Published Paper Details:

The rapid advancement of electric vehicles(EVs) has created a critical demand for intelligent and reliable battery management systems (BMS) to ensure safety, efficiency, and extended battery lifespan. Conventional BMS approaches are predominantly rule based and lack of predictive capabilities, resulting in suboptimal performance under dynamic operating conditions. This paper proposes an IoT driven predictive battery management framework that integrates real time sensing, cloud based communication, and artificial intelligence techniques for enhanced monitoring and control of EV batteries. The system continuously acquires key parameters including voltage (0 to 400 V), current (o to 200 A), temperature (-10 c to 60 C), and charge cycles using IoT enabled sensors and transmits the data to a cloud platform for analysis. Machine learning models, including support vector machine(SVM), Random Forest(RF) and Artificial Neural Network(ANN) are employed for accurate estimation of State of charge(SoC) and State of Health (SoH), as well as early fault detection. Experimental results demonstrate that the ANN model achieves a prediction accuracy of 96.2%. outperforming RF (94.8%) and SVM (91.3%. the proposed system reduces fault detection latency by approximately 28% and improves battery lifespan bt 18 to 22 % compared to conventional BMS techniques. Additionally, real time IoT monitoring enables continuous tracking with a data transmission interval of 1 to 2 seconds. The result indicate that the proposed framework significantly enhances battery reliability, operational efficiency, safety, making it a scalable solution for next generation EV applications.