Optimizing Energy Management in Fuel Cell Hybrid Electric Vehicles for Efficient Power Distribution and Enhanced Performance Across Different Driving Conditions
Rising concerns over global warming, emissions, and fossil fuel depletion are driving the adoption of fuel cell hybrid electric vehicles (FHEVs). By integrating a fuel cell with an ultracapacitor, they enhance efficiency and performance, but nonlinear behavior under demanding conditions challenges voltage and speed control. This paper presents a novel control approach that synergistically combines the single‐candidate optimizer (SCO) and the Chien‐physics‐informed neural network (CPINN), referred to as the SCO‐CPINN method. The proposed framework aims to effectively regulate the DC bus voltage and improve the speed tracking accuracy by minimizing the steady‐state error and reducing the response time. A proportional derivative–proportional integral derivative second derivative (PDPID2) controller is designed to stabilize the DC bus voltage and ensure smooth vehicle speed tracking under the European extra‐urban driving cycle (EUDC). The SCO algorithm optimizes power consumption, while the CPINN model predicts vehicle range under varying driving conditions. Implemented in MATLAB, the proposed technique is benchmarked against existing techniques such as the contrastive self‐supervised graph neural network (CSGNN), multi‐objective particle swarm optimization (MOPSO), and soft actor‐critic algorithm (SACA). The SCO‐CPINN controller achieves the lowest steady‐state error of 0.3 V, outperforming CSGNN (3.2 V), MOPSO (4.5 V), and SACA (6.7 V). These results demonstrate the superior accuracy, faster response, and enhanced energy management capability of the proposed method, promoting more efficient and reliable control strategies for FHEVs.