Article: Remaining useful life prediction for lithium-ion battery using a data-driven method Journal: International Journal of Wireless and Mobile Computing (IJWMC) 2022 Vol.23 No.3/4 pp.239 - 249 Abstract: Accurate prediction of the remaining useful life (RUL) of Li-ion batteries is one of the key technologies in the Battery Management System (BMS). To boost the prediction accuracy of Li-ion battery RUL, a data-driven approach is developed, through the combination of Long and Short-Term Memory (LSTM) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN). First and foremost, the battery capacity extracted from the National Aeronautics and Space Administration (NASA) battery data set is used as original data and the CEEMDAN is utilised to deal with original data into components of dissimilar frequencies. Then, the LSTM model is used to predict components of different frequencies. Finally, the CEEMDAN-LSTM prediction result is efficaciously integrated to acquire the final prediction of the Li-ion battery RUL. The results show that the proposed method is superior for Li-ion battery RUL prediction. Inderscience Publishers - linking academia, business and industry through research

Title: Remaining useful life prediction for lithium-ion battery using a data-driven method

Authors: Zhiyang Jin; Chao Fang; Jingjin Wu; Jinsong Li; Wenqian Zeng; Xiaokang Zhao

Addresses: Department of Electrical Engineering, University of Hainan, Haikou, Hainan, China ' Department of Electrical Engineering, University of Hainan, Haikou, Hainan, China ' Department of Electrical Engineering, University of Hainan, Haikou, Hainan, China ' Department of Electrical Engineering, University of Hainan, Haikou, Hainan, China ' Hainan Association for Artificial Intelligence, Haikou, Hainan, China ' Hainan Curium Technology Co., Ltd., Haikou, Hainan, China

Abstract: Accurate prediction of the remaining useful life (RUL) of Li-ion batteries is one of the key technologies in the Battery Management System (BMS). To boost the prediction accuracy of Li-ion battery RUL, a data-driven approach is developed, through the combination of Long and Short-Term Memory (LSTM) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN). First and foremost, the battery capacity extracted from the National Aeronautics and Space Administration (NASA) battery data set is used as original data and the CEEMDAN is utilised to deal with original data into components of dissimilar frequencies. Then, the LSTM model is used to predict components of different frequencies. Finally, the CEEMDAN-LSTM prediction result is efficaciously integrated to acquire the final prediction of the Li-ion battery RUL. The results show that the proposed method is superior for Li-ion battery RUL prediction.

Keywords: Li-ion battery; remaining useful life long and short-term memory; CEEMDAN; complete ensemble empirical mode decomposition with adaptive noise.

DOI: 10.1504/IJWMC.2022.127586

International Journal of Wireless and Mobile Computing, 2022 Vol.23 No.3/4, pp.239 - 249

Received: 17 Sep 2021
Accepted: 17 Mar 2022
Published online: 12 Dec 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Remaining useful life prediction for lithium-ion battery using a data-driven method

Keep up-to-date