A Health-Aware Fuzzy Logic Controller Optimized by NSGA-II for Real-Time Energy Management of Fuel Cell Electric Commercial Vehicles

This study introduces a health-aware fuzzy logic (FL) energy management strategy (EMS) for fuel cell electric commercial vehicles (FCECVs) that aimed to improve energy efficiency and extending fuel cell system (FCS) lifespan. The FL-based EMS was developed using vehicle power demand and battery state of charge (SOC) as inputs, with the FCS power change rate as the output, aiming to mitigate degradation induced by abrupt load transitions. A multi-objective optimization framework was established to optimize the fuzzy logic controller (FLC) parameters, achieving a balanced trade-off between fuel economy and FCS longevity. The non-dominated sorting genetic algorithm-II (NSGA-II) was utilized for optimization across various driving cycles, with average Pareto-optimal solutions employed for real-time application. Performance evaluation under standard and stochastic driving cycles benchmarked the proposed strategy against dynamic programming (DP), charge-depletion charge-sustaining (CD-CS), conventional FL strategies, and a non-optimized baseline. Results demonstrated an approximately 38% reduction in hydrogen consumption (HC) relative to CD-CS and over 75% improvement in degradation mitigation, with performance superior to that of DP. Although the strategy exhibits an average 17.39% increase in computation time compared to CD-CS, the average single-step computation time is only 2.1 ms, confirming its practical feasibility for real-time applications.