PHYSICS-INFORMED DEEP LEARNING FOR ENHANCED LITHIUM-ION BATTERY PERFORMANCE
Journal of Problems in Computer Science and Information Technologies · 2026
DOI: 10.26577/jpcsit53202610 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Problems in Computer Science and Information Technologies, 2026. Verfasst von Mohammadamin Rezaei und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Lithium-ion batteries are widely used in electric vehicles, portable electronics, and grid energy systems. The constant current–constant voltage (CC–CV) method shows clear limits at high state of charge when polarization increases, temperature rises, and charging time is extended. These effects become stronger in the high SOC region, where the charging rate decreases. Consequently, to address this challenge, in this study we presents a hybrid charging method that combines physics-informed deep learning with an auxiliary hardware circuit. The circuit is placed between the charger and the battery without changes to the charger structure. It enables real-time control of pulse frequency and duty cycle. A one-dimensional convolutional neural network is applied during short relaxation periods for SOC estimation. The proposed method reduces polarization and thermal stress and improves charging efficiency at high SOC. It also improves open-circuit voltage estimation accuracy. Experimental tests are conducted on lithium-ion cells under controlled temperature conditions. The results confirm improved performance in fast charging applications.
Zitieren
APA
Rezaei, M., Suleymen, B., Mosavi, A., Dineva, A., Felde, I., & Gubo, S. (2026). PHYSICS-INFORMED DEEP LEARNING FOR ENHANCED LITHIUM-ION BATTERY PERFORMANCE. Journal of Problems in Computer Science and Information Technologies. https://doi.org/10.26577/jpcsit53202610
Vancouver
Rezaei M, Suleymen B, Mosavi A, Dineva A, Felde I, Gubo S. PHYSICS-INFORMED DEEP LEARNING FOR ENHANCED LITHIUM-ION BATTERY PERFORMANCE. Journal of Problems in Computer Science and Information Technologies. 2026. doi:10.26577/jpcsit53202610
BibTeX
@article{Rezaei2026,
author = {Rezaei, Mohammadamin and Suleymen, Baqıtjan and Mosavi, Amir and Dineva, Adrienn and Felde, Imre and Gubo, Stefan},
title = {PHYSICS-INFORMED DEEP LEARNING FOR ENHANCED LITHIUM-ION BATTERY PERFORMANCE},
journal = {Journal of Problems in Computer Science and Information Technologies},
year = {2026},
doi = {10.26577/jpcsit53202610}
}
EUVIMED