Evolutionary algorithms in nonlinear model identification

Evolutionary algorithms are optimization methods which basic idea lies in biological evolution. They suit well for large and complex optimization problems. In this study, genetic algorithms and differential evolution are used for identifying the parameters of the nonlinear fuel cell model. Different versions of the algorithms are used to compare the methods and their available operators. The problem with the studied algorithms is the parameters that regulate the development of the population. In this report, some suitable methodology is proposed for defining appropriate tuning parameters for the used algorithms. The results show that the used methods suit well for nonlinear parameter identification but that differential evolution performs a bit better on average. The results also show that the studied identification problem has a lot of local minima that are very close to each other and thus the optimization problem is very challenging.