Control of the Water Tank Process Device Based on Particle Swarm Optimization
|School||Hebei University of Technology|
|Course||Control Science and Engineering|
|Keywords||particle swarm optimization algorithm adaptive chaos particle swarm optimization Radial Basis Function neural network multi-step predictive control|
The particle swarm optimization(PSO) algorithm is an evolutionary computation technique based on swarm intelligence developed by Kennedy and Eberhart in 1995. It is an intelligent optimization algorithm inspired by the behavior of birds, fish and laws of human society. As PSO is fast in convergence rate, few in parameter setting and easy in implementation, is an efficient search algorithm. It has aroused wide attention of scholars home and abroad, since the PSO from birth. At the same time, upsurge of research of the algorithm set off. Now it has been widely used in objective function optimization, system identification, fuzzy system control, neural network training, and other engineering fields.PSO have been applied efficiently,but as a new and developing research filed,PSO is still far from mature on systematization and standardization theory and application extending. How particle swarm optimization applied to more areas, is the same we need to focus on .Convergence and parameter selection problems greatly influence the performance and efficiency of PSO, this paper an adaptive chaos particle swarm optimization (ACPSO) was proposed, and used for optimization of RBF neural network. In the training, the neural network model with powerful generalization ability and well stability has been gained. Furthermore, the direct multi-step predictive controller based on the ACPSO-RBF is used to control the nonlinear system. The simulation manifest that the proposed method is more effective and efficient.