Artificial Intelligence-Based Machine Learning toward the Solution of Climate-Friendly Hydrogen Fuel Cell Electric Vehicles

Abstract

The rapid conversion of conventional powertrain technologies to climate-neutral new energy vehicles requires the ramping of electrification. The popularity of fuel cell electric vehicles with improved fuel economy has raised great attention for many years. Their use of green hydrogen is proposed to be a promising clean way to fill the energy gap and maintain a zero-emission ecosystem. Their complex architecture is influenced by complex multiphysics interactions, driving patterns, and environmental conditions that put a multitude of power requirements and boundary conditions around the vehicle subsystems, including the fuel cell system, the electric motor, battery, and the vehicle itself. Understanding its optimal fuel economy requires a systematic assessment of these interactions. Artificial intelligence-based machine learning methods have been emerging technologies showing great potential for accelerated data analysis and aid in a thorough understanding of complex systems. The present study investigates the fuel economy peaks during an NEDC in fuel cell electric vehicles. An innovative approach combining traditional multiphysics analyses, design of experiments, and machine learning is an effective blend for accelerated data supply and analysis that accurately predicts the fuel consumption peaks in fuel cell electric vehicles. The trained and validated models show very accurate results with less than 1% error.