ML-Driven Estimation of Remaining Useful Life and Charging Time in Battery Management Systems for Electric Vehicles

The growing adoption of electric vehicles has increased the need for Battery Management Systems (BMS) that ensure safe operation, improve energy efficiency, and extend battery life. Key battery parameters such as voltage, current, temperature, charging time, and remaining useful life (RUL) must be continuously monitored to assess battery condition. This work presents a BMS framework that integrates machine learning with Internet of Things (IoT) technology. An ESP32 microcontroller is used to acquire battery data and transmit it to the ThingSpeak cloud platform for remote monitoring and analysis. A machine learning model is applied to predict the remaining useful life of the battery, and based on these predictions, suitable charging patterns are implemented. In addition, GPS functionality is used to provide information on nearby charging stations, improving user convenience during travel. A web-based HTML dashboard is designed to display battery data in real time. The proposed system helps handle variations in battery behavior and improves overall performance through cloud-based monitoring and analysis.