This project focuses on predictive energy performance modelling for electric vehicle powertrain systems using machine learning and data-driven analytical approaches.
The research integrates experimental operational datasets with predictive machine learning frameworks to estimate power output, system efficiency, and energy performance behaviour under varying operating conditions.
Advanced regression and predictive modelling techniques including Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Gaussian Process Regression (GPR) were developed and evaluated to improve prediction accuracy and operational performance analysis.
This repository presents the project architecture, modelling workflow, and analytical methodology developed during academic research.
- Machine learning–based EV powertrain energy prediction
- ANN, SVR, and Gaussian Process Regression modelling
- Experimental dataset integration and preprocessing
- Predictive efficiency and power output analysis
- Comparative model evaluation and validation workflow
- MATLAB
- Artificial Neural Networks (ANN)
- Support Vector Regression (SVR)
- Gaussian Process Regression (GPR)
- Experimental EV Operational Datasets
- Data Processing & Predictive Analytics
This project demonstrates how machine learning and predictive analytics can support intelligent energy performance estimation, operational efficiency evaluation, and data-driven decision-making in electric vehicle powertrain systems.
The implementation used in this project was developed as part of academic research and related publications.
To maintain research integrity and comply with institutional and publication-related guidelines, the full source code and modelling configurations are not publicly released.
This repository is intended to present the project concept, predictive workflow, and technical methodology.
Code access may be shared upon request for academic collaboration or research discussion.