A novel PSO algorithm based on an incremental-PID-controlled search strategy

作者：Zhang, Jianhua^*; Yang, Shaozeng

来源：Soft Computing, 2016, 20(3): 991-1005.

DOI：10.1007/s00500-014-1560-x

• Particle Swarm Optimization
• Incremental PID controller
• Benchmark function optimization
• Jiles-Atherton model

Many variants of Particle Swarm Optimization (PSO) algorithm have been proposed in literature in the past two decades. The two research major topics, namely particle movement trajectory analysis and parameter selection, have also been intensively explored. Focused on the two issues, this paper transforms the velocity updating strategy in PSO algorithm to an incremental PID controller and thus develops a new incremental PID controlled search strategy. To endow this new PID-controlled deterministic search strategy with a stochastic nature, a mutation operation is applied on the particles and their exemplars. Based on such learning concepts, a novel incremental PID-controlled PSO, called IPID-PSO in short, algorithm is proposed. The proposed IPID-PSO algorithm is applied to eight benchmark problems of function optimization widely considered in literature. Compare with other two PSO variants, the IPID-PSO algorithm outperforms them on most of the eight functions. This superiority shows the usefulness of the proposed search strategy. Finally, the IPID-PSO is employed to estimate the parameters of the Jiles-Atherton (J-A) model, which is usually adopted to describe the hysteresis loop of magnetic materials. The results demonstrate that the proposed IPID-PSO is also effective for the J-A model parameter estimation. Therefore it can be concluded that the IPID-PSO algorithm provides a promising and satisfactory solution to real-world applications.

• 出版日期2016-3
• 单位华东理工大学