PERFORMANCE EVALUATION OF HYBRID ENERGY MANAGEMENT SYSTEMS IN ELECTRIC VEHICLES USING AI-BASED PREDICTIVE CONTROL

Authors

  • Mr. Vimalkumar T Author
  • Mr. Dineshkumar M Author
  • Mr. Saravanan S Author
  • Dr. Sathik Basha A Author
  • Dr. Cyril Mathew O Author

DOI:

https://doi.org/10.64252/j0sn6585

Keywords:

Hybrid Energy Management, AI Predictive Control, PHEVs, Multi-Objective Optimization, DC-DC Converters, Supercapacitors.

Abstract

As global energy demand rises and environmental concerns intensify, the adoption of sustainable transportation solutions becomes imperative. This study explores the integration of an optimized hybrid energy management system (HEMS) in plug-in hybrid electric vehicles (PHEVs) utilizing a fuzzy logic-based predictive control strategy. The proposed system employs a supercapacitor-assisted battery storage unit to enhance energy efficiency and extend battery lifespan. Unlike conventional approaches, a multi-objective genetic algorithm (MOGA) is implemented to optimize energy distribution between the internal combustion engine (ICE) and the electric powertrain, improving overall performance. A bidirectional DC-DC converter is integrated to regulate energy flow dynamically, ensuring efficient power conversion and minimal switching losses. The study evaluates system performance through real-time hardware-in-the-loop (HIL) simulations, considering parameters such as state of charge (SOC), energy consumption, and powertrain efficiency. The results demonstrate that the AI-based HEMS significantly enhances fuel economy and reduces carbon emissions compared to traditional energy management techniques. The proposed model provides a robust framework for advancing intelligent hybrid powertrains, paving the way for next-generation electric mobility solutions.

Downloads

Download data is not yet available.

Downloads

Published

2025-03-14

How to Cite

PERFORMANCE EVALUATION OF HYBRID ENERGY MANAGEMENT SYSTEMS IN ELECTRIC VEHICLES USING AI-BASED PREDICTIVE CONTROL. (2025). International Journal of Environmental Sciences, 11(1s), 347-357. https://doi.org/10.64252/j0sn6585