International Journal of Scientific Research and Engineering Development

Electric Vehicles (EVs) are gaining widespread adoption as a sustainable transportation solution; however, battery degradation remains a major concern affecting reliability, safety, and cost. Accurate degradation modeling and forecasting are essential for effective battery management and lifespan enhancement. This paper proposes an AI-driven battery degradation modeling framework that combines real-time data acquisition with intelligent prediction techniques. An IoT-based monitoring system using an ESP32 microcontroller is employed to collect key battery parameters, including voltage, current, and temperature. Battery State of Health (SoH) is estimated from the acquired data, and a Long Short-Term Memory (LSTM) neural network is used to learn temporal degradation patterns and forecast future battery health. The proposed approach enables early detection of abnormal degradation and improves prediction accuracy compared to conventional methods, supporting reliable and intelligent battery management in Electric Vehicles.

Mr.J.Shanmugasundaram, Dharshini N, Dharsini P, Kavipriya M, Srinithi S,"AI - Driven Battery Degradation Modeling and Forecasting in Electric Vehicles" International Journal of Scientific Research and Engineering Development, V9(2): Page(2099-2107) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.