Real-Time SOH Estimation for EV Li-Ion Batteries using ML & Digital Twin

In this research, a Digital Twin model is implemented alongside a machine learning model and monitoring technique for electric vehicles (EVs) battery health tracking in order to enable real-time tracking. Optimal performance and longevity of electric vehicles (EVs) hinges on proper management of their lithium-ion (Li-ion) batteries. The algorithm primarily applied in this research is the K-Nearest Neighbors (KNN) algorithm which leverages data from the battery’s cycling charge and discharge processes to guess its health status (SOH) and how long it will still be useful (RUL). Sensors measure real-time values like voltage and current as well as temperature, and these are further processed in the cloud via NodeMCU microcontroller with Wi-Fi. These transferred values are used to construct a Digital Twin technology model that accurately represents the battery model and guesses how the battery will act in different situations to increase KNN performance. Accurate monitoring enables proactive maintenance, sophisticated early issue detection, and improved efficiency and lifespan of the battery which enhances the overall functioning of the EVs. Analyzing dataset from the real world confirms the approach used helps predict monitoring health checks and planning for unforeseen events. The technology improves the operational efficiency of electric vehicles (EVs) increases power system performance, improves the overall energy consumption, drives thorough quality inspection, and significantly reduces maintenance costs which greatly. This work focuses on the application of machine learning and Digital Twin technologies for EV battery management, which enhances the sustainability and intelligence of electric vehicles.