Comparative study of the neural and neuro-fuzzy networks for direct path generation of a new fully spherical parallel manipulator

ABSTRACT

In this paper, the direct kinematics problem of a new 3(RPSP)-S fully spherical parallel manipulator (SPM) is solved using three different models of the artificial intelligence networks, including: a back propagation neural network (BPNN), a radial basis function neural network (RBFNN) and an adaptive neuro-fuzzy inference system (ANFIS). For the proposed networks, we use a training data set which is made from solving the inverse kinematics problem of the robot. After making a database for training the network, different parameters of the networks are changed and finally the best ones for each of BPNN, RBFNN and ANFIS models are derived. Effectiveness of the proposed models is checked by comparing the results of these models with the results of elimination method. As the results show, BPNN has the greatest error and the greatest computational time equal to and 12.4 s, respectively. The next model is RBFNN which has much better precision and less computational time which are equal to and 4.9 s, respectively. Finally, the simulation results by the ANFIS model show that it is the best model for solving the FKP of the 3(RPSP)-S robot. The mean square error (MSE) and computation time of the ANFIS model are and 1.2 s, respectively. These results confirm the reliability of the designed networks.

KEYWORDS:

• Spherical parallel manipulator
• inverse kinematics
• direct kinematics
• back propagation neural network
• radial basis neural network
• adaptive neuro-fuzzy inference system

Additional information

Notes on contributors

Javad Enferadi

Javad Enferadi was born in Mashhad,, Iran, in 1975. He received the B.E. degree in Mechanical engineering from the Ferdowsi University of Mashhad, Mashhad, Iran, in 1999. He received the master degree in Mechanical engineering from the Mazandaran University, Mazandaran, Iran, in 2002, and the Ph.D. degrees in Mechanical engineering from the Ferdowsi University of Mashhad, Mashhad, Iran, in 2010. Now, he is an Assistant Professor in the Department of Mechanical Engineering, Mashhad Branch, Islamic Azad University. His current research interests include kinematics, dynamics, optimization and control of the parallel robots.

Hamed Safari

Hamed Safari was born in Mashhad, Iran in 1985.  He received his bachelor’s degree in Mechanical Engineering from the University of Semnan, Iran. He continued his studies in Islamic Azad University of Mashhad, Iran and got his M.Sc. degree in mechanical engineering in 2015. He has been working on control and robotic field and his thesis title is: “Solving Direct Kinematics of Parallel Manipulators Using Neural Networks and Adaptive Neuro-Fuzzy Inference System”. His research interests include Kinematics and Control of Robots mostly using Artificial Intelligent Networks. What’s more, he works on different usages of robots in rehabilitative engineering and also industrial automation.