CN114578250B - Lithium battery SOH estimation method based on double-triangular structure matrix - Google Patents
Lithium battery SOH estimation method based on double-triangular structure matrix Download PDFInfo
- Publication number
- CN114578250B CN114578250B CN202210205972.9A CN202210205972A CN114578250B CN 114578250 B CN114578250 B CN 114578250B CN 202210205972 A CN202210205972 A CN 202210205972A CN 114578250 B CN114578250 B CN 114578250B
- Authority
- CN
- China
- Prior art keywords
- health
- double
- triangular matrix
- soh
- health characteristics
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
- G01R31/388—Determining ampere-hour charge capacity or SoC involving voltage measurements
-
- 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]
- G01R31/389—Measuring internal impedance, internal conductance or related variables
-
- 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]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The invention discloses a lithium battery SOH estimation method based on a double-triangular structure matrix; acquiring n health characteristics of the battery and corresponding SOH actual values thereof through a cyclic charge and discharge test; determining the feature weights of the n health features based on a comprehensive correlation analysis method, and forming a health feature distribution rule of a double-triangular matrix according to the feature weights, the random number and the feature weight accumulation interval; training a two-dimensional convolutional neural network by using the health characteristics stored in the double triangular matrix according to the distribution rule and the corresponding SOH actual values; when estimating the SOH of the lithium battery, extracting n health characteristics from the measured data, and inputting the health characteristics stored in the double triangular matrix according to the distribution rule into the two-dimensional convolution neural network to obtain an SOH estimated value; the invention provides an input construction standard for the two-dimensional convolutional neural network, effectively utilizes the information of low correlation characteristics, fully combines the advantages of health characteristics and a two-dimensional data matrix, and improves the accuracy of SOH estimation.
Description
Technical Field
The invention relates to the field of battery state estimation, in particular to a lithium battery SOH estimation method based on a double-triangular structure matrix.
Background
The SOH is used as an important parameter for measuring the running state of the electric automobile, and plays an important role in predicting the driving mileage of the electric automobile and running safely and reliably. The conventional SOH estimation link can be mainly divided into two parts of feature processing and model application.
In the characteristic processing link, health characteristics are constructed to map SOH based on voltage, current, temperature and time data in the operation of the battery or secondary data formed after mathematical calculation of the voltage, the current, the temperature and the time, so that SOH estimation with higher practicability and better robustness can be realized. However, after the characteristics are defined, the existing method directly eliminates the characteristics which are poor in correlation analysis, so that information is lost, and the improvement of the SOH estimation precision is limited.
In the model application link, a data driving method takes a convolutional neural network which develops rapidly in recent years as a representative, the accuracy is ensured by combining a big data training model offline, the real-time performance is ensured by using the model to predict rapidly online, and the two aspects of the accuracy and the real-time performance are considered. However, the input of the existing two-dimensional convolutional neural network lacks an effective construction standard, is obtained by simply copying and splicing the health characteristics, is not processed according to the correlation of the health characteristics, and cannot fully utilize the advantages of the health characteristics and the two-dimensional data matrix.
Disclosure of Invention
The invention provides a lithium battery SOH estimation method based on a double-triangular structure matrix to overcome the defects in the prior art. The technical scheme of the invention is as follows:
a lithium battery SOH estimation method based on a double-triangular structure matrix is characterized by comprising the following specific steps:
s1: defining n health characteristics, and obtaining n health characteristics of each cycle and a corresponding SOH actual value through carrying out cycle charge and discharge tests on the battery;
s2: determining the feature weights of the n health features in the step S1 by adopting a comprehensive correlation analysis method;
s3: forming a health characteristic distribution rule of a left upper area of the double triangular matrix according to the characteristic weight, and forming a health characteristic distribution rule of a right lower area of the double triangular matrix according to the random number and the characteristic weight accumulation interval, so that a health characteristic distribution rule of the whole double triangular matrix is formed;
s4: storing the health characteristics into a double triangular matrix according to the double triangular matrix health characteristic distribution rule formed in the step S3, and then respectively taking the health characteristics in the double triangular matrix and the corresponding SOH actual values as the input and the output of the two-dimensional convolutional neural network to train the two-dimensional convolutional neural network;
s5: and when estimating the SOH of the lithium battery, extracting the n health characteristics from the measured data, storing the health characteristics into a double triangular matrix according to the health characteristic distribution rule of the double triangular matrix formed in the step S3, and inputting the health characteristics in the double triangular matrix into the two-dimensional convolutional neural network in the step S4 to obtain a corresponding SOH estimation value.
In this scheme, the health feature distribution rule of the whole double triangular matrix in step S3 specifically includes the following steps:
s3-1: generating an n × n two-dimensional data matrix according to the health feature number n in step S1, where the specific structure of the two-dimensional data matrix is as follows:
wherein a and b respectively represent the upper left area element and the lower right area element of the double triangular matrix, subscript n, and n represents that the element is positioned in the nth row and column of the double triangular matrix;
s3-2: sequencing the health characteristics according to a rule that the characteristic weight is from large to small, copying n parts of the 1 st health characteristic to the 1 st row of a double-triangular matrix after sequencing is completed, copying (n-1) parts of the 2 nd health characteristic to the 2 nd row of the double-triangular matrix, copying (n +1-i) parts of the ith health characteristic to the ith row of the double-triangular matrix according to the rule in sequence until all the n health characteristics are copied, and thus forming a health characteristic distribution rule of the upper left area of the double-triangular matrix;
s3-3: generating a random number between (0, 1) for each element of the right lower area of the double triangular matrix, and determining the health characteristics stored in the element according to the position of the random number in the characteristic weight accumulation interval, thereby forming a health characteristic distribution rule of the right lower area of the double triangular matrix, wherein the specific rule for determining the health characteristics stored in the element is as follows:
c＝rand(0,1]
where c represents a random number, rand (0, 1), generated each time the health characteristics of the element deposit are determined]Is represented by (0, 1)]Random number x generated in between fill A health feature representing the deposit of a single element, n representing the number of health featuresNumber f 1 、f 2 、f 3 、…、f n-1 、f n Respectively represent the 1 st, 2 nd, 3 rd, … th, (n-1) th and nth health characteristics, omega after,j The feature weight representing the jth healthy feature.
In this embodiment, the method for analyzing comprehensive correlation in step S2 includes the following steps:
s2-1: three correlation coefficient evaluation methods are used to obtain a comprehensive correlation coefficient score, and the specific calculation mode is as follows:
ω before,i ＝β 1 ω 1,i +β 2 ω 2,i +β 3 ω 3,i
wherein, ω is before,i 、ω 1,i 、ω 2,i 、ω 3,i A comprehensive correlation coefficient score, a first correlation coefficient score, a second correlation coefficient score, a third correlation coefficient score, beta, respectively representing the ith health characteristic 1 、β 2 、β 3 Respectively representing the weight of the first correlation fraction, the weight of the second correlation fraction and the weight of the third correlation coefficient fraction, d representing the total charge-discharge cycle number of the battery, f i,k Value, s, representing the ith health feature at the kth cycle k Representing the actual value of SOH, e, of the k-th cycle i,k Represents the difference between the rank of the ith health feature of the kth cycle and the SOH actual value of the kth cycle after the sequence, m i Indicates the number of data not repeated in the i-th health characteristic full cycle data and the total SOH actual valueSmaller value of the number of data not repeated in the cycle data, g i 、h i Respectively representing the number of the same sequence pairs and the number of different sequence pairs of the ith health characteristic and the SOH actual value after sequential arrangement;
s2-2: normalizing the comprehensive correlation coefficient fraction obtained in the step S2-1 to obtain a characteristic weight:
wherein, ω is after,i Feature weight, ω, representing the ith healthy feature before,i 、ω before,j Respectively representing the comprehensive correlation coefficient scores of the ith and jth health characteristics.
In this embodiment, the health characteristics in step S1 specifically define the following rules:
the n health characteristics can be voltage, current, temperature and time data in the operation of the battery, and can also be secondary data formed by performing mathematical calculation on the voltage, the current, the temperature and the time.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the invention determines the feature weight of the health feature based on a comprehensive correlation analysis method, forms the health feature distribution rule of the upper left area of the double-triangular matrix according to the feature weight, and forms the health feature distribution rule of the lower right area of the double-triangular matrix according to the random number and the feature weight accumulation interval, thereby forming the health feature distribution rule of the whole double-triangular matrix, effectively utilizing the information of the low correlation feature and improving the SOH estimation precision. The double triangular matrix provided by the invention provides an input construction standard for a two-dimensional convolution neural network, and fully combines the advantages of health characteristics and a two-dimensional data matrix. In conclusion, the invention has good industrial application prospect.
Drawings
Fig. 1 is a flow chart of a lithium battery SOH estimation method based on a double triangular structure matrix according to the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
In a specific embodiment, as shown in fig. 1, a method for estimating the SOH of a lithium battery based on a double triangular structure matrix includes the following steps:
s1: defining n health characteristics, and obtaining n health characteristics of each cycle and a corresponding SOH actual value through carrying out cycle charge and discharge tests on the battery;
s2: determining the feature weights of the n health features in the step S1 by adopting a comprehensive correlation analysis method;
s3: forming a health characteristic distribution rule of a left upper area of the double triangular matrix according to the characteristic weight, and forming a health characteristic distribution rule of a right lower area of the double triangular matrix according to the random number and the characteristic weight accumulation interval, so that a health characteristic distribution rule of the whole double triangular matrix is formed;
s4: storing the health characteristics into a double triangular matrix according to the double triangular matrix health characteristic distribution rule formed in the step S3, and then respectively taking the health characteristics in the double triangular matrix and the corresponding SOH actual values as the input and the output of the two-dimensional convolutional neural network to train the two-dimensional convolutional neural network;
s5: and when estimating the SOH of the lithium battery, extracting the n health characteristics from the measured data, storing the health characteristics into a double triangular matrix according to the health characteristic distribution rule of the double triangular matrix formed in the step S3, and inputting the health characteristics in the double triangular matrix into the two-dimensional convolutional neural network in the step S4 to obtain a corresponding SOH estimation value.
In this scheme, the health feature distribution rule of the whole double triangular matrix in step S3 specifically includes the following steps:
s3-1: generating an n × n two-dimensional data matrix according to the health feature number n in step S1, where the specific structure of the two-dimensional data matrix is as follows:
wherein a and b respectively represent the upper left area element and the lower right area element of the double triangular matrix, subscript n, and n represents that the element is positioned in the nth row and column of the double triangular matrix;
s3-2: sequencing the health characteristics according to a rule that the characteristic weight is from large to small, copying n parts of the 1 st health characteristic to the 1 st row of a double-triangular matrix after sequencing is completed, copying (n-1) parts of the 2 nd health characteristic to the 2 nd row of the double-triangular matrix, copying (n +1-i) parts of the ith health characteristic to the ith row of the double-triangular matrix according to the rule in sequence until all the n health characteristics are copied, and thus forming a health characteristic distribution rule of the upper left area of the double-triangular matrix;
s3-3: generating a random number between (0, 1) for each element of the right lower area of the double triangular matrix, and determining the health characteristics stored in the element according to the position of the random number in the characteristic weight accumulation interval, thereby forming a health characteristic distribution rule of the right lower area of the double triangular matrix, wherein the specific rule for determining the health characteristics stored in the element is as follows:
c＝rand(0,1]
where c represents a random number, rand (0, 1), generated each time the health characteristics of the element deposit are determined]Is represented by (0, 1)]Random number x generated in between fill Health characteristics representing the individual element deposit, n represents the number of health characteristics, f 1 、f 2 、f 3 、…、f n-1 、f n Respectively represent the 1 st, 2 nd, 3 rd, … thN-1, n health characteristics, ω after,j The feature weight representing the jth healthy feature.
In this embodiment, the method for analyzing comprehensive correlation in step S2 includes the following steps:
s2-1: three correlation coefficient evaluation methods are used to obtain a comprehensive correlation coefficient score, and the specific calculation mode is as follows:
ω before,i ＝β 1 ω 1,i +β 2 ω 2,i +β 3 ω 3,i
wherein, ω is before,i 、ω 1,i 、ω 2,i 、ω 3,i A comprehensive correlation coefficient score, a first correlation coefficient score, a second correlation coefficient score, a third correlation coefficient score, beta, respectively representing the ith health characteristic 1 、β 2 、β 3 Respectively representing the weight of the first correlation fraction, the weight of the second correlation fraction and the weight of the third correlation coefficient fraction, d representing the total charge-discharge cycle number of the battery, f i,k Value, s, representing the ith health feature at the kth cycle k Representing the actual value of SOH, e, of the k-th cycle i,k Represents the difference between the rank of the ith health feature of the kth cycle and the SOH actual value of the kth cycle after the sequence, m i G is the smaller of the number of data not repeated in the i-th health characteristic total cycle data and the number of data not repeated in the SOH actual value total cycle data i 、h i Respectively represent the ith health characteristic and the actual value of SOHThe number of the same sequence pairs and the number of the different sequence pairs after the sequence arrangement;
s2-2: normalizing the comprehensive correlation coefficient fraction obtained in the step S2-1 to obtain a characteristic weight:
wherein, ω is after,i Feature weight, ω, representing the ith healthy feature before,i 、ω before,j Respectively representing the integral correlation coefficient scores of the ith and the jth health characteristics.
In this embodiment, the health characteristics in step S1 specifically define the following rules:
the n health characteristics can be voltage, current, temperature and time data in the operation of the battery, and can also be secondary data formed by performing mathematical calculation on the voltage, the current, the temperature and the time.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (2)
1. A lithium battery SOH estimation method based on a double-triangular structure matrix is characterized by comprising the following specific steps:
s1: defining n health characteristics, and obtaining n health characteristics of each cycle and a corresponding SOH actual value through carrying out cycle charge and discharge tests on the battery;
s2: determining the feature weights of the n health features in step S1 by using a comprehensive correlation analysis method, wherein the comprehensive correlation analysis method in step S2 specifically comprises the following steps:
s2-1: three correlation coefficient evaluation methods are used to obtain a comprehensive correlation coefficient score, and the specific calculation mode is as follows:
ω before,i ＝β 1 ω 1,i +β 2 ω 2,i +β 3 ω 3,i
i＝1,2,...,n
wherein, ω is before,i 、ω 1,i 、ω 2,i 、ω 3,i A comprehensive correlation coefficient score, a first correlation coefficient score, a second correlation coefficient score, and a third correlation coefficient score, beta, respectively representing the ith health characteristic 1 、β 2 、β 3 Respectively representing the weight of the first correlation fraction, the weight of the second correlation fraction and the weight of the third correlation coefficient fraction, d representing the total charge-discharge cycle number of the battery, f i,k Value, s, representing the ith health feature at the kth cycle k Representing the actual value of SOH, e, of the k-th cycle i,k Represents the difference between the rank of the ith health feature of the kth cycle and the SOH actual value of the kth cycle after the sequence, m i G is the smaller of the number of data not repeated in the i-th health characteristic total cycle data and the number of data not repeated in the SOH actual value total cycle data i 、h i Respectively representing the number of the same sequence pairs and the number of different sequence pairs of the ith health characteristic and the SOH actual value after sequential arrangement;
s2-2: normalizing the comprehensive correlation coefficient fraction obtained in the step S2-1 to obtain a characteristic weight:
i＝1,2,...,n
wherein, ω is after,i Feature weight, ω, representing the ith healthy feature before,i 、ω before,j Respectively representing the comprehensive correlation coefficient scores of the ith and jth health characteristics;
s3: forming a health characteristic distribution rule of a left upper area of the double triangular matrix according to the characteristic weight, and forming a health characteristic distribution rule of a right lower area of the double triangular matrix according to the random number and the characteristic weight accumulation interval, thereby forming a health characteristic distribution rule of the whole double triangular matrix, which comprises the following specific forming steps:
s3-1: generating an n × n two-dimensional data matrix according to the health feature number n in step S1, where the two-dimensional data matrix has the following specific structure:
wherein a and b respectively represent the upper left area element and the lower right area element of the double triangular matrix, subscript n, and n represents that the element is positioned in the nth row and column of the double triangular matrix;
s3-2: sequencing the health characteristics according to a rule that the characteristic weight is from large to small, copying n parts of the 1 st health characteristic to the 1 st row of a double-triangular matrix after sequencing is completed, copying (n-1) parts of the 2 nd health characteristic to the 2 nd row of the double-triangular matrix, copying (n +1-i) parts of the ith health characteristic to the ith row of the double-triangular matrix according to the rule in sequence until all the n health characteristics are copied, and thus forming a health characteristic distribution rule of the upper left area of the double-triangular matrix;
s3-3: generating a random number between (0, 1) for each element of the right lower area of the double triangular matrix, and determining the health characteristics stored in the element according to the position of the random number in the characteristic weight accumulation interval, thereby forming a health characteristic distribution rule of the right lower area of the double triangular matrix, wherein the specific rule for determining the health characteristics stored in the element is as follows:
c＝rand(0,1]
where c represents a random number, rand (0, 1), generated each time the element storage health characteristics are determined]Is represented by (0, 1)]Random number x generated in between fill Representing the health characteristics of a single element deposit, n representing the number of health characteristics, f 1 、f 2 、f 3 、…、f n-1 、f n Respectively represent the 1 st, 2 nd, 3 rd, … th, (n-1) th and nth health characteristics, omega after,j A feature weight representing a jth healthy feature;
s4: storing the health characteristics into a double-triangular matrix according to the double-triangular matrix health characteristic distribution rule formed in the step S3, and then respectively taking the health characteristics in the double-triangular matrix and the corresponding SOH actual values as the input and the output of the two-dimensional convolutional neural network to train the two-dimensional convolutional neural network;
s5: and when estimating the SOH of the lithium battery, extracting the n health characteristics from the measured data, storing the health characteristics into a double triangular matrix according to the health characteristic distribution rule of the double triangular matrix formed in the step S3, and inputting the health characteristics in the double triangular matrix into the two-dimensional convolutional neural network in the step S4 to obtain a corresponding SOH estimation value.
2. The method for estimating the SOH of the lithium battery based on the double triangular structure matrix according to claim 1, wherein the health characteristics in step S1 are specifically defined as follows:
the n health characteristics are data of voltage, current, temperature and time in the operation of the battery or secondary data formed by performing mathematical calculation on the voltage, the current, the temperature and the time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210205972.9A CN114578250B (en) | 2022-02-28 | 2022-02-28 | Lithium battery SOH estimation method based on double-triangular structure matrix |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210205972.9A CN114578250B (en) | 2022-02-28 | 2022-02-28 | Lithium battery SOH estimation method based on double-triangular structure matrix |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114578250A CN114578250A (en) | 2022-06-03 |
| CN114578250B true CN114578250B (en) | 2022-09-02 |
Family
ID=81771579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210205972.9A Active CN114578250B (en) | 2022-02-28 | 2022-02-28 | Lithium battery SOH estimation method based on double-triangular structure matrix |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114578250B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110988839A (en) * | 2019-12-25 | 2020-04-10 | 中南大学 | Method for quickly identifying health condition of wall based on one-dimensional convolutional neural network |
| CN111638465A (en) * | 2020-05-29 | 2020-09-08 | 浙大宁波理工学院 | Lithium battery health state estimation method based on convolutional neural network and transfer learning |
| CN113009349A (en) * | 2021-04-09 | 2021-06-22 | 哈尔滨工业大学 | Lithium ion battery health state diagnosis method based on deep learning model |
| CN113917337A (en) * | 2021-10-13 | 2022-01-11 | 国网福建省电力有限公司 | Battery health state estimation method based on charging data and LSTM neural network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11637331B2 (en) * | 2017-11-20 | 2023-04-25 | The Trustees Of Columbia University In The City Of New York | Neural-network state-of-charge and state of health estimation |
| KR20210041511A (en) * | 2019-10-07 | 2021-04-15 | 삼성에스디아이 주식회사 | Method and apparatus for estimating state of health of battery |
-
2022
- 2022-02-28 CN CN202210205972.9A patent/CN114578250B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110988839A (en) * | 2019-12-25 | 2020-04-10 | 中南大学 | Method for quickly identifying health condition of wall based on one-dimensional convolutional neural network |
| CN111638465A (en) * | 2020-05-29 | 2020-09-08 | 浙大宁波理工学院 | Lithium battery health state estimation method based on convolutional neural network and transfer learning |
| CN113009349A (en) * | 2021-04-09 | 2021-06-22 | 哈尔滨工业大学 | Lithium ion battery health state diagnosis method based on deep learning model |
| CN113917337A (en) * | 2021-10-13 | 2022-01-11 | 国网福建省电力有限公司 | Battery health state estimation method based on charging data and LSTM neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114578250A (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112765772B (en) | Power battery residual life prediction method based on data driving | |
| CN109061504B (en) | Method and system for predicting remaining service life of lithium ion batteries of same type and different types | |
| CN113805064B (en) | Lithium ion battery pack health state prediction method based on deep learning | |
| CN113917337A (en) | Battery health state estimation method based on charging data and LSTM neural network | |
| CN111443293A (en) | Lithium battery state of health (SOH) estimation method based on data driving | |
| CN112684363A (en) | Lithium ion battery health state estimation method based on discharge process | |
| CN111191824B (en) | Power battery capacity attenuation prediction method and system | |
| CN113125960A (en) | Vehicle-mounted lithium ion battery charge state prediction method based on random forest model | |
| CN115374995A (en) | Distributed photovoltaic and small wind power station power prediction method | |
| CN116298934B (en) | Modeling method of prediction network for lithium battery health state estimation | |
| CN112861436A (en) | Real-time prediction method for engine emission | |
| CN111537888A (en) | Data-driven echelon battery SOC prediction method | |
| CN113406503A (en) | Lithium battery SOH online estimation method based on deep neural network | |
| CN113791351B (en) | Lithium battery life prediction method based on transfer learning and difference probability distribution | |
| CN113033104B (en) | Lithium battery state of charge estimation method based on graph convolution | |
| CN111337833B (en) | Lithium battery capacity integrated prediction method based on dynamic time-varying weight | |
| CN114578250B (en) | Lithium battery SOH estimation method based on double-triangular structure matrix | |
| CN116908727A (en) | Multi-feature combination-based energy storage power station lithium battery capacity estimation method | |
| CN117074951A (en) | Lithium battery state of charge estimation method, device, equipment and readable storage medium | |
| Celen et al. | Calendar ageing modelling using machine learning: an experimental investigation on lithium ion battery chemistries | |
| CN116359762B (en) | Battery state of charge estimation method based on deep learning and network compression | |
| CN116338501B (en) | Lithium ion battery health detection method based on neural network prediction relaxation voltage | |
| Atamuradov et al. | Evaluation of Features with Changing Effectiveness for Prognostics | |
| CN117169743A (en) | Battery health state estimation method and device based on partial data and model fusion | |
| CN114720882B (en) | Reconstruction method of maximum capacity fading curve 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 |