Call for Papers 2024 | Email: editor@ijace.org | ISSN: 2347-7687 | Google Scholar | WikiData | Impact Factor: 4.565

Abstract:


Due to complex usage patterns, variable environmental factors, and aging effects, EV batteries have a challenge with fault diagnostics and prognostics. This review covers recent advances in using DL methods for fault diagnosis and battery lifespan prediction, particularly for lithium-ion batteries in EVs. We discuss the researches in influential journals and databases systematically, including CNN, RNN, and hybrid models, with regard to their applicability, efficacy, and limitation. The empirical results indicate that DL-based methods can significantly improve the prediction accuracy and fault detection abilities but are accompanied by some other challenges related to data availability, model complexity, and interpretability. Key Trends and Open Research Issues Identifying Some Gaps that This Paper Hopes Future Work Should Address in Its Direction Regarding Fault Diagnostics and Prognostics of EV Batteries.

Keywords: Battery diagnostics, Fault detection, Prognostics prediction, Deep learning, Electric vehicles, Battery lifespan, Health monitoring, Lithium batteries, Model training, Data analysis.

Citation:


Dr. Ankit Gupta (2024), Fault Diagnostics and Prognostics in Electric Vehicle Batteries Using Deep Learning: A Systematic Review. International Journal of Arts, Commerce & Education (IJACE), Volume: 01 Issue: 01, Pages: 18-21. https://www.ijace.org/papers/v1/i1/IJACEV1I10002.pdf