ANFIS active vibration control of flexible beam structures

Abstract

This paper presents the development of an adaptive neuro-fuzzy inference system (ANFIS) controller for vibration control of flexible beam structures. ANFIS constructs a fuzzy inference system (FIS) whose membership function parameters are tuned (adjusted) using the backpropagation algorithm and least squares method. This allows the fuzzy system to learn from the data modeling. To allow the non-linear dynamics of the system be incorporated within the design, a pseudo random binary signal (PRBS) covering the dynamic range of interest of the system is used to train the ANFIS model, which gives good output prediction. Simulation results showing the performance of the developed control scheme in vibration suppression of flexible beam structures, with changes in the excitation signal, are presented and discussed.