Parameter Identification for PEM Fuel-Cell Mechanism Model Based on Effective Informed Adaptive Particle Swarm Optimization

TLDR

The paper proposes an effective informed adaptive PSO algorithm to improve PSO’s balance between global and local search and applies it to parameter identification of a proton‑exchange‑membrane fuel‑cell mechanism model. An electrochemical PEMFC mechanism model is developed and a parameter‑identification technique based on the EIA‑PSO algorithm is applied, with validation through comparison of experimental and simulation data. EIA‑PSO achieves higher‑precision fitting of the PEMFC model to experimental data, even with measurement noise, proving it an effective parameter‑identification technique.

Abstract

In order to improve the inherent drawbacks of particle swarm optimization (PSO), an effective informed adaptive PSO (EIA-PSO) algorithm that has better equilibrium characteristic between global search and local search is proposed. In this paper, an electrochemical-based proton exchange membrane fuel cell (PEMFC) mechanism model suitable for engineering optimization is developed, and a parameter-identification-technique-based EIA-PSO for this mechanism model is presented. In order to verify the validity of the advanced method, comparisons between experimental data and simulation data are carried out. The results demonstrate that EIA-PSO can make the mechanism model with identified parameters fit the experimental data with higher precision even in the presence of measurement noise. Therefore, EIA-PSO is an optional effective technique for identifying the parameters of the PEMFC mechanism model.