Aging prognosis model of proton exchange membrane fuel cell in different operating conditions.

The aging prognosis model of Proton Exchange Membrane Fuel Cell (PEMFC) can predict the aging state of PEMFC to develop an effective prognostic maintenance plan. This paper proposes an aging prognosis model of PEMFC in different operating conditions based on the Backpropagation (BP) neural network and evolutionary algorithm. The influence of PEMFC current, hydrogen pressure, temperature, and relative humidity on the aging of PEMFC can be considered by the proposed method. Firstly, the aging prognosis model of PEMFC is built by the BP neural network. Then, the evolutionary algorithm including Mind Evolutionary Algorithm (MEA), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) is used to optimize the parameters of the established aging prognosis model of PEMFC. Finally, the accuracy of the proposed aging prognosis model is validated by 3 PEMFC aging experiments in different operating conditions. The results show that MEA, GA, and PSO can greatly improve the accuracy of the aging prognosis model of PEMFC. The MEA improves the accuracy by 10 times, while the computing time increases by 0.085s. The proposed MEA-BP that has a very short computing time can be applied to online applications. Image 1 • Influence of operating conditions on the aging state of fuel cell is considered. • Proposed aging prognosis model is optimized by evolutionary algorithm. • Proposed method can be applied to online aging prognosis application. • Proposed method is validated by 3 fuel cell aging experiments. [ABSTRACT FROM AUTHOR]