Physics-informed and Data-driven Intelligent Control for Next-generation Electric Vehicles: Powertrain, Chassis, and Energy Management

Electrification and intelligence are accelerating the transformation of modern vehicles, creating new challenges for vehicle modeling, optimization, and control. Traditional physics-based approaches provide strong interpretability and physical consistency but often suffer from limited adaptability under complex and uncertain driving conditions. Meanwhile, purely data-driven methods demonstrate powerful learning capabilities but may lack physical constraints and generalization ability. Recently, physics-informed modeling and hybrid intelligent control approaches have emerged as promising solutions by integrating physical knowledge with advanced artificial intelligence techniques. This Research Topic aims to explore innovative methodologies combining physics-based modeling, data-driven learning, and intelligent optimization for next-generation electric vehicles, including powertrain control, chassis dynamics control, and energy management systems.The goal of this Research Topic is to provide a comprehensive platform for researchers to present recent advances in physics-informed and data-driven approaches for electrified vehicle systems. The Research Topic focuses on developing new theories, models, and control strategies that enhance vehicle efficiency, safety, intelligence, and adaptability. Specifically, this Research Topic aims to address several key challenges, including accurate modeling of highly nonlinear vehicle systems, real-time optimization under uncertain driving scenarios, coordinated control among multiple vehicle subsystems, and the integration of physical knowledge with artificial intelligence algorithms. Contributions are expected to promote the development of advanced methodologies, such as physics-informed neural networks, hybrid modeling, reinforcement learning, predictive control, digital twins, and intelligent optimization algorithms. These approaches will facilitate the transition toward highly efficient, reliable, and autonomous electric vehicles.This Research Topic welcomes original research articles, review articles, and methodological studies related to physics-informed modeling and intelligent control of electrified vehicles. Topics of interest include, but are not limited to: (1) Physics-informed modeling and control of electric vehicle powertrains, including motors, multi-speed transmissions, and hybrid power systems; (2) Intelligent energy management strategies based on model predictive control, reinforcement learning, and optimization algorithms; (3) Vehicle dynamics and chassis coordinated control, including stability control, fault-tolerant control, and integrated vehicle-road interaction; (4) Data-driven modeling, digital twins, and AI-assisted vehicle system optimization; (5) Experimental validation, hardware-in-the-loop testing, and real-world applications of intelligent vehicle control technologies. Topic editors: Ziwang Lu, Hao Chen Source: https://www.frontiersin.org/research-topics/86013/physics-informed-and-data-driven-intelligent-control-for-next-generation-electric-vehicles-powertrain-chassis-and-energy-management