A study on industrial robotic manipulator model using model based predictive controls

In this study, a single input single output (SISO) neural generalized predictive control (NGPC) was applied to a six joint robotic manipulator. The SISO generalized predictive control (GPC) was also used for comparison. Modeling of the dynamics of the robotic manipulator was made by using the Lagrange–Euler equations. The cubic trajectory principle is used for position reference and velocity reference trajectories. A simulation program was prepared by using Delphi 6.0. All computations for manipulator dynamics model, GPC-SISO, and NGPC-SISO were done on PC with 1.6 GHz Centrino CPUs by using this program. The parameter estimation algorithm used in the GPC-SISO is Recursive Least Squares. The minimization algorithm used in the NGPC-SISO is Newton–Raphson. According to the simulation results, the results of the NGPC-SISO algorithm were better than those of the GPC-SISO algorithm.

[1]  Fevzullah Temurtas,et al.  Application of neural generalized predictive control to robotic manipulators with a cubic trajectory and random disturbances , 2006, Robotics Auton. Syst..

[2]  Raymond Gorez,et al.  Fuzzy and Quantitative Model-based Control-systems for Robotic Manipulators , 1993 .

[3]  Ole Ravn,et al.  Implementation of neural network based non-linear predictive control , 1999, Neurocomputing.

[4]  D I Soloway,et al.  Neural Generalized Predictive Control: A Newton-Raphson Implementation , 1997 .

[5]  David W. Clarke,et al.  Generalized Predictive Control - Part II Extensions and interpretations , 1987, Autom..

[6]  Oussama Khatib,et al.  The explicit dynamic model and inertial parameters of the PUMA 560 arm , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[7]  Peng-Yung Woo,et al.  Application of fuzzy logic to robotic control , 1996, Proceedings of the 1996 IEEE IECON. 22nd International Conference on Industrial Electronics, Control, and Instrumentation.

[8]  David W. Clarke,et al.  Generalized predictive control - Part I. The basic algorithm , 1987, Autom..

[9]  M. H. Hamza.  Intelligent systems and control : proceedings of the IASTED International Conference, October 28-30, 1999, Santa Barbara, California, USA , 1999 .

[10]  Azim Eskandarian,et al.  Dynamics modeling of robotic manipulators using an artificial neural network , 1994, J. Field Robotics.

[11]  Shuzhi Sam Ge,et al.  Adaptive neural network control of robot manipulators in task space , 1997, IEEE Trans. Ind. Electron..

[12]  Homayoun Seraji,et al.  Configuration control of redundant manipulators: theory and implementation , 1989, IEEE Trans. Robotics Autom..

[13]  Cemil Oz,et al.  Effects of the Trajectory Planning on the Model Based Predictive Robotic Manipulator Control , 2003, ISCIS.

[14]  William M. Silver.  On the Equivalence of Lagrangian and Newton-Euler Dynamics for Manipulators , 1982 .

[15]  M. Sekiguchi,et al.  A neural network model of the cerebellum performing dynamic control of a robotic manipulator by learning , 1993 .

[16]  C. S. George Lee,et al.  Robot Arm Kinematics, Dynamics, and Control , 1982, Computer.

[17]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .