Feedback-error-learning for controlling a flexible link

Abstract

This paper discusses two approaches for neural control of a flexible link using the feedback-error-learning technique. This technique aims to acquire the inverse dynamics model of the plant and uses a neural network acting as an adaptive controller to improve the performance of a conventional non-adaptive feedback controller. The non-collocated control of a flexible link is characterized as a non-minimum phase system, which is difficult to be controlled by most control techniques. Two different neural approaches are used in this paper to overcome this difficulty. The first approach uses a virtual re-defined output as one of the impacts for the neural network and feedback controllers, while the other employs a delayed reference input signal in the feedback path and a tapped-delay line to process the reference input before presenting it to the neural network.