The Research And Application Of Improved Artificial Fish Swarm Algorithm

Optimization problems need to be solved in many fields and the fine solutions to the problems may be lead to great economic benefit. With the increasing complexity and scale of the optimization problems, classical optimization method which are based on the strict modeling become difficult to use. Intelligent optimization algorithms have been developed by simulating the certain nature and social processes, which provide new approaches to get the optimization of some complex systems. Intelligent optimization algorithms have attracted a lot of attentions from researchers around the world and have been applied in many areas.The Artificial Fish Swarm Algorithm (AFSA) is an evolutionary computation technique based on intelligence bionic optimization algorithm. The AFSA has a stronger robustness; the fine distributed computing and easy to union with other methods.The thesis mainly uses AFSA as research object, systematically researches the structure principle and improvement strategy of AFSA, furthermore, proposes an improved AFSA which has based on Harmony Search. The major research contents are as follows:(1) A brief introduction of intelligent optimization problems and swarm intelligence was made. The biological elements, basic principles, mathematical model and algorithm flow of AFSA were discussed in detail. The research progress of AFSA was summarized by stages. All of the above indicated the importance of researching the AFSA. Through experiments, parameters selection was researched in details, which provided the useful reference for the further study of the AFSA.(2) Summarized the disadvantages of typical AFSA, proposes the methods and steps of improvement algorithm performance. On the basic of former research, to improve the fault of typical AFSA, absorbs the advantages of many improvement algorithms, proposes an improved AFSA which has based on Harmony Search. AFSA algorithm used in the two control parameters HMCR and PAR from Harmony Optimization which to improve artificial fish swimming behavior and the global search ability of artificial fish. It tests the performance of algorithm through Standard test functions. Generally contrasts and researches it through many aspects such as the speed of algorithm iteration, the accuracy of algorithm convergence and the complex of algorithm. Finally, compare with traditional AFSA by some data, we proved that the multiple behavior global optima AFSA has better convergence performance. It is an excellent improvement method.(3) The method was applied to the TSP problem, a simulation experiment results show that the AFSA harmony search based on the convergence rate and better, has better global convergence performance.