Post-prognostics decision-making strategy for load allocation on a stochastically deteriorating multi-stack fuel cell system

Abstract

This work proposes a load allocation decision strategy based on deterioration prognostics information for multi-stack fuel cell systems. The fuel cell deterioration is characterized by the overall resistance value, as it carries the key aging information of a fuel cell. The fuel cell deterioration dynamics is then modeled as an increasing stochastic process whose trend is a function of the fuel cell output power. Combining system deterioration and fuel cell consumption, a multi-objective optimization (MOO) based decision-making strategy is proposed to manage the operation of a multi-stack fuel cell system. Based on this algorithm, the optimal operating power load is computed for each stack. Finally, the performance of the proposed approach is compared to the case without post-prognostics decision for a three-stack fuel cell system. The simulation results show that the proposed post-prognostics decision-making strategy can manage fuel cell system operating in real time by scheduling the optimal load allocation among stacks.