Genetic Algorithm Based Back-Propagation Neural Network Approach for Fault Diagnosis in Lithium-ion Battery System

Zuchang Gao; Cheng Siong Chin; Wai Lok Woo; Junbo Jia; Wei Da Toh

doi:10.1109/PESA.2015.7398911

Genetic Algorithm Based Back-Propagation Neural Network Approach for Fault Diagnosis in Lithium-ion Battery System

Zuchang Gao, Cheng Siong Chin, Wai Lok Woo, Junbo Jia, Wei Da Toh

Computer Information Sciences Department

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

25 Citations (Scopus)

Abstract

Safety is important in a lithium-ion battery power system. It is necessary to adopt an effective fault diagnosis method to keep the battery power system in the good working status. In this paper, Genetic Algorithm (GA) is integrated to build a single hidden layer Back-Propagation Neural Network (BPNN) for fault diagnosis. In the process of training the neural network, GA is used to initialize and optimize the connection weights and thresholds of the neural network. Several faults are detected by the proposed GA optimized fault diagnosis scheme. Simulation results show that the proposed fault diagnosis scheme provides satisfactory results.

Original language	English
Title of host publication	2015 6th International Conference on Power Electronics Systems and Applications (PESA)
Subtitle of host publication	Electric Transportation - Automotive, Vessel and Aircraft, PESA 2015
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	9781509000623
DOIs	https://doi.org/10.1109/PESA.2015.7398911 https://doi.org/10.1109/PESA.2015.7398911
Publication status	Published - 4 Feb 2016
Event	6th International Conference on Power Electronics Systems and Applications, PESA 2015 - Hong Kong, Hong Kong Duration: 15 Dec 2015 → 17 Dec 2015

Conference

Conference	6th International Conference on Power Electronics Systems and Applications, PESA 2015
Country/Territory	Hong Kong
City	Hong Kong
Period	15/12/15 → 17/12/15

Keywords

Back-propagation neural network
fault diagnosis
genetic algorithm
lithium-ion battery

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

Cite this

Gao, Z., Chin, C. S., Woo, W. L., Jia, J., & Toh, W. D. (2016). Genetic Algorithm Based Back-Propagation Neural Network Approach for Fault Diagnosis in Lithium-ion Battery System. In 2015 6th International Conference on Power Electronics Systems and Applications (PESA): Electric Transportation - Automotive, Vessel and Aircraft, PESA 2015 IEEE. https://doi.org/10.1109/PESA.2015.7398911, https://doi.org/10.1109/PESA.2015.7398911

@inproceedings{452df8c4fedd4af8844999693d8ac0d5,

title = "Genetic Algorithm Based Back-Propagation Neural Network Approach for Fault Diagnosis in Lithium-ion Battery System",

abstract = "Safety is important in a lithium-ion battery power system. It is necessary to adopt an effective fault diagnosis method to keep the battery power system in the good working status. In this paper, Genetic Algorithm (GA) is integrated to build a single hidden layer Back-Propagation Neural Network (BPNN) for fault diagnosis. In the process of training the neural network, GA is used to initialize and optimize the connection weights and thresholds of the neural network. Several faults are detected by the proposed GA optimized fault diagnosis scheme. Simulation results show that the proposed fault diagnosis scheme provides satisfactory results.",

keywords = "Back-propagation neural network, fault diagnosis, genetic algorithm, lithium-ion battery",

author = "Zuchang Gao and Chin, {Cheng Siong} and Woo, {Wai Lok} and Junbo Jia and Toh, {Wei Da}",

year = "2016",

month = feb,

day = "4",

doi = "10.1109/PESA.2015.7398911",

language = "English",

booktitle = "2015 6th International Conference on Power Electronics Systems and Applications (PESA)",

publisher = "IEEE",

address = "United States",

note = "6th International Conference on Power Electronics Systems and Applications, PESA 2015 ; Conference date: 15-12-2015 Through 17-12-2015",

}

Gao, Z, Chin, CS, Woo, WL, Jia, J & Toh, WD 2016, Genetic Algorithm Based Back-Propagation Neural Network Approach for Fault Diagnosis in Lithium-ion Battery System. in 2015 6th International Conference on Power Electronics Systems and Applications (PESA): Electric Transportation - Automotive, Vessel and Aircraft, PESA 2015. IEEE, 6th International Conference on Power Electronics Systems and Applications, PESA 2015, Hong Kong, Hong Kong, 15/12/15. https://doi.org/10.1109/PESA.2015.7398911, https://doi.org/10.1109/PESA.2015.7398911

Genetic Algorithm Based Back-Propagation Neural Network Approach for Fault Diagnosis in Lithium-ion Battery System. / Gao, Zuchang; Chin, Cheng Siong; Woo, Wai Lok et al.
2015 6th International Conference on Power Electronics Systems and Applications (PESA): Electric Transportation - Automotive, Vessel and Aircraft, PESA 2015. IEEE, 2016.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Genetic Algorithm Based Back-Propagation Neural Network Approach for Fault Diagnosis in Lithium-ion Battery System

AU - Gao, Zuchang

AU - Chin, Cheng Siong

AU - Woo, Wai Lok

AU - Jia, Junbo

AU - Toh, Wei Da

PY - 2016/2/4

Y1 - 2016/2/4

N2 - Safety is important in a lithium-ion battery power system. It is necessary to adopt an effective fault diagnosis method to keep the battery power system in the good working status. In this paper, Genetic Algorithm (GA) is integrated to build a single hidden layer Back-Propagation Neural Network (BPNN) for fault diagnosis. In the process of training the neural network, GA is used to initialize and optimize the connection weights and thresholds of the neural network. Several faults are detected by the proposed GA optimized fault diagnosis scheme. Simulation results show that the proposed fault diagnosis scheme provides satisfactory results.

AB - Safety is important in a lithium-ion battery power system. It is necessary to adopt an effective fault diagnosis method to keep the battery power system in the good working status. In this paper, Genetic Algorithm (GA) is integrated to build a single hidden layer Back-Propagation Neural Network (BPNN) for fault diagnosis. In the process of training the neural network, GA is used to initialize and optimize the connection weights and thresholds of the neural network. Several faults are detected by the proposed GA optimized fault diagnosis scheme. Simulation results show that the proposed fault diagnosis scheme provides satisfactory results.

KW - Back-propagation neural network

KW - fault diagnosis

KW - genetic algorithm

KW - lithium-ion battery

U2 - 10.1109/PESA.2015.7398911

DO - 10.1109/PESA.2015.7398911

M3 - Conference contribution

BT - 2015 6th International Conference on Power Electronics Systems and Applications (PESA)

PB - IEEE

T2 - 6th International Conference on Power Electronics Systems and Applications, PESA 2015

Y2 - 15 December 2015 through 17 December 2015

ER -

Gao Z, Chin CS, Woo WL, Jia J, Toh WD. Genetic Algorithm Based Back-Propagation Neural Network Approach for Fault Diagnosis in Lithium-ion Battery System. In 2015 6th International Conference on Power Electronics Systems and Applications (PESA): Electric Transportation - Automotive, Vessel and Aircraft, PESA 2015. IEEE. 2016 doi: 10.1109/PESA.2015.7398911, 10.1109/PESA.2015.7398911

Genetic Algorithm Based Back-Propagation Neural Network Approach for Fault Diagnosis in Lithium-ion Battery System

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this