State of health prediction of lithium-ion batteries based on incremental capacity analysis and adaptive genetic algorithm optimized Elman neural network model

Zimo Liu, Huirong Wang, Xun Zhou, Haoyuan Chen, Haolei Duan, Kunfeng Liang, Bin Chen, Yong Cao, Weimin Wang, Dapeng Yang and Lusheng Song

Energy, 2025, vol. 335, issue C

Abstract: Accurate prediction of the State of Health (SOH) for lithium-ion batteries is essential for ensuring timely battery replacements and mitigating safety risks related to capacity degradation. This paper introduces the Adaptive Genetic Algorithm-optimized Elman neural network (AGA-Elman) for SOH prediction. The approach starts by deriving incremental capacity (IC) curves from battery current, voltage, capacity, and time data. A subset of IC data is selected based on battery aging and correlation analysis, then used to train an Elman neural network, which captures temporal information effectively. The Adaptive Genetic Algorithm (AGA) optimizes the network's weights and thresholds, enhancing convergence accuracy and speed compared to traditional genetic algorithms. Validation with real battery data shows that the AGA-Elman model achieves prediction errors below 2.43 % using only 50 % of the data for training. This model significantly outperforms conventional genetic algorithm-optimized Elman networks, demonstrating its practical suitability for accurate battery SOH prediction and contributing to safer and more efficient energy storage solutions.

Keywords: Lithium-ion batteries; Battery state of health; Incremental capacity; Elman neural network; Adaptive genetic algorithm (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225035972
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:335:y:2025:i:c:s0360544225035972

DOI: 10.1016/j.energy.2025.137955

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().