The project analyzes battery cycling data to predict degradation patterns and performance metrics using both deep learning (LSTM) and traditional machine learning (XGBoost) approaches. The implementation enables accurate estimation of battery health, which is crucial for battery management systems in various applications.

MCP-Based EV Digital Twin Agent with Dynamic Tool Discovery, Multi-Step Reasoning, Fleet Analytics, and Battery Intelligence.

SQL-based EV battery health and charging abuse analytics system

IoT-enabled lifecycle monitoring and cloud-based decision framework for lithium-ion battery recycling and material recovery optimization.

Machine learning–assisted EV powertrain energy prediction using ANN, SVR, and Gaussian Process Regression models.

High-performance 3D visualization engine for solar energy audit data. Implements Python-based surface mesh rendering for real-time voltage and battery health analysis.

Data-driven lithium-ion battery health prognostics and lifecycle performance modelling for EV systems.

AI-powered Battery Management System (BMS) featuring State of Health (SoH) and State of Charge (SoC) estimation, cell failure prediction, battery health analytics, and 282-cycle early warning using the NASA Li-ion Battery Dataset.