An improved genetic-backpropagation neural network for state of charge estimation of lithium-ion batteries.

Wang, Shunli; Hai, Nan; Yang, Jiangnan; Fernandez, Carlos

Abstract

The state of charge estimation with high precision plays an important role in the usage of lithium-ion batteries in electronic vehicles. An improved genetic-backpropagation neural network (GA-BPNN) is proposed to predict the state of charge with high precision under complex working conditions. Specifically, the elite retention strategy is introduced to genetic operations to enhance the efficiency of the algorithm. Moreover, a further performance comparison of the improved GA-BPNN is achieved to prove its effectiveness. The experimental results show that the accuracy of the improved GA-BPNN is 7.92% and 6.71% under BBDST and DST working conditions, which are higher than that of traditional methods.

Citation

WANG, S., HAI, N., YANG, J. and FERNANDEZ, C. 2023. An improved genetic-backpropagation neural network for state of charge estimation of lithium-ion batteries. In Proceedings of the 3rd New energy and energy storage system control summit forum 2023 (NEESSC 2023), 26-28 September 2023, Mianyang, China. Piscataway: IEEE [online], pages 369-372. Available from: https://doi.org/10.1109/NEESSC59976.2023.10349297

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 3rd New energy and energy storage system control summit forum 2023 (NEESSC 2023)
• Start Date: Sep 26, 2023
• End Date: Sep 28, 2023
• Acceptance Date: Sep 20, 2023
• Online Publication Date: Dec 31, 2023
• Publication Date: Dec 31, 2023
• Deposit Date: Feb 1, 2024
• Publicly Available Date: Feb 2, 2024
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Pages: 369-372
• DOI: https://doi.org/10.1109/NEESSC59976.2023.10349297
• Keywords: Backpropagation; Genetic algorithm; Elite retention strategy; State of charge; Lithium-ion batteries
• Public URL: https://rgu-repository.worktribe.com/output/2225966