A distributive neural control system is advocated for flexible multibo
dy structures. The proposed neural controller is designed to achieve t
rajectory slewing of a structural member as well as vibration suppress
ion for precision pointing capability. The motivation to support such
an innovation is to pursue a real-time implementation of a robust and
fault tolerant structural controller. The proposed control architectur
e which takes advantage of the geometric distribution of piezoceramic
sensors and actuators has provided a tremendous freedom from computati
onal complexity. In the spirit of model reference adaptive control, we
utilize adaptive time-delay radial basis function networks as a build
ing block to allow the neural network to function as an indirect close
d-loop controller. The horizon-of-one predictive controller cooperativ
ely regulates the dynamics of the nonlinear structure to follow the pr
especified reference models asymptotically. The proposed control strat
egy is validated in the experimental facility, called the planar artic
ulating controls experiment which consists of a two-link flexible plan
ar structure constrained to move over a granite table. This paper addr
esses the theoretical foundation of the architecture and demonstrates
its applicability via a realistic structural test bed. Copyright (C) 1
996 Elsevier Science Ltd.