Parameter optimization for a PEMFC model with a hybrid genetic algorithm

Abstract

SUMMARYMany steady-state models of polymer electrolyte membrane fuel cells (PEMFC) have been developed and published in recent years. However, models which are easy to be solved and feasible for engineering applications are few. Moreover, rarely the methods for parameter optimization of PEMFC stack models were discussed. In this paper, an electrochemical-based fuel cell model suitable for engineering optimization is presented. Parameters of this PEMFC model are determined and optimized by means of a niche hybrid genetic algorithm (HGA) by using stack output-voltage, stack demand current, anode pressure and cathode pressure as input-output data. This genetic algorithm is a modified method for global optimization. It provides a new architecture of hybrid algorithms, which organically merges the niche techniques and Nelder-Mead's simplex method into genetic algorithms (GAs). Calculation results of this PEMFC model with optimized parameters agreed with experimental data well and show that this model can be used for the study on the PEMFC steady-state performance, is broader in applicability than the earlier steady-state models. HGA is an effective and reliable technique for optimizing the model parameters of PEMFC stack.

Genetic Algorithms in Model Structure Identification for Fuel Cell Polarization Curve

“…The partial pressures and the oxygen concentration can be calculated as a function of the anode and cathode inlet pressures (pa, pc), temperature, relative humidity of vapor in the anode and cathode (RHa, RHc), saturation pressure of the water vapor (p sat H2O), effective electrode area (A), and cell current. The equations are as follows [4] …”

“…The polarization curve data is originated from [4,20] comprising four different fuel cells. The numerical data is extracted from the plotted polarization curves by careful visual inspection.…”

“…[4,5,6,7,8]. In this study, a novel approach to apply the evolutionary optimization tools in model structure identification of the FC polarization curve model is taken.…”

Thermal and Electrical Parameter Identification of a Proton Exchange Membrane Fuel Cell Using Genetic Algorithm

“…The coefficients are identified using an optimization function which minimizes the error between simulated and real signals. In [6] the current demand is used as input to generate de polarization curve. The identification of the coefficients was performed with an OA called hybrid genetic algorithm (HGA) that avoids the premature convergence of the simple genetic algorithm (SGA).…”

Identification of PEM fuel cells based on support vector regression and orthonormal bases

“…In [4] the parameters of the fuel cell model are determined and optimized through a hybrid genetic algorithm (HGA) by using stack output-voltage and current, and anode and cathode pressure as input-output data. In [5] a Particle Swarm Optimization (PSO)-based identification technique is applied to estimate the parameters of fuel cells in terms of the voltage-current characteristics.…”