An adaptive neurocontroller for vibration suppression and shape control ofa flexible beam

This paper presents research into an adaptive nonlinear neural network cont rol algorithm that can be used with smart structure actuators and sensors t o control the shape and suppress the vibrations of flexible beams. The algo rithm presented couples an explicitly model-based adaptive component, which employs time-varying estimates of the beam material properties, with an ad aptive neural network, learning in real-time, which is used to estimate the additional actuator moments needed to offset the effects of periodic exter nal disturbances. Experimental results are given for a thin beam, with bond ed piezoceramic sensors and actuators, demonstrating the ability of the alg orithm to track desired bending profiles and reject the vibrations caused b y external disturbances, as well as to maintain this performance despite ch anges in the material properties of the structure or in the properties of t he external disturbance.