Improving Particle Swarm Algorithm And Its Application

Along with the progress of science and technology, the progress of engineering technology has become general, complicated and intelligent. There are many optimization problems in the fields of industry, society, economy, management, and so on. There are many methods for the optimization. Stochastic optimization, as a method of real efficient and common adaptive, is a kind of intelligent optimization algorithm and its foundation is bionics, artificial intelligence. It makes progress through simulating some natural phenomenon, which includes Simulating Anneal, Genetic Algorihm, Ant Colony Algorithm and so on. As a new evolutionary technology, Swarm Intelligence Algorithm has become the research focus of many scholars. As one of Swarm Intelligence Algorithm, Particle Swarm Optimization(PSO) theory recently, is recognized in the control field and the computer field broadly. Particle Swarm Optimization for further study, will contribute to much better engineering solution of the problems.In this paper, PSO algorithm has been further improved, and the improved algorithm used in the 0-1 Knapsack Problem.research work of the paper is as follows:①Based on the PSO's idea, the PSO has been introduced and discussed in detail in this paper. The merits and disadvantage of the PSO is analyzed and then its basal principle is analyzed and reseached in this paper. The algorithmic basal steps of design and flow progress are offered, behavior analysis and convergence analysis of PSO are presented.②In order to prove algorithm's performance, according to the basic principles of algorithm design, a new improved PSO algorithm that based on particle swarm optimization with organization has been presented, which is called SM-OPSO. The method of survival of the fitter is canceled, NM simplex method is used to improve the worst organization. It will keep the current structure of particle, accelerate the convergence rate and maintain the merits of the original algorithm.③The SM-PSO algorithm is applied to the 0-1 Knapsack Problem. the MATLAB simulation experiments are implemented, and analyzed the basic PSO algorithm, OPSO algorithm and the SM-OPSO performance indicators. The result shows algorithm presented in this paper is valid, practical and feasible. Finally, the work of this dissertainion is summarized and the prospective of research on particle swarm optimization is discussed.