Research And Application Of Modified Particle Swarm Optimization Algorithm Based On Simulated Annealing

Particle swarm optimization (PSO) algorithm is a simple stochastic global optimization technique. But this algorithm has some demerits, such as relapsing into local extremum, slow convergence velocity and low convergence precision in the late evolutionary. The parameters of the PSO algorithm are always based on experience without theories in the past. To resolve these problems, a composite particle swarm optimization algorithm based on simulated annealing is proposed in this paper. The parameters of particle swarm optimization algorithm are optimized by the simulated annealing, so that it can alter with the algorithmic process to adapt to the object. The results of experiment clearly demonstrate the improved performances of the proposed PSO algorithm. Finally, the modified PSO algorithm was applied to the constrained optimization problem, the solving nonlinear equations and the system identification of thermal process, and it was proved effectively that the proposed PSO in this paper is effective and applicable.