Chaos Immune Particle Swarm Optimization Algorithm with Hybrid Discrete Variables and its Application to Mechanical Optimization

During the iterative process of standard particle swarm optimization (PSO), the premature convergence of particles decreases the algorithm's searching ability. Through analyzing the reason of particle premature convergence during the renewal process, by introducing the selection strategy based on antibody density and initiation based on equal probability chaos, chaos immune particle swarm optimization (CIPSO) algorithm with hybrid discrete variables model was proposed, and its program CIPSO1.0 with Matlab software was developed. Initiation based on chaos makes initial particles possess good performance and the selection strategy based on antibody density makes the particles of immune particle swarm optimization (CIPSO) maintain the diversity during the iterative process, thus overcomes the defect of premature convergence. Example for mechanical optimization indicates that compared with the exiting algorithms, CIPSO gets better result, thus certify the improvement of the algorithm's searching ability by immunity mechanism and chaos initiation particle swarm.