An Adaptive Neuro-Fuzzy Controller for Vibration Suppression of Flexible Structuress
Adam Genno, Wilson Wang
Abstract
Neuro-fuzzy (NF) controllers are useful in a wide range of industrial applications due to their adaptive capability by proper training. In this article, an adaptive NF controller is developed to suppress the vibration of flexible structures. A new training method based on the bisection particle swarm optimization (BPSO) algorithm is proposed to optimize the NF controller parameters recursively. To reduce additional vibration induced by controller response to nonlinearities in the steady-state solution space, a fuzzy boundary function is suggested to shape the control signal and reduce the induced vibrations from the control action. The parameters related to output suppression are optimized simultaneously during recursive NF system training. The effectiveness of the adaptive NF control technique and the BPSO training method are validated by a series of experimental tests.