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

Abstract

In this paper we propose a neural network approach for the identification and control of a benchmark flexible structure: a thin simply-supported plate with bonded piezoelectric film actuators and sensors. A specific linear differential inclusion is developed for a class of multilayer feedforward networks. With this technique, it is shown that the plant model identified by the neural network can be represented as a linear time-invariant system so that traditional or advanced linear control theory can be directly applied to design the stabilizing flexible structure controller.