Application study on a fuzzy-controlled niche genetic algorithm

Based on the keystone of genetic algorithm (GA), improvements are made to simple genetic algorithm (SGA) in two aspects. The theory of fuzzy control and the niche technique are introduced into the GA, for the purpose of enhancing the population diversity and maintaining the best part of each generation. In order to avoid premature convergence and occurrence of minimal deceptive problems, which is caused by the niche technique, fuzzy control is presented for the controlling of the crossover probability P_c and mutation probability P_m. Above all, that is the new type of algorithm-fuzzy controlled niche genetic algorithm (FNGA). Through comparisons to FGA and NGA with the optimization of several functions, the result of the new algorithm shows its feasibilityand reliability.