Global Optimal Energy Management of Fuel Cell Vehicles with Considering Degradation Adaption

The research on energy management of fuel cell hybrid electric vehicles (FCHVs) mostly focuses on fuel economy. However, as fuel cells degrade and their performance deteriorate, the original energy management strategies become unsuitable. Therefore, this paper investigates the energy management strategies with considering degradation adaption. In this paper, the Pontryagin's Maximum Principle (PMP) was utilized for energy management. It was found that under moderate and severe degradation conditions, the PMP was unable to achieve real-time global optimization. Consequently, a fuel cell degradation adaptive PMP energy management strategy was proposed. The objective is to minimize hydrogen consumption under different states of health (SOH) of the fuel cell, while ensuring SOC of the battery remains within a reasonable range. Simulation results indicate that the degradation adaptive PMP control strategy can achieve the lowest hydrogen consumption and attains global optimization. Additionally, the Equivalent Consumption Minimization Strategy (ECMS) was implemented in real driving cycle with considering fuel cells degradation, and the Extreme Learning Machine (ELM) algorithm was applied to adapt the optimal co-state factor. By incorporating the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$A$</tex> factors predicted by the ELM algorithm, the hydrogen consumption of ECMS is significantly reduced, approaching the performance of PMP.