Experimental adaptive vibration control of smart structures using LVQ neural networks

This paper presents experimental adaptive identification and control of a smart structure featuring piezoceramic-based sensors/actuators. An inverted L-structure with surface bonded piezoceramic sensors/actuators is used for analysis. The state-space presentation, from control input voltages to output sensor voltage is established in multivariable form. It is assumed that the parameters of the smart structure are changing at fast rates. Computational time required for classical identification techniques is generally quite high. For the system, whose parameters change quickly with time, classical system identification techniques fail. So, for improving the system performance, Linear Quadratic Regulator (LQR) cannot be re-designed in real-time for changed parameters of the flexible structure, even if these parameters are identified in real time. Closed loop identification of system parameters and control gains based on system classification technique is proposed for the systems changing at fast rates.