Application of neural network training in forward kinematics simulation for a novel modular hybrid manipulator with experimental validation

详细信息    查看全文

• 作者：Arash Rahmani ; Ahmand Ghanbari
• 关键词：2 ; (6UPS)  manipulators ; Image processing ; Kinematics simulation ; Nonlinear multivariable system ; Wavelet neural network
• 刊名：Intelligent Service Robotics
• 出版年：2016
• 出版时间：January 2016
• 年：2016
• 卷：9
• 期：1
• 页码：79-91
• 全文大小：4,716 KB
• 参考文献：1.Rico J, Gallardo J, Duffy J (1999) Screw theory and higher order kinematic analysis of open serial and closed chains. Mechan Mach Theory 34(4):559–586MATH MathSciNet CrossRef
  2.Carbone G, Ceccarelli M (2004) A stiffness analysis for a hybrid parallel–serial manipulator. Robotica 22(05):567–576CrossRef
  3.Carbone G, Ceccarelli M (2005) A serial–parallel robotic architecture for surgical tasks. Robotica 23(03):345–354CrossRef
  4.Zhou B, Xu Y (2007) Robust control of a 3-DOF hybrid robot manipulator. Int J Adv Manuf Technol 33(5–6):604–613CrossRef
  5.Cheng G, Gu W, Ge S-R (2012) Kinematic analysis of a 3SPS+ 1PS parallel hip joint simulator based on Rodrigues parameters. J Mech Sci Technol 26(10):3299–3310CrossRef
  6.Huang MZ, Ling S-H, Sheng Y (1993) A study of velocity kinematics for hybrid manipulators with parallel–series configurations. In: Proceedings of the 1993 IEEE international conference on robotics and automation. IEEE, New York
  7.Romdhane L (1999) Design and analysis of a hybrid serial–parallel manipulator. Mech Mach Theory 34(7):1037–1055MATH MathSciNet CrossRef
  8.Tanev TK (2000) Kinematics of a hybrid (parallel–serial) robot manipulator. Mech Mach Theory 35(9):1183–1196CrossRef
  9.Yang G, Chen W, Ho EHL (2002) Design and kinematic analysis of a modular hybrid parallel–serial manipulator. In: 7th international conference on control, automation, robotics and vision, 2002 (ICARCV 2002). IEEE, New York
  10.Huang T et al (2005) Conceptual design and dimensional synthesis for a 3-DOF module of the TriVariant-a novel 5-DOF reconfigurable hybrid robot. IEEE Trans Robot 21(3):449–456CrossRef
  11.LiangZhi F, Elatta A, XiaoPing L (2005) Kinematic calibration for a hybrid 5DOF manipulator based on 3-RPS in-actuated parallel manipulator. Int J Adv Manuf Technol 25(7–8):730–734CrossRef
  12.Campos A, Budde C, Hesselbach J (2008) A type synthesis method for hybrid robot structures. Mech Mach Theory 43(8):984–995MATH CrossRef
  13.Gallardo-Alvarado J et al (2008) Kinematics and dynamics of 2 (3-RPS) manipulators by means of screw theory and the principle of virtual work. Mech Mach Theory 43(10):1281–1294MATH CrossRef
  14.Gallardo-Alvarado J et al (2008) Solving the kinematics and dynamics of a modular spatial hyper-redundant manipulator by means of screw theory. Multibody Syst Dyn 20(4):307–325MATH MathSciNet CrossRef
  15.Gallardo J et al (2011) The kinematics of modular spatial hyper-redundant manipulators formed from RPS-type limbs. Robot Auton Syst 59(1):12–21CrossRef
  16.Hu B et al (2012) Analyses of inverse kinematics, statics and workspace of a novel 3RPS-3SPR serial–parallel manipulator. Open Mech Eng J 6:65–72CrossRef
  17.Li B, Zhao W, Deng Z (2012) Modeling and analysis of a multi-dimensional vibration isolator based on the parallel mechanism. J Manuf Syst 31(1):50–58CrossRef
  18.Chen C-T, Pham H-V (2012) Trajectory planning in parallel kinematic manipulators using a constrained multi-objective evolutionary algorithm. Nonlinear Dyn 67(2):1669–1681MathSciNet CrossRef
  19.Ahmad Ghanbari AR (2013) Neural network solutions for forward kinematics problem of hybrid serial–parallel manipulator. World Sci J 1(8):148–158
  20.Pedrammehr S, Mahboubkhah M, Khani N (2012) Improved dynamic equations for the generally configured Stewart platform manipulator. J Mech Sci Technol 26(3):711–721CrossRef
  21.Pedrammehr S, Mahboubkhah M, Khani N (2013) A study on vibration of Stewart platform-based machine tool table. Int J Adv Manuf Technol 65(5–8):991–1007CrossRef
  22.Qazani MRC et al (2014) An experimental study on motion error of hexarot parallel manipulator. Int J Adv Manuf Technol 72(9–12):1361–1376CrossRef
  23.Qazani MRC, Pedrammehr S, Rahmani A, Danaei B, Ettefagh MM, Rajab AKS, Abdi H (2015) Kinematic analysis and workspace determination of hexarot-a novel 6-DOF parallel manipulator with a rotation-symmetric arm system. Robotica 33:1686–1703. doi:10.​1017/​S026357471400098​8 CrossRef
  24.Zhang Q, Benveniste A (1992) Wavelet networks. IEEE Trans Neural Netw 3(6):889–898CrossRef
  25.Banakar A, Azeem MF (2008) Artificial wavelet neuro-fuzzy model based on parallel wavelet network and neural network. Soft Comput 12(8):789–808
  26.Huang M, Cui B (2005) A novel learning algorithm for wavelet neural networks. In: Advances in natural computation. Springer, Berlin, pp 1–7
  27.Chen D, Han J (2011) Application of wavelet neural network in signal processing of MEMS accelerometers. Microsyst Technol 17(1):1–5CrossRef
  
• 作者单位：Arash Rahmani (1)
  Ahmand Ghanbari (1)
  
  1. Mechatronics Laboratory, School of Engineering Emerging Technologies, University of Tabriz, 51666-16471, Tabriz, Iran
  
• 刊物类别：Engineering
• 刊物主题：Automation and Robotics
  Control Engineering
  Artificial Intelligence and Robotics
  User Interfaces and Human Computer Interaction
  Vibration, Dynamical Systems and Control
  Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1861-2784

文摘

This contribution addresses forward kinematic solution of modular hybrid manipulator which includes two similar Stewart mechanisms in serial form, known as 2-(6UPS) manipulator. First, using geometrical and vectorial analysis, mathematical model of kinematic analysis for 2-(6UPS) is extracted. Due to highly nonlinear characteristic of kinematic model of 2-(6UPS), which is related to complicated configuration of manipulator, forward kinematic solutions of mechanism is so difficult. Therefore, we proposed artificial neural network based on wavelet analysis to resolve forward kinematics of 2-(6UPS). Also, we used wavelet neural network (WNN) to approximate specific trajectory in circle oscillates in z direction and spiral with semi-cardioid base paths for mid and upper platforms movement respectively. Comparison between the results of proposed network and closed form solution of kinematics for 2-(6UPS) shows proper performance of proposed network in \(<\)1 % error. Also, WNN results are verified by experimental results which are obtained by image processing. Keywords 2-(6UPS)  manipulators Image processing Kinematics simulation Nonlinear multivariable system Wavelet neural network