There are a lot of optimization problems in the engineering application, which have the outstanding characteristics, such as complexity, constraint, nonlinearity and difficulty of modeling etc and are diffcult to solve by traditional mathematical techniques. Therefore, it is attractive for more and more researchers to find a new type of intelligent optimization method. Swarm intelligence, as a kind of intelligence computation, which exhibits a number of interesting properties such as cooperation, distribution, robustness and rapidness, provides reliable and convenient resolutions to complicated engineering optimization problems under no global information. Particle swarm optimization (PSO), which is a kind of intelligent optimization algorithm, has been paid attention and researched widely. Now PSO has been applied to the objective functions optimization, dynamic environments optimization, and neural network training, and so on.The theory and technique of PSO algorithm are introduced detailedly in this paper. Moreover, several weaknesses and their cause of formation of PSO are analyzed thoroughly. So PSO algorithm is combined with immune algorithm. Convergence rate and precision are improved by using better diversity in immune system and other immune operators. The disadvantages that PSO algorithm is easy to fall into local best and search ability is weak for discrete optimization problems are validly avoided. The main works of this dissertation are as follows:(1) The background, basic theory, maths description, convergence rule of randomicity algorithms and convergence of PSO are reviewed. Then the drawbacks and their cause of formation of PSO are analyzed.(2) The principles of immunity in biology are introduced briefly and some mechanism of artificial immune system is investigated. Furthermore, the mechanism of searching optimum of immune particle swarm optimization is researched.(3) A noval PSO algorithm solving discrete optimization problems is discussed. On the basis of binary encoding, a new evolution rule is proposed and negative selection, through using its characteristic of detecting abnormity to control the speed of particles and enhance the diversity of swarm, is introduced into binary PSO algorithm. Applied the proposed algorithm to function optimization problems, the simulation results show the improvement of the searching ability and increment in the convergence speed in comparison with the other binary particle swarm optimization and genetic algorithm.(4) The immune information processing mechanism and opposition-based learning are involved in PSO algorithm. We use the diversity of immune system, self-regulation and immune memory to make the algorithm have a strong global searching capacity. Then we extract bacterin through using characteristic information and knowledge of problems and direct the search process by vaccination and immune selection. Thus the premature phenomenon can be avoided effectively. Moreover, we employ opposition-based learning for population initialization to obtain fitter starting candidate solutions and improve the convergence speed. A real application in classifying two data sets in UCI machine learning database is provided. Numerical experiments show that the proposed algorithm has a better effect.(5) The mechanism of clonal selection of artificial immune system and chaos optimization are involved into PSO algorithm. Via clone operator and chaos mutation the diversity of the swarm is improved apparently. It was applied in BP neural network training combing with Iris-classify problem. The proposed algorithm compared with that of which was based on the standard PSO and BP algorithm. The results show that the proposed algorithm is superior to the other two algorithms with a better astringency and stability.Finally, the works of this dissertation are summarized roundly, and further research directions are indicated. |