CN114994541A - Lithium ion battery SOH estimation method based on multi-strategy fusion - Google Patents
Lithium ion battery SOH estimation method based on multi-strategy fusion Download PDFInfo
- Publication number
- CN114994541A CN114994541A CN202210624209.XA CN202210624209A CN114994541A CN 114994541 A CN114994541 A CN 114994541A CN 202210624209 A CN202210624209 A CN 202210624209A CN 114994541 A CN114994541 A CN 114994541A
- Authority
- CN
- China
- Prior art keywords
- charging
- lithium ion
- ion battery
- soh
- discharging
- 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]
- G01R31/367—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]
- G01R31/378—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
- G01R31/3828—Arrangements for monitoring battery or accumulator variables, e.g. SoC using current integration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
- H01M2010/4271—Battery management systems including electronic circuits, e.g. control of current or voltage to keep battery in healthy state, cell balancing
-
- 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)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Electrochemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Chemical & Material Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Manufacturing & Machinery (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Secondary Cells (AREA)
Abstract
The invention provides a lithium ion battery SOH estimation method based on multi-strategy fusion, which comprises the steps of converting an original historical data set collected by a sensor into a historical data set through data cleaning and charging and discharging process matching, then distributing a corresponding label generation strategy according to the integrity level of the charging and discharging process, then utilizing the historical data set to iteratively train a BP neural network model, and finally distributing a corresponding SOH estimation strategy according to the integrity level of the charging and discharging data of a lithium ion battery collected in real time. The method can effectively estimate the SOH of the lithium ion battery, and has rapidity and accuracy.
Description
Technical Field
The invention belongs to the field of lithium ion battery SOH estimation, and particularly relates to a lithium ion battery SOH estimation method based on multi-strategy fusion.
Background
With the widespread use of fossil fuels in the transportation sector, the atmospheric pollution caused by the byproducts of their combustion poses a serious threat to human health. In recent years, lithium ion batteries have attracted much attention because of their advantages such as environmental protection, low self-discharge rate, and high coulombic efficiency. The State Of Health (SOH) estimation Of a lithium ion Battery is an important component in a Battery Management System (BMS) and has an important significance in evaluating the performance degradation degree Of the lithium ion Battery. Accurately estimating the SOH of the lithium ion battery can remind a user to replace an aged battery in time and prevent major safety accidents to a certain extent.
The data-driven method, one of the methods for estimating the SOH of the lithium ion battery, has been the focus of current research with the development of big data and artificial intelligence. Although the data driving method does not need to deeply master the complex lithium ion battery mechanism, and can estimate the SOH of the lithium ion battery by combining data with a mathematical model, the method still has certain limitation in practical application. Under the condition of actual working conditions, the integrity of the charging and discharging data of the lithium ion battery acquired by the sensor is different according to different behaviors of a user on charging and discharging of the electric automobile. The charge/discharge data includes fragmented data, but also includes data for fully charging a lithium ion battery. For data during full charge, an ampere-hour integration method is rapid and accurate, and is also a method for calibrating SOH in the current cycle accelerated aging experiment of the lithium ion battery. At the moment, if a complex nonlinear data driving method is reused for estimating the SOH, not only is the operation time increased, but also the SOH estimation precision is reduced by an ampere-hour integration method.
Therefore, aiming at the limitation of the data driving method, the invention provides a lithium ion battery SOH estimation method based on multi-strategy fusion, the application strategy of the model is adjusted according to the integrity of the data, and the rapidity and the accuracy of the lithium ion battery SOH estimation are both considered.
Disclosure of Invention
The invention aims to provide a lithium ion battery SOH estimation method based on multi-strategy fusion, so as to overcome the defects of the existing method and take the estimation rapidity and accuracy of SOH into account.
The purpose of the invention can be realized by the following technical scheme:
a lithium ion battery SOH estimation method based on multi-strategy fusion is characterized by comprising the following steps:
the method comprises the following steps: historical data in the charging and discharging processes of the lithium ion battery are collected by a sensor to form an original historical data set;
step two: carrying out data cleaning on the original historical data set, processing abnormal values and missing values, and carrying out corresponding matching on the charging and discharging processes to obtain a historical data set;
step three: according to an SOC-OCV curve provided by the lithium ion battery manufacturer, dividing the integrity of the charging and discharging process of each period in the historical data set into four stages I, II, III and IV respectively;
step four: distributing an SOH label generation strategy according to the level of the integrity degree of the charging and discharging process, and forming a training set with the characteristics;
step five: carrying out iterative training on the training set by using a BP neural network to obtain an SOH estimation model;
step six: and (4) collecting real-time charging and discharging data of the lithium ion battery in the same type as the steps, preprocessing the data similar to the step two, judging the charging and discharging integrity degree grade according to the standard of the step three, distributing an SOH estimation strategy, and estimating the SOH of the lithium ion battery.
Further, the original historical data set in the step one is a time sequence of current, voltage and temperature in the charging and discharging process of the lithium ion battery.
Further, the processing of the abnormal value and the missing value in the step two specifically includes: identifying abnormal values through a triple standard deviation criterion, and replacing the abnormal values and the missing values by using average values of adjacent values;
the corresponding matching of the charging and discharging processes is specifically as follows: charge and discharge processes that are most closely spaced in time are considered to be the same cycle.
Further, in the third step, the grading of the integrity of the charging and discharging process in the historical data set takes the electric quantity change Δ SOC caused by the charging or discharging process as a standard, and the grading is specifically as follows:
stage I: the delta SOC (state of charge) caused by any one process of charge and discharge is more than or equal to 70% and less than or equal to 100%;
and II, stage: the electric quantity change caused by any one process of charging and discharging meets the requirement that the delta SOC is more than or equal to 30% and less than 70%;
grade III: the electric quantity change caused by any process of charging and discharging meets the requirement that the delta SOC is more than or equal to 0% and less than 30%.
Further, the SOH label generation strategy distributed according to the level of the integrity of the charging and discharging process in the fourth step is specifically as follows:
stage I: performing ampere-hour integration on the process with the maximum delta SOC in the charging and discharging processes, and performing amp-hour integration result Cap I Dividing by delta SOC as the maximum capacity Q of the lithium ion battery in the current cycle now Then SOH label of current cycle is
And II, stage: performing ampere-hour integration on the process with the maximum Delta SOC in the charging and discharging processes, and performing ampere-hour integration on the result Cap Ⅱ Dividing the current cycle by the delta SOC to obtain the uncorrected maximum capacity Q of the lithium ion battery in the current cycle r Taking the maximum capacity Q of the cycle nearest to the current cycle b Uncorrected maximum capacity Q of the current cycle r Averaging to obtain the maximum capacity Q of the lithium ion battery after current cycle correction now Then SOH label of current cycle is
Grade III: for all the cycles of the two stages I and II, recording the time T, the average temperature T and the initial voltage V of the battery in each cycle charging or discharging process S End voltage V E And average current I M The SOH labels corresponding to the SOH labels form a label training set [ (t) Ⅰ、Ⅱ ,T Ⅰ、Ⅱ ,V S Ⅰ、Ⅱ ,V E Ⅰ、Ⅱ ,I M Ⅰ、Ⅱ ),SOH Ⅰ、Ⅱ ]Training a BP neural network by using the label training set to obtain a label generation model, and enabling the time T, the average temperature T and the initial voltage V of the cyclic charging or discharging process to meet the class III condition S And a termination voltage V E And inputting the label generation model to obtain the cyclic SOH label meeting the class III condition.
Further, the training set [ (T, T, V) in step five S ,V E ,I M ),SOH]The system is composed of characteristics of all cycles of I, II and III stages and corresponding labels, wherein the characteristics comprise time T of a charging or discharging process, average temperature T of a battery and initial voltage V S End voltage V E And average current I M 。
Further, the SOH estimation strategy of step six is specifically:
stage I: performing ampere-hour integration on the process with the maximum delta SOC in the current cyclic charge-discharge process, and performing ampere-hour integration on the result Cap I Dividing by delta SOC as the maximum estimated capacity of the lithium ion battery in the current cycleThe SOH value of the current cycle is
II, III stage: extracting time T, average temperature T and initial voltage V of the process from the process of maximum delta SOC in the current cyclic charge-discharge process S End voltage V E And average current I M Inputting the SOH estimation model in the step five to obtain an SOH estimation value
Further, the features and the labels are extracted from the process meeting the classification condition in the same cycle of charge and discharge.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
fig. 2 is a typical image of the SOC-OCV curve of the lithium ion battery in the embodiment of the present invention.
Fig. 3 is a model structure of a BP neural network in the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments; all other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the present embodiment provides a lithium ion battery SOH estimation method based on multi-strategy fusion, including the following steps:
the method comprises the following steps: historical data in the charging and discharging processes of the lithium ion battery are collected by a sensor to form an original historical data set;
the historical data of the lithium ion battery in the charging and discharging processes are time sequences of current, voltage and temperature.
Step two: carrying out data cleaning on the original historical data set, processing abnormal values and missing values, and carrying out corresponding matching on charging and discharging to obtain a historical data set;
the processing of the abnormal value and the missing value is specifically as follows: calculating standard deviations of current, voltage and temperature respectively aiming at each charging and discharging process, marking abnormal values of data points with numerical values more than three times of the standard deviations in the process, and filling and replacing missing values and the abnormal values by using average values of adjacent values of the missing values and the abnormal values; the corresponding matching of charging and discharging is specifically: charge and discharge processes that are temporally closest apart are considered to be the same cycle.
Step three: according to an SOC-OCV curve provided by the lithium ion battery manufacturer, dividing the integrity of the charging and discharging process of each period in the historical data set into four stages I, II, III and IV respectively;
the grading of the integrity degree of the historical data centralized charging and discharging process takes the electric quantity change delta SOC caused by the charging or discharging process as a standard, and the grading is specifically as follows:
stage I: the delta SOC (state of charge) caused by any one process of charge and discharge is more than or equal to 70% and less than or equal to 100%;
and II, stage: the electric quantity change caused by any one process of charging and discharging meets the requirement that the delta SOC is more than or equal to 30% and less than 70%;
grade III: the electric quantity change caused by any process of charging and discharging meets the requirement that the delta SOC is more than or equal to 0% and less than 30%.
As shown in fig. 2, which is a typical image of the SOC-OCV curve of the lithium ion battery in this embodiment, the value of the electric quantity change Δ SOC can be obtained according to fig. 2 by using the terminal voltage of the lithium ion battery before and after the charging or discharging process; if the charging and discharging processes belong to different grades, the grade of the process causing the maximum electric quantity change delta SOC is taken as the grade of the cycle.
Step four: distributing an SOH label generation strategy according to the level of the integrity degree of the charging and discharging process, and forming a training set with the characteristics;
the SOH label generation strategy is specifically distributed according to the charging and discharging process integrity degree grade as follows:
stage I: performing ampere-hour integration on the process with the maximum Delta SOC in the charging and discharging processes, and performing ampere-hour integration on the result Cap I Dividing by delta SOC as the maximum capacity Q of the lithium ion battery in the current cycle now Then SOH label of current cycle is
And II, stage: performing ampere-hour integration on the process with the maximum Delta SOC in the charging and discharging processes, and performing ampere-hour integration on the result Cap Ⅱ Dividing the current cycle by the delta SOC to obtain the uncorrected maximum capacity Q of the lithium ion battery in the current cycle r Taking the maximum capacity Q of the cycle nearest to the current cycle b Uncorrected maximum capacity Q of the current cycle r Averaging to obtain the maximum capacity Q of the lithium ion battery after current cycle correction now Then SOH label of current cycle is
Grade III: for all the cycles of the two stages I and II, recording the time T, the average temperature T and the initial voltage V of the battery in each cycle charging or discharging process S End voltage V E And average current I M The SOH labels corresponding to the SOH labels form a label training set [ (t) Ⅰ、Ⅱ ,T Ⅰ、Ⅱ ,V S Ⅰ、Ⅱ ,V E Ⅰ、Ⅱ ,I M Ⅰ、Ⅱ ),SOH Ⅰ、Ⅱ ]Training a BP neural network by using the label training set to obtain a label generation model, and enabling the time T, the average temperature T and the initial voltage V of the cyclic charging or discharging process to meet the class III condition S And a termination voltage V E And inputting the label generation model to obtain the cyclic SOH label meeting the class III condition.
Step five: carrying out iterative training on the training set by using a BP neural network to obtain an SOH estimation model;
wherein, the device is composed of the characteristics of all the I, II and III-grade circulations and the corresponding labels, and is characterized by the time T of the charging or discharging process, the average temperature T of the battery, and the initial voltage V S End voltage V E And average current I M (ii) a The characteristics and the labels are extracted from the process of meeting the grading conditions in the same cycle charging and discharging process; in this example, the structure of the BP neural network is shown in fig. 3.
Step six: and (4) collecting real-time charging and discharging data of the same type of the lithium ion battery and the step (II), preprocessing the data similar to the step (II), judging the charging and discharging integrity degree grade according to the standard of the step (III), allocating an SOH estimation strategy, and estimating the SOH of the lithium ion battery.
The SOH estimation strategy specifically includes:
stage I: performing ampere-hour integration on the process with the maximum delta SOC in the current cyclic charge-discharge process, and performing ampere-hour integration on the result Cap I Dividing by delta SOC as the maximum estimated capacity of the lithium ion battery in the current cycleThe SOH value of the current cycle is
II, III stage: extracting time T, average temperature T and initial voltage V of the process from the process of maximum delta SOC in the current cyclic charge-discharge process S End voltage V E And average current I M Inputting the SOH estimation model in the step five to obtain an SOH estimation value
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A lithium ion battery SOH estimation method based on multi-strategy fusion is characterized by comprising the following steps:
the method comprises the following steps: historical data in the charging and discharging processes of the lithium ion battery are collected by a sensor to form an original historical data set;
step two: carrying out data cleaning on the original historical data set, processing abnormal values and missing values, and carrying out corresponding matching on the charging and discharging processes to obtain a historical data set;
step three: according to an SOC-OCV curve provided by the lithium ion battery manufacturer, dividing the integrity of the charging and discharging process of each period in the historical data set into four stages I, II, III and IV respectively;
step four: distributing an SOH label generation strategy according to the level of the integrity degree of the charging and discharging process, and forming a training set with the characteristics;
step five: carrying out iterative training on the training set by using a BP neural network to obtain an SOH estimation model;
step six: and (4) collecting real-time charging and discharging data of the same type of the lithium ion battery and the step (II), preprocessing the data similar to the step (II), judging the charging and discharging integrity degree grade according to the standard of the step (III), allocating an SOH estimation strategy, and estimating the SOH of the lithium ion battery.
2. The lithium ion battery SOH estimation method based on multi-strategy fusion of claim 1, wherein the original historical data set in the step one is a time sequence of current, voltage and temperature in the charging and discharging process of the lithium ion battery.
3. The lithium ion battery SOH estimation method based on multi-strategy fusion according to claim 1, wherein the processing of the abnormal values and the missing values in the second step is specifically as follows: identifying abnormal values through a triple standard deviation criterion, and replacing the abnormal values and the missing values by using average values of adjacent values;
the corresponding matching of the charging and discharging processes is specifically as follows: charge and discharge processes that are most closely spaced in time are considered to be the same cycle.
4. The lithium ion battery SOH estimation method based on multi-strategy fusion of claim 1, wherein the grading of the integrity of the charging and discharging process in the historical data set in the third step is based on the electric quantity change Δ SOC caused by the charging or discharging process, and the grading is specifically as follows:
stage I: the delta SOC caused by any charge and discharge process is more than or equal to 70% and less than or equal to 100%;
and II, stage: the electric quantity change caused by any process of charging and discharging meets the requirement that delta SOC is more than or equal to 30% and less than 70%;
grade III: the electric quantity change caused by any process of charging and discharging meets the requirement that the delta SOC is more than or equal to 0% and less than 30%.
5. The lithium ion battery SOH estimation method based on multi-strategy fusion according to claim 1, wherein the SOH label generation strategy distributed according to the charging and discharging process integrity level in the fourth step specifically comprises:
stage I: performing ampere-hour integration on the process with the maximum Delta SOC in the charging and discharging processes, and performing ampere-hour integration on the result Cap I Dividing by delta SOC as the maximum capacity Q of the lithium ion battery in the current cycle now Then SOH label of current cycle is
And II, stage: performing ampere-hour integration on the process with the maximum Delta SOC in the charging and discharging processes, and performing ampere-hour integration on the result Cap Ⅱ Dividing the current cycle by the delta SOC to obtain the uncorrected maximum capacity Q of the lithium ion battery in the current cycle r Taking the maximum capacity Q of the cycle nearest to the current cycle b Uncorrected maximum capacity Q of the current cycle r Averaging to obtain the maximum capacity Q of the lithium ion battery after current cycle correction now Then SOH label of current cycle is
Grade III: for all the cycles of the two stages I and II, recording the time T, the average temperature T and the initial voltage V of the battery in each cycle charging or discharging process S End voltage V E And average current I M The SOH labels corresponding to the SOH labels form a label training set [ (t) Ⅰ、Ⅱ ,T Ⅰ、Ⅱ ,V S Ⅰ、Ⅱ ,V E Ⅰ、Ⅱ ,I M Ⅰ、Ⅱ ),SOH Ⅰ、Ⅱ ]Training a BP neural network by using the label training set to obtain a label generation model, and enabling the time T, the average temperature T and the initial voltage V of the cyclic charging or discharging process to meet the class III condition S And a termination voltage V E And inputting the label generation model to obtain the cyclic SOH label meeting the class III condition.
6. The lithium ion battery SOH estimation method based on multi-strategy fusion of claim 1, characterized in that in step fiveTraining set [ (T, T, V) S ,V E ,I M ),SOH]The system is composed of characteristics of all cycles of I, II and III stages and corresponding labels, wherein the characteristics comprise time T of a charging or discharging process, average temperature T of a battery and initial voltage V S End voltage V E And average current I M 。
7. The lithium ion battery SOH estimation method based on multi-strategy fusion as claimed in claim 1, wherein the SOH estimation strategy of step six is specifically:
stage I: performing ampere-hour integration on the process with the maximum delta SOC in the current cyclic charge-discharge process, and performing ampere-hour integration on the result Cap I Dividing by delta SOC as the maximum estimated capacity of the lithium ion battery in the current cycleThe SOH value of the current cycle is
II, III stage: extracting time T, average temperature T and initial voltage V of the process from the process of maximum delta SOC in the current cyclic charge-discharge process S End voltage V E And average current I M Inputting the SOH estimation model in the step five to obtain an SOH estimation value
8. The lithium ion battery SOH estimation method based on multi-strategy fusion of claim 5, wherein the features and the labels are extracted from the process meeting the classification condition in the same cycle of charge and discharge.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210624209.XA CN114994541A (en) | 2022-06-02 | 2022-06-02 | Lithium ion battery SOH estimation method based on multi-strategy fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210624209.XA CN114994541A (en) | 2022-06-02 | 2022-06-02 | Lithium ion battery SOH estimation method based on multi-strategy fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114994541A true CN114994541A (en) | 2022-09-02 |
Family
ID=83031243
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210624209.XA Pending CN114994541A (en) | 2022-06-02 | 2022-06-02 | Lithium ion battery SOH estimation method based on multi-strategy fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114994541A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116011993A (en) * | 2023-01-10 | 2023-04-25 | 九源云(广州)智能科技有限公司 | Storage battery health management system based on CPS architecture |
CN117706406A (en) * | 2024-02-05 | 2024-03-15 | 安徽布拉特智能科技有限公司 | Lithium battery health state monitoring model, method, system and storage medium |
-
2022
- 2022-06-02 CN CN202210624209.XA patent/CN114994541A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116011993A (en) * | 2023-01-10 | 2023-04-25 | 九源云(广州)智能科技有限公司 | Storage battery health management system based on CPS architecture |
CN116011993B (en) * | 2023-01-10 | 2024-01-30 | 九源云(广州)智能科技有限公司 | Storage battery health management system based on CPS architecture |
CN117706406A (en) * | 2024-02-05 | 2024-03-15 | 安徽布拉特智能科技有限公司 | Lithium battery health state monitoring model, method, system and storage medium |
CN117706406B (en) * | 2024-02-05 | 2024-04-16 | 安徽布拉特智能科技有限公司 | Lithium battery health state monitoring model, method, system and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107957562B (en) | Online prediction method for residual life of lithium ion battery | |
CN106383316B (en) | A kind of echelon utilizes lithium battery method of evaluating performance | |
CN114994541A (en) | Lithium ion battery SOH estimation method based on multi-strategy fusion | |
WO2022213597A1 (en) | New energy vehicle eic system safety feature database construction method | |
CN107612071B (en) | Battery failure judgment and processing method for battery pack | |
CN111007399A (en) | Lithium battery state of charge prediction method based on improved generation countermeasure network | |
CN103698713A (en) | Method for assessing SOH (state of health) of lithium ion battery | |
CN110940920A (en) | Method for acquiring maximum charging current of lithium battery without lithium precipitation under preset SOC (state of charge) | |
CN112904219B (en) | Big data-based power battery health state prediction method | |
CN109975715B (en) | Method for obtaining residual electric quantity of lithium ion battery module of electric vehicle | |
CN113030758B (en) | Aging early warning method and system based on lithium ion battery capacity water jump point, automobile and computer storage medium | |
CN107436412B (en) | Method for estimating power of power battery based on self-learning | |
CN112083331A (en) | Fusion method for improving lithium ion battery state of charge estimation precision | |
CN107045104A (en) | A kind of On-line Estimation method of lithium titanate battery capacity | |
WO2022100229A1 (en) | Artificial-intelligence-based soc estimation method for lithium ion battery system | |
CN111064253A (en) | Battery health degree rapid evaluation method based on average discrete Frechet distance | |
CN112098893B (en) | Internal short-circuit fault diagnosis method based on initial capacity difference and suitable for electric automobile | |
CN113484771A (en) | Method for estimating wide-temperature full-life SOC and capacity of lithium ion battery | |
CN108732499A (en) | A kind of method and system of detection cycle life of lithium ion battery | |
CN113567873A (en) | Battery capacity and SOC estimation method based on monomer charging curve difference in battery pack | |
CN111366864B (en) | Battery SOH on-line estimation method based on fixed voltage rise interval | |
CN114942386A (en) | Power battery fault online detection method and system | |
CN113884890A (en) | Power battery internal short circuit detection method | |
CN116754971A (en) | Method, device and storage medium for detecting lithium precipitation of battery | |
CN114910793B (en) | SOH estimation method for series battery pack of energy storage power station |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |