ANFIS and Fuzzy Tuning of PID Controller for Trajectory Tracking of a Flexible Hydraulically Driven Parallel Robot Machine

Abstract

Parallel robots exhibit good performance in terms of rigidity, accuracy, and dynamic characteristics. However, parallel robots have complex configurations and their dynamic model is highly nonlinear, and conventional PID controllers are not sufficiently robust for their motion control. In this paper, we have investigated the intelligent control of a hydraulically driven parallel robot based on the dynamic model and two control schemes have been developed: 1) Fuzzy-PID self tuning controller composed of the conventional PID control and with Fuzzy logic; 2) Adaptive neuro-fuzzy inference system-PID (ANFIS-PID) self tuning of the gains of the PID controller. The two controllers are used to track a straight line. The obtained results confirm the theoretical findings, i.e., the Fuzzy–PID and ANFIS-PID self tuning controller can reduce more tracking errors than the conventional PID controller. Amongst these methods, ANFIS has provided the best results for controlling robotic manipulators as compared to the conventional control strategies. Finally, simulated results that demonstrate the robot behaviors are presented. 