Abstract :

The Utilization Of Fuel Cells (FC) In Automotive Technology Has Grown Significantly, Particularly In Fuel Cell Hybrid Electric Vehicles (FCHEVs), Which Integrate Fuel Cells, Batteries, And Ultracapacitors (UCs). Through Power Electronic Converters, These Hybrid Systems Overcome The Individual Limitations Of Each Energy Source. However, The Overall Performance Of FCHEVs Depends Heavily On Converter Control Efficiency And The Technical Efficiency Of The Energy Sources. Effective Energy Management Systems (EMSs) Are Essential, As Poor EMS Design Can Result In Reduced Efficiency And Accelerated Degradation Of Fuel Cells And Batteries. This Research Proposes An Intelligent Machine Learning (ML) Framework To Predict Battery Performance And Charging Behavior In Hybrid Electric Vehicle Systems Using Operational Battery Parameters. Key Features Analyzed Include State Of Charge (SoC), Voltage, Current, Battery Temperature, Ambient Temperature, Degradation Rate, And Charging Cycles. The Framework Performs Two Classification Tasks (2CA) And Two Regression Tasks (2RT). Implemented Models Include Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XGB), Adaptive Boosting (AdaBoost), Bidirectional Long Short-Term Memory (Bi-LSTM) With Attention Mechanism, And Rule-based Models Such As Optimal Decision Rule List Classifier (ODRLC) And Optimal Decision Rule List Regressor (ODRLR). These Models Are Integrated Into The Proposed Attention Rule Framework (ARF) To Enhance Prediction Accuracy And Interpretability. Classification Tasks Predict Battery Type And Optimal Charging Duration Class, While Regression Tasks Estimate Efficiency And Charging Duration Values. Experimental Results, Evaluated Using Accuracy, Precision, Recall, F1-score, MAE, RMSE, And R²-score, Demonstrate That ARF Outperforms Existing Models. Visualization Tools Further Validate Its Effectiveness, Offering A Reliable Solution For Intelligent Energy Management In Electric Vehicles.

Published:

24-4-1-2026

Issue:

Vol. 26 No. 4-1 (2026)

Page Nos:

826-834

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite