Multi-Feature Coordinated Adaptive ECMS with Fuzzy Logic for Low-Carbon Sustainable Fuel Cell Hybrid Electric Commercial Vehicles

This paper introduces a multi-feature coordinated adaptive equivalent consumption minimization strategy (MFCA-ECMS) using fuzzy logic control (FLC) to enhance hydrogen efficiency in fuel cell hybrid electric commercial vehicles (FCHECVs) and extend the lifespan of the fuel cell system (FCS), contributing to sustainable, low-carbon transport. First, a baseline ECMS model is established for the FCHECV, whilst the optimal equivalent factor (EF) is determined using a multi-island genetic algorithm (MIGA) based on representative driving cycles. Second, an adaptive EF framework is developed to overcome the inherent limitation of conventional ECMS—its reliance on a fixed EF—by dynamically integrating three operational features: variation in the battery’s state of charge (SOC), the rate of change in the FCS’s output power, and fluctuations in vehicle power demand. Third, feature-specific adaptive weights are assigned and updated in real time using a fuzzy inference system to regulate the EF online, incorporating multiple features. Simulations are conducted under different initial SOC levels (90% and 45%) across different driving cycles. The results demonstrate that the MFCA-ECMS consistently reduces hydrogen consumption (HC). Compared to the charge-depleting and charge-sustaining (CD-CS) strategy, it achieves HC reductions of 17.98% on the stochastic driving cycle (Random-C) and 18.73% on the urban dynamometer driving schedule (UDDS), outperforming both CD-CS and conventional ECMS in all tested scenarios. Furthermore, the MFCA-ECMS actively suppresses FCS power fluctuations. Regardless of the initial SOC, the proportion of power change rates within the reasonable range exceeds 97%, thereby contributing to extending the FCS lifespan. This reduces emissions and operating costs, enabling sustainable hydrogen-powered commercial vehicle deployment.