Lithium-ion Battery SOH Prediction Model Based on LSTM Optimized by Singer Chaotic Map Zebra Optimization Algorithm.

Saved in:

Bibliographic Details
Title:	Lithium-ion Battery SOH Prediction Model Based on LSTM Optimized by Singer Chaotic Map Zebra Optimization Algorithm.
Authors:	Yao, Cheng¹ 250849634@qq.com, Wang, Fei-Fei¹ 3151744145@qq.com, Li, Ling¹ liling2002@jlu.edu.cn, Zhang, Hai-Ying¹ 24652900@qq.com
Source:	Engineering Letters. Jul2026, Vol. 34 Issue 7, p2861-2876. 16p.
Subjects:	Long short-term memory, Metaheuristic algorithms, Prediction models, Lithium-ion batteries
Abstract:	To build an accurate model for battery state-of-health (SOH) prediction, a hybrid approach that combines a novel metaheuristic algorithm, the Zebra Optimization Algorithm (ZOA), with Long Short-Term Memory (LSTM) is proposed. The ZOA is employed to optimize the hyperparameters of the LSTM network, thereby enhancing its predictive performance. Furthermore, recognizing the limitations of the original ZOA in solving complex optimization problems, we introduce a chaotic map convergence factor, SC6, to improve the algorithm's convergence accuracy. Experimental results on the NASA datasets show that the proposed SC6-ZOA-LSTM model reduces the RMSE by 2.3% compared to the standard LSTM model. [ABSTRACT FROM AUTHOR]
	Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	To build an accurate model for battery state-of-health (SOH) prediction, a hybrid approach that combines a novel metaheuristic algorithm, the Zebra Optimization Algorithm (ZOA), with Long Short-Term Memory (LSTM) is proposed. The ZOA is employed to optimize the hyperparameters of the LSTM network, thereby enhancing its predictive performance. Furthermore, recognizing the limitations of the original ZOA in solving complex optimization problems, we introduce a chaotic map convergence factor, SC6, to improve the algorithm's convergence accuracy. Experimental results on the NASA datasets show that the proposed SC6-ZOA-LSTM model reduces the RMSE by 2.3% compared to the standard LSTM model. [ABSTRACT FROM AUTHOR]
ISSN:	1816093X