Proton exchange membrane (PEM) fuel cell stack configuration using genetic algorithms

For stand alone power supply systems based on fuel cells to work efficiently, the fuel cell stack has to be configured so that it delivers the maximum power output at the load’s operating voltage. This paper discusses how genetic algorithms were applied to optimise a proton exchange membrane fuel cell stack design by searching for the best configuration in terms of number of cells and cell surface area. First, a mathematical simulation model of the fuel cell was developed. The model parameters were obtained by fitting the mathematical model to experimental data. A genetic algorithm code was then developed. The code is based on the fuel cell stack model as an evaluation measure for the fitness of the solutions generated. Results are presented confirming the effectiveness of using the genetic algorithm technique for fuel cell configuration.