Equivalent consumption minimization with prediction confidence regulation for hydrogen fuel cell heavy-duty trucks

Energy management for hydrogen fuel cell heavy-duty trucks must balance hydrogen consumption, terminal state of charge (SOC), and component degradation under rapidly changing driving conditions. Predictive equivalent consumption minimization strategies can anticipate future power demand, but inaccurate predictions may distort equivalence factor adaptation and compromise charge sustainability. This study proposes a confidence-aware equivalent consumption minimization strategy (CA-ECMS) that integrates driving condition recognition, short-horizon speed prediction, an adaptive SOC reference, and online fusion of equivalence factors associated with current and predicted conditions. Prediction confidence and SOC tracking error jointly regulate the contribution of future driving information, retaining anticipatory control while limiting the influence of unreliable predictions. A vehicle-level model incorporating component degradation and operating cost was developed for evaluation. The recognition model achieved 94.78% accuracy, and the prediction model achieved a root mean square error of 1.241 km h −1 . Controller performance was evaluated using five repeated China Heavy-Duty Commercial Vehicle Test Cycle for Tractor-Trailer (CHTC-TT) cycles, three repeated Heavy Heavy-Duty Diesel Truck (HHDDT) cycles, and module-by-module ablation tests. Under CHTC-TT, CA-ECMS reduced operating cost, hydrogen cost, and fuel cell degradation cost by 9.31%, 6.14%, and 59.88%, respectively, relative to adaptive ECMS, while reducing terminal SOC error from 3.58% to 0.08%. Under HHDDT, CA-ECMS limited terminal SOC error to 0.40%, compared with 10.50%, 30.00%, and 25.90% for rule-based control, adaptive ECMS, and fuzzy dynamic switching, respectively. Ablation results confirmed the complementary roles of confidence regulation, the adaptive SOC reference, and SOC feedback. These results demonstrate that reliability-aware use of predicted driving information can improve operating cost and charge sustainability within an interpretable ECMS framework.