Artificial Intelligence Techniques for An Efficient Hybrid Ladybug Beetle and Physics Informed Neural Network for Electric Vehicle Energy Management: Trends and Challenges

Abstract

The rapid advancement of artificial intelligence has significantly transformed electric vehicle energy management, enabling intelligent control of complex, nonlinear, and dynamically coupled subsystems. Efficient energy management systems are essential for optimizing battery performance, driving range, thermal stability, and overall vehicle efficiency, particularly under varying operating and environmental conditions. This paper presents a comprehensive review of artificial intelligence techniques for electric vehicle energy management, with a focus on hybrid frameworks integrating the Ladybug Beetle Optimization (LBO) algorithm and Physics-Informed Neural Networks (PINNs). The LBO algorithm provides effective global optimization through adaptive exploration–exploitation strategies, while PINNs embed physical laws governing electrochemical, thermal, and mechanical dynamics into the learning process. This integration ensures accurate, interpretable, and physically consistent predictions while optimizing energy distribution and control strategies.Applications include battery state estimation, hybrid energy storage management, regenerative braking optimization, thermal control, and grid-integrated charging systems. Comparative analysis demonstrates that hybrid optimization–learning frameworks outperform traditional rule-based, model-based, and standalone AI approaches in efficiency, adaptability, and robustness. However, challenges such as computational complexity, real-time implementation, and scalability remain. This review highlights the potential of combining metaheuristic optimization and physics-informed learning to develop intelligent, reliable, and efficient energy management systems for next-generation electric vehicles.