Life Predication Online Model Using Fine KKN Algorithm for Smart Batteries to Estimate the Accurate Degradation Phase Point in Hybrid Electric Vehicle Application

Abstract

This project uses Arduino Uno and Unity 3D to create a digital twin with IoT capabilities for real-time battery monitoring and lifespan prediction. The system monitors battery metrics including voltage, current, temperature, State of Charge (SoC), and State of Health (SoH) using sensors and an Arduino microcontroller. The obtained data is transmitted to a cloud-based IoT platform via a Wi-Fi module (ESP8266), allowing for real-time remote access. Unity 3D's digital twin simulates the behavior of a real battery, providing interactive display of important parameters and performance trends. Coulomb counting is used to compute SoC, whereas watching the loss of battery capacity over time determines SoH. Predictive analytics are used in the system to predict the battery's remaining useful life (RUL). When performance thresholds are met, alerts and notifications are sent via the IoT dashboard and Unity interface. The digital twin enhances monitoring and enables predictive maintenance, resulting in optimal utilization and preventing unexpected problems. This concept has several applications, including electric cars, renewable energy storage systems, and consumer electronics. This system offers real-time IoT connectivity, 3D visualization, and predictive modeling, making it a powerful tool for battery management, analytics, and health tracking