Fuzzy and neuro-fuzzy approaches to control a flexible single-link manipulator

Abstract

In this paper, new fuzzy and neuro-fuzzy approaches to tip position regulation of a flexiblelink manipulator are presented. Firstly, a non-collocated, proportional-derivative (PD) type, fuzzy logic controller (FLC) is developed. This is shown to perform better than typical model-based controllers (LQR and PD). Following this, an adaptive neuro-fuzzy controller (NFC) is described that has been developed for situations where there is payload variability. The proposed NFC tunes the input and output scale parameters of the fuzzy controller on-line. The efficacy of the NFC has been evaluated by comparing it with a fuzzy model reference adaptive controller (FMRC).