Real-Coded Adaptive Genetic Algorithm Applied to PID Parameter Optimization on a 6R Manipulators

Abstract

A new matching crossover real-code adaptive genetic algorithm base on the population maturity is presented to optimize the parameters of a PID controller. The individual is coded in real number, and its crossover probability varies according to the individual fitness and the population maturity in course of evolution. New individuals generated by the crossover between individuals with the best fitness and the second best fitness are added into the population to decrease the search size of the real-coded genetic algorithm. To a certain extent, this algorithm can improve the crossover efficiency of the real-coded adaptive genetic algorithm, solve the premature problem and generate new preponderant individuals much more efficiently. The experiments on the PID parameter optimization of a 6 R series arc welding manipulators demonstrate that this algorithm can enhance the performance of searching global optimum and keep the population diversity at a high level at the same time. The optimization result of this algorithm is better than the one of the others.