Identification and control of a benchmark flexible structure using piezoelectric actuators and sensors

This paper proposes a neural network approach for the identification and control of a benchmark flexible structure, i.e. a thin simply-supported plate with bonded piezoelectric film actuators and sensors. A specific linear differential inclusions (LDI) model is developed for a class of multilayer feedforward networks. With the technique, the plant model identified by the neural network can be represented as a linear time-invariant system so that the linear control theory can be applied to design the stabilizing flexible structure controller.