AI-Enabled Battery Management System for Real-Time SOC and SOH Estimation in Electric Vehicles

Abstract

Battery Management System (BMS) plays a vital role in the safety, reliability and performance of Electric Vehicles (EVs). Accurate estimation of State of Charge (SOC) and State of Health (SOH) of Lithium-ion batteries remains a major challenge due to nonlinear battery behaviour, temperature variations and aging effects. Conventional estimation techniques such as Coulomb counting and model-based methods suffer from accumulated errors and reduced accuracy under dynamic operating conditions.

This research presents an experimental investigation of Artificial Intelligence (AI) embedded Battery Management System for precise SOC and SOH estimation. Real-time battery data including voltage, current, temperature and charge–discharge cycles were collected from Lithium-ion battery cells under different operating conditions. Machine learning algorithms including Artificial Neural Network (ANN) and Support Vector Machine (SVM) were implemented and trained using experimental datasets.

The proposed AI-based model was validated through laboratory experiments and performance comparison with conventional estimation techniques. Results demonstrate that the AI embedded BMS significantly improves estimation accuracy, reduces prediction error and enhances battery life prediction capability.

The developed approach contributes toward safer, smarter and more efficient Electric Vehicle battery systems and supports future intelligent energy storage applications.

Keywords: Battery Management System, State of Charge, State of Health, Electric Vehicle, Artificial Intelligence, Machine Learning, Lithium-ion Battery.