Abstract: The premature convergence seriously affects the performance of genetic algorithm. At present time, most of the improved algorithms focus on improving the convergence accuracy and speed at the expense of the algorithm time complexity, which limits the applications of genetic algorithm in industrial control system. For this situation, this paper presented a new improved genetic algorithm with adaptive convergence populations. This algorithm optimizes performance through increasing the genetic quality of populations, and at the same time, strictly controls the algorithm complexi ty. Simulation results show that the new algorithm can significantly improve the accuracy and speed of convergence, without time complexity increasing.

Key words: Genetic algorithm, Premature convergence, Aaptive mutation operator, Industrial control