IJE TRANSACTIONS C: Aspects Vol. 30, No. 9 (August 2017) 1404-1410    Article in Press

PDF URL: http://www.ije.ir/Vol30/No9/C/13.pdf  
downloaded Downloaded: 0   viewed Viewed: 64

J. Ghasemi, R. Moradinezhad and M. A. Hosseini
( Received: March 04, 2017 – Accepted: July 07, 2017 )

Abstract    In this research, Artificial Neural Networks have been used as a powerful tool to solve the inverse kinematic equations of a parallel robot. For this purpose, we have developed the kinematic equations of a Tricept parallel kinematic mechanism with two rotational and one translational degrees of freedom (DoF). Using the analytical method, the inverse kinematic equations are solved for specific trajectory, and used as inputs for the applied ANNs. The results of both applied networks (Multi-Layer Perceptron and Redial Basis Function) satisfied the required performance in solving complex inverse kinematics with proper accuracy and speed.


Keywords    Parallel Robot, Kinematics, Artificial Neural Network.


چکیده    در این تحقیق، شبکه های عصبی به عنوان یک ابزار قدرتمند برای حل معادلات سینماتیک معکوس یک ربات موازی به کار گرفته شده است. به این منظور معادلات سینماتیک یک مکانیزم Tricept با دو درجه آزادی چرخشی و یک درجه آزادی انتقالی توسعه داده شد. با استفاده از روش های آنالیز تحلیلی، معادلات سینماتیک معکوس برای یک فضای مشخص حل شد. پاسخ به دست آمده به عنوان ورودی شبکه عصبی به کار گرفته شده است. نتایج دو شبکه عصبی بکار گرفته شده (پرسپترون چند لایه و شبکه عصبی تابع شعاعی) با سرعت و دقت مناسبی توانست معادلات پیچیده سینماتیکی مکانیزم را مدل کرده و حل نماید.

References    [1]          J. -P., Merlet, 2006, Parallel Robots, Springer. [2]          K.-E.Neumann (1988) US patent 4,732,525, Mar. 22. [3]          www.pkmtricept.com. [4]          G. Pond, J. A. Carretero (2007) “Quantitative dexterous workspace comparison of parallel manipulators, Mechanism and Machine Theory”, 42(10), 1388-1400. [5]          M. A. Hosseini, H. M. Daniali (2011) “Weighted local conditioning index of a positioning and orienting parallel manipulator”, Sientica Iranica B, 18(1), 115-120. [6]          M. A. Hosseini, H. R. M. Daniali, H. D. Taghirad (2011) “Dexterous Workspace Optimization of a Tricept Parallel Manipulator”, Advanced Robotics,  25, 1697-1712. [7]          M. A. Hosseini, H. R. M. Daniali (2011) “Dexterous Workspace Shape and Size Optimization of a Tricept Parallel Manipulator”, International Journal of Robotics, Vol. 2, No. 1, pp.18-26. [8]          M. A. Hosseini, H. R. M. Daniali (2014) “Cartesian Workspace Optimization of Tricept Parallel Manipulator with Machining Application”, Accepted in Robotica. [9]             H. P. Singh, N. Sukavanam (2013) “Stability analysis of robust adaptive hybrid position/force controller for robot manipulators using neural network with uncertainties”, Neural Computing and Applications, Volume 22, Issue 7-8, pp. 1745-1755. [10]         N. Kumar, V. Panwar, J. H. Borm, J. Chai, J. Yoon (2013) “Adaptive neural controller for space robot system with an attitude controlled base”, Neural Computing and Applications, Volume 23, Issue 7-8, pp. 2333-2340. [11]         C. Jayawardena, K. Watanabe, K. Izumi (2007) “Controlling a robot manipulator with fuzzy voice commands using a probabilistic neural network”, Neural Computing and Applications, Volume 16, Issue 2, pp 155-166.[12]         Q. Xu, Y. Li (2007) “A 3-PRS Parallel Manipulator Control Based on Neural Network” Advances in Neural Networks - ISNN 2007,Lecture Notes in Computer Science Volume 4491, pp. 757-766.[13]         P. J. Parikh, S. S. Lam (2009) “Solving the forward kinematics problem in parallel manipulators using an iterative artificial neural network strategy” s.l.,The International Journal of Advanced Manufacturing Technology,Volume 40 Issue 5-6 , pp. 595-606.[14]         Y. Li, Y. Wang (2009)  “Trajectory Tracking Control of a Redundantly Actuated Parallel Robot Using Diagonal Recurrent Neural Network” s.l.,Natural Computation, 2009. ICNC '09. Fifth International Conference on ,Volume 2.[15]         L. Guan, J. Wang, L. Wang (2003) “Hybrid computational intelligence based kinematic analysis for parallel machine tool”   s.l.,Systems, Man and Cybernetics, 2003. IEEE International Conference on,Volume 3.[16]         Z. Yang, J. Wu,  J. Mei (2007) “Motor-mechanism dynamic model based neural network optimized computed torque control of a high speed parallel manipulator” s.l.,Mechatronics,Vols. Volume 17, Issue 7, pp. 381–390.[17]         A. Morella, M. Tarokh, L. Acosta (2013)  “Solving the forward kinematics problem in parallel robots using Support Vector Regression” s.l.,Engineering Applications of Artificial Intelligence Volume 26, Issue 7, pp. 1698–1706.[18]         B. Siciliano (1990) “Kinematic control of redundant robot manipulators: A tutorial”, Journal of Intelligent and Robotic Systems, Volume 3, Issue 3, pp. 201-212. [19]         S. G. Kim, J. Ryu (2003) “New dimensionally homogeneous Jacobian matrix formulation by three end-effector points for optimal design of parallel manipulators”, IEEE Trans. Robotics Automat. 19, 731–737. [20]      J. Wang, C. M. Gosselin (1998) “A new approach for the dynamic analysis of parallel manipulators” Multibody Syst. Dyn. , 2: 317–334.[21]         M. A. Hosseini, H. M. Daniali (2011) “Kinamatic analysis of Tricept parallel manipulator”, IIUMEJ, Vol. 12, no. 5, pp. 7-16. [22]         M. A. Hosseini, H. R. M. Daniali, H. D. Taghirad (2011) “Dexterous Workspace Shape and Size Optimization of a Tricept Parallel Manipulator”, International Journal of Robotics, Vol. 2, No. 1, pp.18-26.[23]      S. O. Haykin (2009) “Neural Networks: A Comprehensive Foundation 3rd edition” NewYork,Macmillan.

Download PDF 

International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir