Parameter estimation for time-varying system based on improved genetic algorithm

In this paper, the authors first analyze the drawback of genetic algorithm with traditional mutation operator in preventing GA from converging prematurely, then study its influence on the diversity of genes in the same locus, and point out that the traditional mutation, to some extent, can result in premature convergence of genes in the same locus. This will cause the loss of critical alleles. Inspired by digital technique, we import two kinds of Boolean operation into GA to develop a novel mutation operator and discuss its contribution to prevent the loss of critical alleles. The experimental results of function optimization show that the improved mutation operator can prevent premature convergence effectively, and can provide a wide range of selecting control parameters for GA. Then we present a new parameter estimation algorithm based on the improved GA. Simulation experiments have been carried out and their results show that this estimation algorithm has good tracking ability and is not sensitive to the noise.