Immune Clone Selection Algorithm Research And Its Application

Artificial Immune Systems (AIS) is an artificial intelligent system, which simulating the high-performance, self-organization and robustness of biological immune system. The objective of this study is to explore the evolutionary learning mechanisms contained in biological immune system。A novel algorithm based on Immunodominance Clonal Selection Algorithm is proposed, the Local Optimization Immunodominance Clonal Selection Algorithm for combinatorial optimization problem is devised. Immune ant Clonal Selection Algorithm through combining Immunodominance Clonal Selection Algorithm and ant colony algorithm is proposed. At last, a theory and method of Intelligent Disturbance Rejection Control by integrating the immune Algorithm with Auto-Disturbance Rejection Controller Technique is presented. The study focuses on the following aspects:(1) This paper proposes the model of Local Optimization immunodominance Clonal Selection Algorithm. Clonal multiplication operator and affinity function etal operator are improved. The affinity maturation of antibody is enhanced by local Optimization Immunodominance operating, clone expansion and dynamic hyper mutation and so on. Simultaneously, adjusting mechanism of antibody concentration and antibody clonal deletion are introduced into this algorithm, which enhances the diversity of antibody and get the balance between the depth and breadth research. Providing theoretical proof for the quicker convergence speed of Local Optimization immunodominance Clonal Selection Algorithm. Simulation testing illustrates that the algorithm has a remarkable quality of convergence velocity and global convergence reliability.(2) This paper proposes a Local Optimization immunodominance Clonal Selection Algorithm for combinatorial optimization problem. Local Optimization immunodominanc operators are designed for Travelling Salesman Problem. Excellent antibodies are obtained by Local Optimization mmunodominance operating. The Multiple of clone according to the affinity and Concentration of antibodies. The affinity maturation of antibody is enhanced clone expansion and adaptive dynamic hyper mutation and so on. Adjusting mechanism of antibody concentration and antibody clonal deletion are introduced into this algorithm. Simulation testing illustrates that the algorithm is Feasible, efficient, has a remarkable quality of convergence velocity and global convergence reliability. (3) The paper proposes immune ant Clonal Selection Algorithm through combining Immunodominance Clonal Selection Algorithm and ant colony algorithm. In order to enhance explorative capacity of the algorithm while avoiding the premature stagnation behavior, ants were divided into two groups with different state, elitist ants were got from tabu table which was optimized through immune operator like clone expansion and hyper mutation, etal, and then local optimization immunodominance operating was introduced into this algorithm. Providing theoretical proof for the quicker convergence speed of the algorithm, and then the algorithm is applied into combinatorial optimization problem, the experiments on TSP problems show that the new algorithm is capable of improving the search performance significantly no matter in convergent speed or precision.(4) The Theory and Methods of Intelligent Disturbance Rejection Control by integrating the immune Algorithm with Auto-Disturbance Rejection Controller Technique are proposed. Utilizing the optimization-ability of the improved immune clonal selection algorithm. And then is applied to to optimize the Auto-Disturbance Rejection Controller.The optimization Methods and procedures of the Disturbance Rejection Control are proposed. Bring The Superiority of the Auto-Disturbance Rejection Controller Technique into full play. Simulation results of nonlinear discrete-time systems demonstrate that has excellent control quality. Providing new ideas for modern intelligent control.