CN111812535A - Power battery fault diagnosis method and system based on data driving - Google Patents

Power battery fault diagnosis method and system based on data driving Download PDF

Info

Publication number
CN111812535A
CN111812535A CN202010616251.8A CN202010616251A CN111812535A CN 111812535 A CN111812535 A CN 111812535A CN 202010616251 A CN202010616251 A CN 202010616251A CN 111812535 A CN111812535 A CN 111812535A
Authority
CN
China
Prior art keywords
data
power battery
module
model
fault diagnosis
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
Application number
CN202010616251.8A
Other languages
Chinese (zh)
Inventor
张涌
黄林雄
张煜
吕立亚
赵奉奎
李冰林
吴海啸
姜朋昌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Forestry University
Original Assignee
Nanjing Forestry University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing Forestry University filed Critical Nanjing Forestry University
Priority to CN202010616251.8A priority Critical patent/CN111812535A/en
Publication of CN111812535A publication Critical patent/CN111812535A/en
Pending legal-status Critical Current

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]
    • G01R31/3644—Constructional arrangements
    • G01R31/3648—Constructional arrangements comprising digital calculation means, e.g. for performing an algorithm
    • 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]
    • G01R31/385—Arrangements for measuring battery or accumulator variables
    • G01R31/387—Determining ampere-hour charge capacity or SoC

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)
  • Tests Of Electric Status Of Batteries (AREA)

Abstract

The invention provides a power battery fault diagnosis method and an early warning system based on data driving, which comprises the following steps: step 1, collecting performance parameters of a power battery under various working conditions and various states of the power battery, wherein the performance parameters comprise the capacity, the voltage, the internal resistance, the power and the like of the power battery; step 2, cleaning the acquired data; step 3, calculating the SOC and SOH of the power battery according to the cleaned data; step 4, formulating a fault level according to actual driving experience and automobile safety; step 5, making the data obtained in the steps 2, 3 and 4 into a data set; step 6, putting the training set into a gradient lifting regression tree model, and performing iterative training on the training set; and 7, putting the test set into a model, evaluating the accuracy of the model, and adjusting the parameters of the model according to the accuracy. The method and the device can realize accurate prediction of the power battery fault, carry out early warning on the fault and greatly improve the safety of the electric automobile.

Description

Power battery fault diagnosis method and system based on data driving
Technical Field
The invention relates to the field of safety of power batteries of electric automobiles, in particular to a power battery fault diagnosis method and system based on data driving.
Background
With the increasingly prominent environmental protection problem and energy problem, various industries have responded to the national call for energy conservation and emission reduction, and the new energy industry has come into spring. The new energy automobile is regarded as a support industry of the new energy industry, and is focused by the nation, the new energy automobile is listed as one of seven strategic emerging industries in China, and the new energy automobile can be considered as the best development era of the new energy automobile in the current era.
The new energy automobile mainly comprises a pure electric automobile, a fuel cell automobile and a hybrid electric automobile, wherein the pure electric automobile drives the automobile to run by taking electric energy provided by a storage battery as a power source; the fuel cell automobile drives the automobile by means of electric energy generated by a fuel cell; hybrid vehicles rely on a conventional internal combustion engine in conjunction with a generator to drive the vehicle. No matter which form of new energy automobile, the electric energy provided by the battery is used as the power source of the new energy automobile. With the development of technology, lithium ion batteries are widely used. Compared with the traditional lead-acid battery, the lithium ion power battery has the characteristics of higher energy density, wide working temperature range, long service life and stable power supply. However, the lithium ion power battery is a complex electrochemical system, the working principle and the failure mechanism of the lithium ion power battery are extremely complex, and the working condition and the use environment of the electric vehicle have complexity, so that the possibility of the lithium ion power battery being in failure is greatly improved, the destructive power generated by the lithium ion power battery is strong, and the life of a driver is seriously influenced. In conclusion, the method has important significance for fault diagnosis of the power battery.
At the present stage, the power battery fault diagnosis has the difficulties of diversity of diagnosis objects and complexity of fault states, so that the fault diagnosis intelligence and the fault diagnosis adaptability need to be continuously improved. At present, mainstream fault diagnosis is divided into an offline diagnosis mode and an online diagnosis mode, wherein the offline diagnosis mode cannot meet the fault diagnosis requirement of the power battery of the new energy automobile, and the fault diagnosis mode has the characteristics of low intelligence and weak adaptability of fault diagnosis.
Disclosure of Invention
Aiming at the difficulties and the defects in the prior art, the invention aims to provide a power battery fault diagnosis method and system based on data driving.
The invention provides a power battery fault diagnosis method based on data driving, which comprises the following steps:
step 1: collecting performance parameters of the power battery under various working conditions and various states of the power battery;
step 2: cleaning the acquired data;
and step 3: calculating the SOC and SOH of the power battery according to the cleaned data;
and 4, step 4: formulating a fault level according to actual driving experience and automobile safety;
and 5: making the data obtained in the steps 2, 3 and 4 into a data set;
step 6: putting the training set into a gradient lifting regression tree model, and performing iterative training on the gradient lifting regression tree model;
and 7: and putting the test set into the model, evaluating the accuracy of the model, and adjusting the parameters of the model according to the accuracy.
The power battery performance parameters comprise: capacity, voltage, internal resistance and power of the power battery.
Preferably, the step 2 includes:
step 2.1: data cleaning is carried out, and data with serious deviation are deleted;
step 2.2: duplicate redundant data is deleted.
Preferably, the step 5 comprises:
step 5.1: matching the fault grade with the battery parameters to form a complete data set;
step 5.2: the data set is split into a training set and a test set.
Preferably, the step 6 comprises:
step 6.1: defining a training set as: x ═ X1，...，xnThe target is: y ═ Y1，...，ynCalculating initial values of the optimal segmentation characteristic j and the segmentation value s by using the following formula;
Figure BSA0000212381710000021
in the formula, c1、c2Raising the output value, R, of each region of the regression tree for the gradient1(j, s) are divided regions.
Step 6.2: defining an initialized single-node tree F as shown in0(x)：
Figure BSA0000212381710000022
In the formula, c is the output value of each region of the gradient lifting regression tree.
Step 6.3: the loss function is defined as follows:
L(y，F(x))＝y-F(x)
step 6.4: iterative training, namely performing residual error fitting on the model after each round of iterative training, and obtaining a gradient lifting regression tree model shown as the following formula after p times of iterative training:
Figure BSA0000212381710000023
Figure BSA0000212381710000024
in the formula (I), the compound is shown in the specification,
Figure BSA0000212381710000025
and (4) segmenting the original data domain for m nodes in the gradient lifting regression tree to generate corresponding data segments.
Preferably, the step 7 includes:
step 7.1: calculating the regression error of the test set;
step 7.2: and judging whether to modify the model parameters according to the regression error.
According to the invention, a data-driven-based power battery fault diagnosis system is provided, which comprises:
module 1: collecting performance parameters of the power battery under various working conditions and various states of the power battery;
and (3) module 2: cleaning the acquired data;
and a module 3: calculating the SOC and SOH of the power battery according to the cleaned data;
and (4) module: formulating a fault level according to actual driving experience and automobile safety;
and a module 5: making the data obtained in the steps 2, 3 and 4 into a data set;
and a module 6: putting the training set into a gradient lifting regression tree model, and performing iterative training on the gradient lifting regression tree model;
a module 7; and putting the test set into the model, evaluating the accuracy of the model, and adjusting the parameters of the model according to the accuracy.
The power battery performance parameters comprise: capacity, voltage, internal resistance and power of the power battery.
Preferably, the module 2 comprises:
module 2.1: data cleaning is carried out, and data with serious deviation are deleted;
module 2.2: duplicate redundant data is deleted.
Preferably, said module 5 comprises:
module 5.1: matching the fault grade with the battery parameters to form a complete data set;
module 5.2: the data set is split into a training set and a test set.
Preferably, said module 6 comprises:
module 6.1: defining a training set as: x ═ X1，...，xnThe target is: y ═ Y1，...，ynCalculating initial values of the optimal segmentation characteristic j and the segmentation value s by using the following formula;
Figure BSA0000212381710000031
in the formula, c1、c2Raising the output value, R, of each region of the regression tree for the gradient1(j, s) are divided regions.
Module 6.2: defining an initialized single-node tree F as shown in0(x)：
Figure BSA0000212381710000032
In the formula, c is the output value of each region of the gradient lifting regression tree.
Module 6.3: the loss function is defined as follows:
L(y，F(x))＝y-F(x)
module 6.4: iterative training, namely performing residual error fitting on the model after each round of iterative training, and obtaining a gradient lifting regression tree model shown as the following formula after p times of iterative training:
Figure BSA0000212381710000033
Figure BSA0000212381710000034
in the formula (I), the compound is shown in the specification,
Figure BSA0000212381710000035
and (4) segmenting the original data domain for m nodes in the gradient lifting regression tree to generate corresponding data segments.
Preferably, said module 7 comprises:
module 7.1: calculating the regression error of the test set;
module 7.2: and judging whether to modify the model parameters according to the regression error.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention has the characteristics of strong adaptability because a large amount of data is collected as the training set of the system, can be suitable for various working conditions in the actual use of new energy vehicles, and has higher intelligent level;
2. the invention has higher accuracy for the fault diagnosis result through the training of a large amount of data, and can realize the rapid diagnosis of the fault.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a schematic diagram of a gradient lifting regression tree structure.
Detailed Description
The present invention will be described in detail below with reference to lithium iron phosphate batteries, and in particular embodiments of the present invention, the SOC and SOH of the power battery are calculated by methods that are currently common, and different embodiments may use different calculation methods. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
The invention provides a power battery fault diagnosis method based on data driving, which comprises the following steps:
step 1: collecting performance parameters of the lithium iron phosphate battery under various working conditions and various states of the lithium iron phosphate battery;
step 2: cleaning the acquired data;
and step 3: calculating the SOC and SOH of the power battery according to the cleaned data;
and 4, step 4: formulating a fault level according to actual driving experience and automobile safety;
and 5: making the data obtained in the steps 2, 3 and 4 into a data set;
step 6: putting the training set into a gradient lifting regression tree model, and performing iterative training on the gradient lifting regression tree model;
and 7: and putting the test set into the model, evaluating the accuracy of the model, and adjusting the parameters of the model according to the accuracy.
The lithium iron phosphate battery performance parameters comprise: capacity, voltage, internal resistance and power of the power battery.
Preferably, the step 2 includes:
step 2.1: data cleaning is carried out, and data with serious deviation are deleted;
step 2.2: duplicate redundant data is deleted.
Preferably, the step 3 comprises:
step 3.1: the SOC of the lithium iron phosphate battery is calculated by using an ampere-hour integration method common in the current engineering, and the calculation formula is as follows:
Figure BSA0000212381710000041
in the formula, SOC0The SOC value in the initial state can be inquired according to an OCV-SOC table; q is the capacity of the lithium iron phosphate battery; eta is a static capacity test value; i is a current value.
Step 3.2: the SOH is calculated by using a currently common mode of applying the change of the internal resistance of the battery, and the calculation formula is as follows:
Figure BSA0000212381710000042
in the formula, R0Actually measuring internal resistance for the battery; rnewThe internal resistance of the battery when leaving factory; rEOLThe internal resistance value of the battery when the battery reaches the cycle life.
Preferably, the step 5 comprises:
step 5.1: matching the fault grade with the battery parameters to form a complete data set;
step 5.2: the data set is split into a training set and a test set.
Preferably, the step 6 comprises:
step 6.1: defining a training set as: x ═ X1，...，xnThe target is: y ═ Y1，...，ynCalculating initial values of the optimal segmentation characteristic j and the segmentation value s by using the following formula;
Figure BSA0000212381710000051
in the formula, c1、c2Raising the output value, R, of each region of the regression tree for the gradient1(j, s) are divided regions.
Step 6.2: defining an initialized single-node tree F as shown in0(x)：
Figure BSA0000212381710000052
In the formula, c is the output value of each region of the gradient lifting regression tree.
Step 6.3: the loss function is defined as follows:
L(y，F(x))＝y-F(x)
step 6.4: iterative training, namely performing residual error fitting on the model after each round of iterative training, and obtaining a gradient lifting regression tree model shown as the following formula after p times of iterative training:
Figure BSA0000212381710000053
Figure BSA0000212381710000054
in the formula (I), the compound is shown in the specification,
Figure BSA0000212381710000055
corresponding data segments generated by segmenting original data domain for m nodes in gradient lifting regression tree。
Preferably, the step 7 includes:
step 7.1: calculating the regression error of the test set;
step 7.2: and judging whether to modify the model parameters according to the regression error.
According to the invention, a data-driven-based power battery fault diagnosis system is provided, which comprises:
module 1: collecting performance parameters of the power battery under various working conditions and various states of the power battery;
and (3) module 2: cleaning the acquired data;
and a module 3: calculating the SOC and SOH of the power battery according to the cleaned data;
and (4) module: formulating a fault level according to actual driving experience and automobile safety;
and a module 5: making the data obtained in the steps 2, 3 and 4 into a data set;
and a module 6: putting the training set into a gradient lifting regression tree model, and performing iterative training on the gradient lifting regression tree model;
and a module 7: and putting the test set into the model, evaluating the accuracy of the model, and adjusting the parameters of the model according to the accuracy.
The power battery performance parameters comprise: capacity, voltage, internal resistance and power of the power battery.
Preferably, the module 2 comprises:
module 2.1: data cleaning is carried out, and data with serious deviation are deleted;
module 2.2: duplicate redundant data is deleted.
Preferably, the module 3 comprises:
module 3.1: the SOC of the lithium iron phosphate battery is calculated by using an ampere-hour integration method common in the current engineering, and the calculation formula is as follows:
Figure BSA0000212381710000061
in the formula, SOC0Is in an initial stateThe lower SOC value can be inquired according to an OCV-SOC table; q is the capacity of the lithium iron phosphate battery; eta is a static capacity test value; i is a current value.
Module 3.2: the SOH is calculated by using a currently common mode of applying the change of the internal resistance of the battery, and the calculation formula is as follows:
Figure BSA0000212381710000062
in the formula, R0Actually measuring internal resistance for the battery; rnewThe internal resistance of the battery when leaving factory; rEOLThe internal resistance value of the battery when the battery reaches the cycle life.
Preferably, said module 5 comprises:
module 5.1: matching the fault grade with the battery parameters to form a complete data set;
module 5.2: the data set is split into a training set and a test set.
Preferably, said module 6 comprises:
module 6.1: defining a training set as: x ═ X1，...，xnThe target is: y ═ Y1，...，ynCalculating initial values of the optimal segmentation characteristic j and the segmentation value s by using the following formula;
Figure BSA0000212381710000063
in the formula, c1、c2Raising the output value, R, of each region of the regression tree for the gradient1(j, s) are divided regions.
Module 6.2: defining an initialized single-node tree F as shown in0(x)：
Figure BSA0000212381710000064
In the formula, c is the output value of each region of the gradient lifting regression tree.
Module 6.3: the loss function is defined as follows:
L(y，F(x))＝y-F(x)
module 6.4: iterative training, namely performing residual error fitting on the model after each round of iterative training, and obtaining a gradient lifting regression tree model shown as the following formula after p times of iterative training:
Figure BSA0000212381710000065
Figure BSA0000212381710000066
in the formula (I), the compound is shown in the specification,
Figure BSA0000212381710000067
and (4) segmenting the original data domain for m nodes in the gradient lifting regression tree to generate corresponding data segments.
Preferably, said module 7 comprises:
module 7.1: calculating the regression error of the test set;
module 7.2: and judging whether to modify the model parameters according to the regression error.

Claims (11)

1. A power battery fault diagnosis method based on data driving is characterized by comprising the following steps:
step 1: collecting performance parameters of the power battery under various working conditions and various states of the power battery;
step 2: cleaning the acquired data;
and step 3: calculating the SOC and SOH of the power battery according to the cleaned data;
and 4, step 4: formulating a fault level according to actual driving experience and automobile safety;
and 5: making the data obtained in the steps 2, 3 and 4 into a data set;
step 6: putting the training set into a gradient lifting regression tree model, and performing iterative training on the gradient lifting regression tree model;
and 7: and putting the test set into the model, evaluating the accuracy of the model, and adjusting the parameters of the model according to the accuracy.
The power battery performance parameters comprise: capacity, voltage, internal resistance and power of the power battery.
2. The method for diagnosing the fault of the power battery based on the data driving as claimed in claim 1, wherein the step 2 comprises:
step 2.1: data cleaning is carried out, and data with serious deviation are deleted;
step 2.2: duplicate redundant data is deleted.
3. The data drive-based power battery fault diagnosis method according to claim 1, wherein the step 5 comprises:
step 5.1: matching the fault grade with the battery parameters to form a complete data set;
step 5.2: the data set is split into a training set and a test set.
4. The data drive-based power battery fault diagnosis method according to claim 1, wherein the step 6 comprises:
step 6.1: defining a training set as: x ═ X1，...，xnThe target is: y ═ Y1，...，ynCalculating initial values of the optimal segmentation characteristic j and the segmentation value s by using the following formula;
Figure FSA0000212381700000011
in the formula, c1、c2Raising the output value, R, of each region of the regression tree for the gradient1(j, s) are divided regions.
Step 6.2: defining an initialized single-node tree F as shown in0(x)：
Figure FSA0000212381700000012
In the formula, c is the output value of each region of the gradient lifting regression tree.
Step 6.3: the loss function is defined as follows:
L(y，F(x))＝y-F(x)
step 6.4: iterative training, namely performing residual error fitting on the model after each round of iterative training, and obtaining a gradient lifting regression tree model shown as the following formula after p times of iterative training:
Figure FSA0000212381700000013
Figure FSA0000212381700000014
in the formula (I), the compound is shown in the specification,
Figure FSA0000212381700000021
and (4) segmenting the original data domain for m nodes in the gradient lifting regression tree to generate corresponding data segments.
5. The data drive-based power battery fault diagnosis method according to claim 1, wherein the step 7 comprises:
step 7.1: calculating the regression error of the test set;
step 7.2: and judging whether to modify the model parameters according to the regression error.
6. A data-driven-based power battery fault diagnosis system, comprising:
module (1): collecting performance parameters of the power battery under various working conditions and various states of the power battery;
module (2): cleaning the acquired data;
module (3): calculating the SOC and SOH of the power battery according to the cleaned data;
module (4): formulating a fault level according to actual driving experience and automobile safety;
module (5): making the data obtained in the steps 2, 3 and 4 into a data set;
module (6): putting the training set into a gradient lifting regression tree model, and performing iterative training on the gradient lifting regression tree model;
module (7): and putting the test set into the model, evaluating the accuracy of the model, and adjusting the parameters of the model according to the accuracy.
7. The data-drive-based power battery fault diagnosis system according to claim 6, characterized in that the parameters of the specific power battery to be collected by the module (1) are: capacity, voltage, internal resistance and power of the power battery.
8. The data drive-based power battery fault diagnosis system according to claim 6, wherein the module (2) comprises:
module (2.1): data cleaning is carried out, and data with serious deviation are deleted;
module (2.2): duplicate redundant data is deleted.
9. The data drive-based power battery fault diagnosis system according to claim 6, wherein the module (5) comprises:
module (5.1): matching the fault grade with the battery parameters to form a complete data set;
module (5.2): the data set is split into a training set and a test set.
10. The data drive-based power battery fault diagnosis system according to claim 6, wherein the module (6) comprises:
module (6.1): defining a training set as: x ═ X1，...，xnThe target is: y ═ Y1，...，ynCalculating initial values of the optimal segmentation characteristic j and the segmentation value s by using the following formula;
Figure FSA0000212381700000022
in the formula, c1、c2Raising the output value, R, of each region of the regression tree for the gradient1(j, s) are divided regions.
Module (6.2): defining an initialized single-node tree F as shown in0(x)：
Figure FSA0000212381700000023
In the formula, c is the output value of each region of the gradient lifting regression tree.
Module (6.3): the loss function is defined as follows:
L(y，F(x))＝y-F(x)
module (6.4): iterative training, namely performing residual error fitting on the model after each round of iterative training, and obtaining a gradient lifting regression tree model shown as the following formula after p times of iterative training:
Figure FSA0000212381700000031
Figure FSA0000212381700000032
in the formula (I), the compound is shown in the specification,
Figure FSA0000212381700000033
and (4) segmenting the original data domain for m nodes in the gradient lifting regression tree to generate corresponding data segments.
11. The data drive-based power battery fault diagnosis system according to claim 6, wherein the module (7) includes:
module (7.1): calculating the regression error of the test set;
module (7.2): and judging whether to modify the model parameters according to the regression error.
CN202010616251.8A 2020-06-30 2020-06-30 Power battery fault diagnosis method and system based on data driving Pending CN111812535A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010616251.8A CN111812535A (en) 2020-06-30 2020-06-30 Power battery fault diagnosis method and system based on data driving

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010616251.8A CN111812535A (en) 2020-06-30 2020-06-30 Power battery fault diagnosis method and system based on data driving

Publications (1)

Publication Number Publication Date
CN111812535A true CN111812535A (en) 2020-10-23

Family

ID=72855214

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010616251.8A Pending CN111812535A (en) 2020-06-30 2020-06-30 Power battery fault diagnosis method and system based on data driving

Country Status (1)

Country Link
CN (1) CN111812535A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112782589A (en) * 2021-01-26 2021-05-11 武汉理工大学 Vehicle-mounted fuel cell remote fault classification diagnosis method and device and storage medium
CN113866642A (en) * 2021-09-22 2021-12-31 中国华能集团清洁能源技术研究院有限公司 Lithium ion battery fault diagnosis method based on gradient lifting tree
CN116154239A (en) * 2023-04-14 2023-05-23 湖南省计量检测研究院 Multi-level implementation-based hydrogen fuel cell energy conversion method and device
CN117067920A (en) * 2023-10-18 2023-11-17 北京航空航天大学 Fault detection method and device of power battery, electronic equipment and electric automobile

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112782589A (en) * 2021-01-26 2021-05-11 武汉理工大学 Vehicle-mounted fuel cell remote fault classification diagnosis method and device and storage medium
CN113866642A (en) * 2021-09-22 2021-12-31 中国华能集团清洁能源技术研究院有限公司 Lithium ion battery fault diagnosis method based on gradient lifting tree
CN116154239A (en) * 2023-04-14 2023-05-23 湖南省计量检测研究院 Multi-level implementation-based hydrogen fuel cell energy conversion method and device
CN116154239B (en) * 2023-04-14 2023-11-21 湖南省计量检测研究院 Multi-level implementation-based hydrogen fuel cell energy conversion method and device
CN117067920A (en) * 2023-10-18 2023-11-17 北京航空航天大学 Fault detection method and device of power battery, electronic equipment and electric automobile
CN117067920B (en) * 2023-10-18 2024-01-05 北京航空航天大学 Fault detection method and device of power battery, electronic equipment and electric automobile

Similar Documents

Publication Publication Date Title
CN111812535A (en) Power battery fault diagnosis method and system based on data driving
Feng et al. Propagation mechanisms and diagnosis of parameter inconsistency within Li-Ion battery packs
CN110346734B (en) Machine learning-based lithium ion power battery health state estimation method
Yu et al. OCV-SOC-temperature relationship construction and state of charge estimation for a series–parallel lithium-ion battery pack
Jiaqiang et al. Effects analysis on active equalization control of lithium-ion batteries based on intelligent estimation of the state-of-charge
CN107741568B (en) Lithium battery SOC estimation method based on state transition optimization RBF neural network
CN111352032A (en) Lithium battery dynamic peak power prediction method
WO2019184864A1 (en) Electric vehicle, and system and method for giving prompt according to usage habits of user thereof
CN111983457A (en) Battery pack SOH estimation method based on LSTM neural network
CN111308356A (en) SOC estimation method with weighted ampere-hour integration
CN111366864B (en) Battery SOH on-line estimation method based on fixed voltage rise interval
CN112163372B (en) SOC estimation method of power battery
CN112858929A (en) Battery SOC estimation method based on fuzzy logic and extended Kalman filtering
CN111983463B (en) Lithium ion battery residual capacity early warning diagnosis test method for electric automobile
Li et al. The open-circuit voltage characteristic and state of charge estimation for lithium-ion batteries based on an improved estimation algorithm
Yang et al. Advanced Battery Management System for Electric Vehicles
CN111562499B (en) Thermal management simulation method for lithium power battery of new energy automobile
CN116466250A (en) Dynamic working condition model error characteristic-based power battery health state estimation method
Zhu A state of charge estimation approach based on fractional order adaptive extended Kalman filter for lithium-ion batteries
CN115166566A (en) Method for identifying battery self-discharge rate abnormity on line
Bhattacharyya et al. Convolution neural network-based SOC estimation of Li-ion battery in EV applications
Wei et al. State of charge estimation for lithium-ion battery using Dynamic Neural Networks
Zheng et al. Capacity and state‐of‐charge (SOC) estimation for lithium‐ion cells based on charging time differences curves
Zhang et al. A novel method of battery state-of-health estimation for energy storage station based on inconsistency and dual time-scale extended Kalman filtering
Jiang Research on SOC estimation of residual power of lithium-ion batteries for electric vehicles based on extended Kalman filtering algorithm

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