Optimization Of A Function Based On Improved Particle Swarm Algorithm

In this paper,the particle swarm optimization(PSO)is used as a random search algorithm in the swarm intelligence algorithm.It can be used to solve optimization problems that traditional optimization methods cannot solve.And it has the advantages of simple algorithm,less parameter setting and faster convergence speed.However,when it comes to solving optimization problems,there are still some limitations: it is easy to “premature”,and the diversity of populations is insufficient at the end of the iteration,and it is easy to fall into a local optimum.The limitations of the particle swarm algorithm are proposed to improve from some aspects:(1)In order to solve the problem that the algorithm is easy to fall into local optimum and the lack of population diversity in the later period: the paper uses the Canchy-Lortenz transition distribution and the Tsallis acceptance criterion in the generalized simulated annealing algorithm to blend in the particle swarm algorithm;and introducing the selection and crossover and mutation strategy in the genetic algorithm.(2)The particle swarm algorithm is more dependent on the parameters.In this paper,the adaptive adjustment inertia weight method and the asynchronous adjustment learning factor method are adopted.The parameter adjustment method given in this paper is more conducive to the global search and local search of the balanced algorithm.Finally,the algorithm proposed in this paper is applied to the function optimization problem and compared with other algorithms to verify the effectiveness of the improved algorithm.