery pack considering fast-varying cell temperature | |
| Takyi‐Aninakwa et al. | A strong tracking adaptive fading‐extended Kalman filter for the state of charge estimation of lithium‐ion batteries | |
| Wang et al. | A novel feedback correction-adaptive Kalman filtering method for the whole-life-cycle state of charge and closed-circuit voltage prediction of lithium-ion batteries based on the second-order electrical equivalent circuit model | |
| Zhang et al. | State of charge-dependent aging mechanisms in graphite/Li (NiCoAl) O2 cells: Capacity loss modeling and remaining useful life prediction | |
| CN112098849B (en) | Remaining power estimation method of lithium battery based on integrating Kalman filter | |
| Chang et al. | Micro-fault diagnosis of electric vehicle batteries based on the evolution of battery consistency relative position | |
| CN112986831A (en) | Lithium ion battery life prediction method based on correlation coefficient particle filtering | |
| CN112989690B (en) | Multi-time-scale state-of-charge estimation method for lithium battery of hybrid electric vehicle | |
| CN116609686B (en) | Battery cell consistency assessment method based on cloud platform big data | |
| Duan et al. | Online parameter identification and state of charge estimation of battery based on multitimescale adaptive double Kalman filter algorithm | |
| CN114329760A (en) | Vehicle-mounted lithium ion battery modeling and fault diagnosis method based on digital twinning | |
| CN111950205A (en) | A Lithium Battery SOH Prediction Method Based on FWA Optimization Extreme Learning Machine | |
| CN116577686A (en) | Multi-working condition SOH estimation method and system based on local stage charging data | |
| CN112881916A (en) | Method and system for predicting health state and remaining usable life of lithium battery | |
| CN114089193A (en) | On-line estimation method, device and computer equipment for battery temperature and negative electrode potential | |
| Bian et al. | An improved particle filter method to estimate state of health of lithium-ion battery | |
| Xin et al. | A novel state of charge estimation method for ternary lithium batteries based on system function and extended kalman filter | |
| CN118226283B (en) | Energy storage battery health state prediction method based on different temperatures | |
| Mao et al. | An ultrafast variable forgetting factor recursive least square method for determining the state-of-health of Li-ion batteries | |
| Dar et al. | Advanced integration of bidirectional long short-term memory neural networks and innovative extended Kalman filter for state of charge estimation 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |