Particle Swarm Optimizations in Disturbance Observer Based Control of PEMFC Generation Systems

This paper proposed particle swarm optimizations of proportional-integral-derivative (PID) gains used in the disturbance observer based control of Proton Exchange Membrane Fuel Cell (PEMFC) generation system. The proposed approach is easy to implement and have good computational efficiency. In order to get satisfactory dynamic performance, a new performance index is introduced. Comparisons between the results obtained by Genetic Algorithm (GA) method and those by Particle Swarm Optimizations (PSO) method are made. Numerical results show that the gains obtained by PSO are more optimal than the GA method, and Particle swarm optimizations take the least time to achieve the same optimal gains.