Study of Strip Flatness and Gauge Complex Control Based on Improved PSO-RBF Neural Networks

An improved particle swarm optimization (IPSO) is presented to solve the premature and low precision based on shrinking chaotic mutation with population's fitness, which is used to train the radius basis function (RBF) neural networks, and optimization parameters of the network. Considering the stronger nonlinearity and coupling of strip flatness and gauge complex control, using the IPSO-RBF neural networks as a controller, an AFC-AGC system is designed. The simulation results show that the design method is simple and effective and has good performance of adaptively tracking target and resistance to disturbances, and provides a new way for strip flatness and gauge complex control

[1]  Wang Li.  Strip Flatness and Gauge Complex Control of RBF Neural Network Based on Hierarchical Genetic Algorithm , 2003 .

[2]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[3]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[4]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[5]  Hou Zhi-rong,et al.  Particle Swarm Optimization with Adaptive Mutation , 2006 .