Genetic Operators Significance Assessment in Simple Genetic Algorithm

Abstract

Genetic algorithms, proved as successful alternative to conventional optimization methods for the purposes of parameter identification of fermentation process models, search for a global optimal solution via three main genetic operators, namely selection, crossover, and mutation. In order to determine their importance for finding the solution, a procedure for significance assessment of genetic algorithms operators has been developed. The workability of newly elaborated procedure has been tested when simple genetic algorithm is applied to parameter identification of S. cerevisiae fed-batch cultivation. According to obtained results the most significant genetic operator has been distinguished and its influence for finding the global optimal solution has been evaluated.