The Adaptive Niche Genetic Algorithm for Optimum Design of PID Controller

Abstract

Standard genetic algorithms have the defects of pre-maturity and stagnation when applied in optimizing problems. In order to avoid the shortcomings, an adaptive niche genetic algorithm (ANGA) is proposed. The Elitist strategy is utilized to ensure the stable convergence, niche ideology is used to maintain diversity of evolution population, and the adaptive crossover rate and mutation probability are introduced to enhance the local search ability around every peak value. This algorithm is applied to design of optimal parameters of PID controllers with examples, and the simulation results show that fast tuning of optimum PID controller parameters yields high-quality solution. Compared with the standard genetic algorithm, ANGA is indeed more efficient in improving searching capability and convergence characteristic.