基于改进粒子群算法的质子交换膜燃料电池最优参数估计

Optimal Parameter Estimation of Proton Exchange Membrane Fuel Cell Based on Improved Particle Swarm Optimization Algorithm

摘要: 质子交换膜燃料电池的精确建模有利于对其性能进行更准确地预测。本文首先针对质子交换膜燃料电池进行数学建模，提出一种改进粒子群算法，通过对比改进粒子群算法、基本粒子群算法以及遗传算法对其参数估计，结果表明改进粒子群算法对质子交换膜建模参数估计的结果比其他两种算法更为准确。同时，运用该改进粒子群算法可以预测不同温度与气压下燃料电池的极化曲线。结果表明改进粒子群算法具有寻优能力强、寻优结果准确等特点。

Abstract: Precise modeling of proton exchange membrane fuel cell (PEMFC) is helpful to predict its perfor-mance more accurately. In this paper, the mathematical modeling of the proton exchange mem-brane fuel cell is firstly carried out, proposing an Improved Particle Swarm Optimization (IPSO) al-gorithm, by comparing the improved particle swarm optimization (IPSO) algorithm, the basic parti-cle swarm algorithm (PSO) and genetic algorithm (GA) for the parameter estimation. The results show that the improved particle swarm optimization (IPSO) algorithm to the results of the proton exchange membrane model parameter estimation algorithm is more accurate than the other two. The polarization curves of fuel cells at different temperatures and pressures can be predicted by using the improved particle swarm optimization algorithm (IPSO). The results show that the im-proved particle swarm optimization algorithm (IPSO) has a strong searching ability and accurate searching results.