Neural Network-Based Adaptive Sliding Mode Control for Gyroelastic Body

Abstract

Gyroelastic body refers to a flexible structure with a cluster of angular momentum devices. The torques exerted by the angular momentum devices can be used for active vibration suppression. This paper addresses the vibration suppression of gyroelastic body in the presence of uncertainties and external disturbances. Considering that the modal variables of the gyroelastic body cannot be measured directly. Therefore, a neural network (NN) based adaptive modal observer is designed to estimate the modal information of the gyroelastic body. Based on the modal observer, a NN-based adaptive sliding mode output feedback controller (NNASMOFC) is designed. The stabilities of the NN-based modal observer and the NNASMOFC are proved using Lyapunov theory. The possible spillover problem is considered by optimal actuator placement. Simulation results demonstrate the effectiveness of the proposed controller and observer.