State-of-Charge Estimation of Medium- and High-Voltage Batteries Using LSTM Neural Networks Optimized with Genetic Algorithms

• Published in: Sensors (Basel, Switzerland) Vol. 25; no. 15; p. 4632
• Main Authors: Carrera, Romel, Quiroz, Leonidas, Guevara, Cesar, Acosta-Vargas, Patricia
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 26.07.2025; MDPI
• Subjects: Accuracy; Batteries; Deep learning; Electric vehicles; Embedded systems; Genetic algorithms; Lithium; Machine learning; monitoring system; Neural networks; Optimization; Parameter identification; SOC estimation; Support vector machines; vehicle range; SOC estimation; genetic algorithms; monitoring system; vehicle range
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s25154632

This study presents a hybrid method for state-of-charge (SOC) estimation of lithium-ion batteries using LSTM neural networks optimized with genetic algorithms (GA), combined with Coulomb Counting (CC) as an initial estimator. Experimental tests were conducted using medium-voltage (48–72 V) lithium-ion battery packs under standardized driving cycles (NEDC and WLTP). The proposed method enhances prediction accuracy under dynamic conditions by recalibrating the LSTM output with CC estimates through a dynamic fusion parameter α. The novelty of this approach lies in the integration of machine learning and physical modeling, optimized via evolutionary algorithms, to address limitations of standalone methods in real-time applications. The hybrid model achieved a mean absolute error (MAE) of 0.181%, outperforming conventional estimation strategies. These findings contribute to more reliable battery management systems (BMS) for electric vehicles and second-life applications.