Experimental Investigation of Active Vibration Control Using a Filtered-Error Neural Network and Piezoelectric Actuators
The filtered-error back-propagation neural network (FEBPNN) algorithm for control of smart structure is investigated experimentally. Piezoelectric actuator is employed to suppress the structural vibration. The controllers based on the FEBPNN algorithm and the filtered-x least mean square (FXLMS) algorithm are implemented on a digital signal processor (DSP) TMS320VC33. The experimental verification tests show that the FEBPNN algorithm is effective for a nonlinear control problem, and has better tracking ability under change of the primary disturbance signal.
Unable to display preview. Download preview PDF.