Recent Advances in An Efficient Hybrid Ladybug Beetle and Physics Informed Neural Network for Electric Vehicle Energy Management: A Systematic Review

Abstract

The rapid growth of electric vehicles has intensified the need for intelligent and adaptive energy management systems capable of optimizing complex energy flows within modern electrified powertrains. These systems must handle nonlinear dynamics, multi-objective constraints, and real-time decision-making to improve energy efficiency, battery longevity, and system reliability. This paper presents a systematic review of hybrid energy management frameworks combining the Ladybug Beetle Optimization (LBO) algorithm with Physics-Informed Neural Networks (PINNs). The LBO algorithm offers efficient global optimization through adaptive exploration–exploitation strategies, while PINNs embed physical laws governing battery dynamics, thermal behavior, and motor efficiency into the learning process. This hybrid approach enables accurate state estimation and optimal energy distribution, ensuring both data-driven adaptability and physical consistency in decision-making. Applications include battery electric vehicles, hybrid electric vehicles, and fuel cell vehicles operating under diverse driving conditions. Comparative studies demonstrate that the LBO-PINN framework outperforms conventional methods in energy efficiency, battery health preservation, and computational performance. Despite these advantages, challenges such as computational complexity, model scalability, and real-time deployment persist. This review highlights the potential of integrating metaheuristic optimization with physics-informed learning to develop intelligent, robust, and efficient energy management systems for next-generation electric vehicles.