Optimization of Fuzzy Controller Based on Three Population Genetic Algorithm

Using the idea of species migrating mechanism for reference, this article improved the three population genetic algorithm, the population was divided into three sub-populations: low population, sub-optimal population, senior population. The fitness and the encoding digits of individual gene chain increased gradually, therefore, the possibility of producing a higher fitness individual would improve greatly, and could enhance the search capability of genetic algorithm, equilibrate the local searching ability and global exploration ability. By quoting a shrinking factor to reduce the number of parameters to be optimized. Membership functions of fuzzy control, scaling factor and quantitative factors optimization were optimized by the improved genetic algorithm.