Machine Learning

Electric Vehicle Battery Health Prediction Using Machine Learning

The Electric Vehicle Battery Health Prediction Using Machine Learning system is a comprehensive machine learning solution that classifies EV battery health status into four categories: Healthy, Moderate, Degraded, and Critical. This project is ideal for B.Tech, MCA, CSE, and engineering students as their final year project. It implements Logistic Regression and Random Forest with feature engineering, achieving 87.45% accuracy and 0.9328 ROC-AUC.

The system utilizes the Battery_RUL_Dataset containing comprehensive battery operational parameters including SOH, internal resistance, temperature, cycle count, voltage, current, and engineered features like Power_W, Thermal_Stress, and Aging_Impact. It provides a user-friendly web interface for data upload, exploratory data analysis, model training, and real-time battery health prediction, enabling proactive maintenance and improved vehicle safety.

• Multi-Model Battery Health Classification
• Random Forest (87.45% Accuracy)
• Logistic Regression (84.89% Accuracy)
• Feature Engineering (Power_W, Thermal_Stress)
• 4 Health Categories (Healthy → Critical)
• Interactive Visualizations
• Real-time Health Predictions
• Model Performance Comparison
• Feature Importance Analysis
• Flask Web Application