An adaptive RNA genetic algorithm for modeling of proton exchange membrane fuel cells

The accurate mathematical model is the key issue to simulation and design of the fuel cell power systems. Aiming at estimating the proton exchange membrane fuel cell (PEMFC) model parameters, an adaptive RNA genetic algorithm (ARNA-GA) which is inspired by the mechanism of biological RNA is proposed. The ARNA-GA uses the RNA strands to represent the potential solutions and new genetic operators are designed for improving the global searching ability. In order to maintain the population diversity and avoid premature convergence, on the basis of the dissimilarity coefficient, the adaptive genetic strategy that allows the algorithm dynamically select crossover operation or mutation operation to execute is proposed. Numerical experiments have been conducted on some benchmark functions with high dimensions. The results indicate that ARNA-GA has better search capability and a higher quality of solutions. Finally, the proposed approach has been applied for the parameter estimation of PEMFC model and the satisfactory results are reached.