Optimal Parameter Estimation of Proton Exchange Membrane Fuel Cell Models with Hybrid Salp Swarm Algorithm

Abstract

Parameter estimation is of paramount importance for the modeling, design and operation of proton exchange membrane fuel cell (PEMFC) systems. However, the inherent nonlinearity and complex dynamics of PEMFC systems present significant challenges for conventional optimization techniques in achieving accurate and efficient parameter optimization. To address these issues, we propose a novel optimization approach called the Hybrid Salp Swarm Algorithm (HSSA). In the HSSA, an orthogonal learning strategy is employed to help the leader salp avoid getting stuck in local optima and improve its ability to explore new and promising areas. Moreover, a dynamic control parameter mechanism is incorporated into the position update equation for follower salps, which aims to maintain an appropriate balance between exploration and exploitation capabilities. Additionally, the Levy flight strategy is implemented to increase population diversity and enhance the exploration efficiency of the SSA. To assess the feasibility and effectiveness of the HSSA, it was first tested on six benchmark functions and then applied to estimate the parameters of four PEMFC models: 250 W, NedStack PS6, SR-12 500 W, and BCS 500 W. The simulation results reveal that the proposed HSSA exhibits superior performance compared to other algorithms in terms of accuracy, stability, and convergence speed, suggesting its promising potential for future application in PEMFC modeling.

Keywords: Proton Exchange Membrane Fuel Cell, Parameter Estimation, hybrid salp swam algorithm, Orthogonal learning