Circular genetic operators based RNA genetic algorithm for modeling proton exchange membrane fuel cells

Inspired by the biological RNA, a circular genetic operators based RNA genetic algorithm (cRNA-GA) is proposed to estimate the model parameters of the proton exchange membrane fuel cell (PEMFC). To maintain the population diversity and avoid premature convergence, we design the novel genetic operator of the double-loop crossover operator. To allow the algorithm to jump out of local optima, the adaptive mutation probabilities are presented and the stem-loop mutation operator is adopted with the other mutation operators. The simulated annealing method is also incorporated into the cRNA-GA to improve local search ability. Performance tests conducted on some typical benchmark functions have witnessed the validity of cRNA-GA. The cRNA-GA is also applied to estimate the parameters of the PEMFC model and the satisfactory results have shown its effectiveness.