Hybrid Intelligent Optimization Algorithm Based On AFSA And Its Application

Optimization technology has attracted a lot of attention in the fields of science and engineering. Some problems have been found in classical optimization methods to solve high dimension, multi-modal and other complex systems. In order to overcome these shortcomings, a lot of research on Intelligent Optimization Algorithms has been done, and several Hybrid Intelligent Optimization Algorithms combined with the advantage of various optimization algorithms are proposed with discussed in-depth. In this paper, two new Hybrid Intelligent Optimization Algorithms are proposed, which combined Artificial Fish Swarm Algorithm with Tabu Search and Genetic Algorithm. Then the paper discusses the application of the two hybrid algorithms in Multi-objective Optimization, Parameter Estimation, and Combinatorial Optimization, which is seldom covered by other authors. The main contents of the paper are as follows:1,The status of the Intelligent Optimization Algorithm research is systematically introduced, as well as the limitations of simple Intelligent Optimization Algorithms and the advantages of Hybrid Intelligent Optimization Algorithms. By analyzing the Artificial Fish Swarm Algorithm and the typical bench-mark simulation, the influence of parameters on the convergence speed and accuracy of the Artificial Fish Swarm Algorithm is discussed. Then, the basic principles of setting the parameters in Artificial Fish Swarm Algorithm are summarized and a grading and variable parameter optimization strategy is proposed.2,Based on improved Artificial Fish Swarm Algorithm, two new Hybrid Intelligent Optimization Algorithms are proposed, one of which is combined with Tabu Search while the other with Genetic Algorithm. Comparing with previous studies, effectiveness of these two algorithms has been proven by Matlab simulation.3,The application of HIOA-TSFA algorithm in solving Multi-objective Optimization Problem by the method of Punishment Items is introduced. Simulation studies show that it is very effective to solve complex function and Multi-objective Optimization Problem. Secondly, the application of HIOA-GFA in solving Parameter estimation of Nonlinear System is discussed. Simulation study under the absence of noise and white noise conditions show that it is very effective in solving the parameter estimation problem in the Lorenz chaotic system. Finally, the cross-partial optimization strategy is introduced to improve the HIOA-GFA, the application of the improved algorithm in the Traveling Salesman Problem (Combinatorial Optimization Problem) is discussed. It is proved to be effective to solve TSP problem by Matlab simulation.