A hybrid data driven framework considering feature extraction for battery state of health estimation and remaining useful life prediction.

Chen, Yuan; Duan, Wenxian; He, Yigang; Wang, Shunli; Fernandez, Carlos

Abstract

Battery life prediction is of great significance to the safe operation, and the maintenance costs are reduced. This paper proposed a hybrid framework considering feature extraction to solve the problem of data backward, large sample data and uneven distribution of high-dimensional feature space, then to achieve a more accurate and stable prediction performance. By feature extraction, the measured data can be directly fed into the life prediction model. The hybrid framework combines variational mode decomposition, the multi-kernel support vector regression model and the improved sparrow search algorithm. Better parameters of the estimation model are obtained by introducing elite chaotic opposition-learning strategy and adaptive weights to optimize the sparrow search algorithm. The comparison is conducted by dataset from National Aeronautics and Space Administration, which shows that the proposed framework has a more accurate and stable prediction performance.

Citation

CHEN, Y., DUAN, W., HE, Y., WANG, S. and FERNANDEZ, C. 2024. A hybrid data driven framework considering feature extraction for battery state of health estimation and remaining useful life prediction. Green energy and intelligent transportation [online], 3(2), article number 100160. Available from: https://doi.org/10.1016/j.geits.2024.100160

• Journal Article Type: Article
• Acceptance Date: Sep 27, 2023
• Online Publication Date: Jan 10, 2024
• Publication Date: Apr 30, 2024
• Deposit Date: Jan 15, 2024
• Publicly Available Date: Jan 15, 2024
• Journal: Green energy and intelligent transportation
• Print ISSN: 2097-2512
• Electronic ISSN: 2773-1537
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 3
• Issue: 2
• Article Number: 100160
• DOI: https://doi.org/10.1016/j.geits.2024.100160
• Keywords: State of heath; Improved sparrow search algorithm; Remaining useful life; Variational mode decomposition; Multi-kernel support vector regression; Feature extraction
• Public URL: https://rgu-repository.worktribe.com/output/2204905