Loading

Modeling and Simulation of Industrial SCARA Robot Arm
Yousif Ismail Mohammed1, Safwan Mawlood Hussein2

1Yousif Ismail Mohammed, Department of Computer Engineering– Engineering College – Ishik University, Erbil, Iraq.
2Safwan Mawlood Hussein, Department of Computer Engineering– Engineering College – Ishik University, Erbil, Iraq

Manuscript received on 15 April 2015 | Revised Manuscript received on 25 April 2015 | Manuscript Published on 30 April 2015 | PP: 220-229 | Volume-4 Issue-4, April 2015 | Retrieval Number: D3944044415/15©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Many industrial applications needed inelegant robot, especially with trajectory processing for movement and pressing things with very accurate points. This paper presents study of Adaptive Neuro Fuzzy Inference Scheme (ANFIS) for Selective Compliant Assembly Robot. Detail description of a Four degrees of freedom (DOFs) mathematical model of an industrialapplication SCARA robot with three (shoulder, elbow, wrist) controlled by servo motors and one pneumatics. DC servomotor driving each of the robot-arm joint is modeled and analytical inverse kinematic problem (IKP) and the forward kinematic solution by D-H parameters. Neural networks with fuzzy logic controller (FLC) select the proper rule base through the RBFNN algorithm as inelegant controller for driving the robot with specific trajectory and apply specific handling processing suitable with certain job. The simulation of mathematical model is done by using Matlab Ver. 2014a, satisfactory results was obtained proved the implement of the system design as practical implement with accurate industrial application.
Keywords: SCARA Robot, Adaptive Neuro Fuzzy Inference Strategy (ANFIS), Industrial Applications

Scope of the Article: Fuzzy Logics