Study of Neuro-Fuzzy Network Control of a Flexible Robot

This paper deals with the tracking control problem of a rigid-flexible manipulator system with unknown and changing dynamics. Lagrange-Euler formulation is used to establish the dynamics of the robotic system. Because of the characteristics of high non-linearity and complexity of the robotic system, intelligent control strategy is proposed to control the system in this study, in which a fuzzy logic controller in the feedback configuration and an efficient dynamic recurrent neural network in the feedforward configuration are developed. Simulations are carried out for both the fuzzy logic controller and the proposed intelligent controller under the condition of three groups of step inputs. Results demonstrate that the performance of the system is greatly improved by using the proposed controller.