The Theory And Application Of Particle Swarm Optimization Algorithm Based On Chaos

As a swarm intelligence algorithm, particle swarm optimization (PSO) algorithm has been one of the research hotspots in the international artificial intelligence field at present. It takes advantage of colony to find new avenue for the solution of complex problems. Therefore, to study and master the characteristics and rule of PSO is a task that is significant in both theory and application areas. In addition, in view of its wide market prospect, extending its application scope is also very important in practice. PSO has been applied efficiently, but as a new and developing intelligent algorothm, PSO is still far from mature on systematization and standardization theory and application extending.This article concentrates the research on the theory and application of PSO, based on the analysis of research methods and algorithm frame, several aspects of PSO such as basic principle, algorithm characters, improvement and realization are systematically discussed. The main contributions given in this dissertation are as follows:1. Knowledge emergence in swarm intelligence and its research methods are presented, then ant colony optimization and PSO as two swarm intelligence patterns are described, the research actuality and the problems faced by PSO are analyzed.2. Parameters and convergence greatly influence the performance and efficiency of PSO, this paper studies the convergence of PSO using the theory of difference equation, discusses the influence with the convergence of PSO by the track and the velocity of particle, and the guideline of better choosing the parameters is given. A chaos particle swarm optimization (CPSO) algorithm is introduced to overcome the problem of premature convergence, CPSO uses the properties of ergodicity, stochastic property, and regularity of chaos to lead particles'exploration. In order to improve the algorithm's efficiency, an adaptive CPSO (ACPSO)was proposed, in which the inertia weight of the particle was adjusted adaptively based on the premature convergence degree of the swarm and the fitness of the particle, the diversity of inertia weight makes a compromise between the global convergence and convergence speed, so it can effectively alleviate the problem of premature convergence,3. Only few research pay attention to the cluster analysis of uncompact and irregular data, this article take advantage of ant colony algorithm's superiority on combinatorial optimization problems, bring forward a new algorithm based on ant colony algorithm integrated with PSO and neighbor function criterion to solve this problem. A dynamic and adaptive ant colony algorithm is proposed to increase the diversity of solution space and the capacity of global searching, local optima estimating and disposing mechanism is added in the algorithm while updating pheromone adaptively. Result shows that this new clustering algorithm can commendably solve the problem about the uncompact and irregular distribution to a certain extent.4. Redundant connections not only decrease the processing speed, large numbers of redundant connections but also affect the performance of ANN, therefore, a novel and efficient method combining chaos particle swarm optimization (CPSO) and discrete particle swarm optimization (DPSO) is proposed to optimize the topology and connection weights of multilayer feed-forward artificial neural network (ANN) simultaneously. In the proposed algorithm, the topology of neural network is optimized by DPSO and connection weights are trained by CPSO to search the global optimal ANN structure and connectivity. The proposed algorithm is successfully applied to fault diagnosis and temperature prediction of molten iron in blast furnace, able to eliminate some bad effects introduced by redundant structure of ANN. Compared with other algorithms, the proposed method shows its superiority on convergence property and efficiency in training ANN.Due to its good optimizing performance, the application of PSO in neural network area is carried on. A hybrid clustering algorithm (PSO/SOM) based on Particle Swarm Optimization (PSO) and Self-Organizing Map (SOM) is proposed. In the proposed algorithm, SOM network is trained by PSO algorithm instead of SOM'heuristic-based training algorithm, Moreover, kernel method is introduced to strengthen performance of PSO/SOM nonlinear clustering. The algorithm is successfully applied to pattern clustering recognition problems including Wine, Iris, etc.The experimental results show that this algorithm can obtain good clustering results. Compared with standard SOM algorithm, PSO/SOM can improve the clustering accuracy with lower quantization error and topological error.5. Current intrusion detection systems have low detection rate and high false positive rate for new intrusion types, this article applied PSO in network security area, a novel intrusion detection method based on Particle Swarm Optimization (PSO) and Fuzzy C-Means Clustering (FCM) is proposed in order to solve the problem of FCM which is much more sensitive to the initialization and easier to fall into local optimization. This method can quickly obtain global optimal clustering and can detect unknown intrusions efficiently, it does not need to classify the training data sets with artificial or other methods. The experimental results show that this method can detect unknown intrusions with lower false positive rate and higher true positive rate.In general, the theory and application of PSO are analyzed comprehensively. Finally, whole research contents are summarized, and further research directions are indicated.