Position estimation for timing belt drives of precision machinery using structured neural networks

Abstract This paper focuses on a viable position estimation scheme for timing-belt drives using artificial neural networks. In this study, the position of a carriage (load) is calculated via a structured neural network topology accepting input from a position sensor on the actuator side of the timing belt. The paper presents a detailed discussion on the source of transmission errors. The characteristics of the error in different operation regimes are exploited to construct different network topologies. That is, a relevant neural network model is developed by the sketchy guidance of a priori knowledge on the process. The resulting structured neural network is shown to estimate the error of the carriage quite accurately whereas generic recurrent neural networks fail to capture the dynamics of the system under investigation altogether. Extensive testing demonstrates the effectiveness of proposed method when the drive system is not subjected to external loads while the operating conditions such as ambient temperature and belt tensions do not deviate from the experimental conditions.

[1]  O. Nelles.  Nonlinear System Identification , 2001 .

[2]  Ralph Kennel,et al.  Levenberg-marquardt-based OBS algorithm using adaptive pruning interval for system identification with dynamic neural networks , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[3]  Weiping Li,et al.  Modeling and control of a belt-drive positioning table , 1996, Proceedings of the 1996 IEEE IECON. 22nd International Conference on Industrial Electronics, Control, and Instrumentation.

[4]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[5]  Robert D. Lorenz,et al.  General Methodologies for Neural Network Programming , 2002 .

[6]  Eric B. Baum,et al.  Neural net algorithms that learn in polynomial time from examples and queries , 1991, IEEE Trans. Neural Networks.

[7]  Yonghong Tan,et al.  Diagonal recurrent neural network with modified backlash operators for modeling of rate-dependent hysteresis in piezoelectric actuators , 2008 .

[8]  Yonghong Tan,et al.  Modeling Hysteresis and Its Inverse Model Using Neural Networks Based on Expanded Input Space Method , 2008, IEEE Transactions on Control Systems Technology.

[9]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[10]  Ronald L. Rivest,et al.  Training a 3-node neural network is NP-complete , 1988, COLT '88.

[11]  Musa Jouaneh,et al.  Nonlinear Control of a Belt Driven Two-Axis Positioning System , 2008 .

[12]  R. D. Lorenz,et al.  A structure by which a recurrent neural network can approximate a nonlinear dynamic system , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[13]  Gregory D. Buckner,et al.  Modeling piezoelectric actuators with Hysteretic Recurrent Neural Networks , 2010 .

[14]  Melik Dolen,et al.  Novel position estimators for timing belt drivers , 2007 .

[15]  K. Jezernik,et al.  Improved design of VSS controller for a linear belt-driven servomechanism , 2005, IEEE/ASME Transactions on Mechatronics.

[16]  D. Schroder,et al.  Identification of a nonlinear multi stand rolling system by a structured recurrent neural network , 2000, Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy (Cat. No.00CH37129).

[17]  M. A. El-Sharkawi,et al.  Intelligent Precision Position Control of Elastic Drive Systems , 2001, IEEE Power Engineering Review.

[18]  Mayergoyz,et al.  Mathematical models of hysteresis. , 1986, Physical review letters.

[19]  Masanori Kagotani,et al.  Transmission Error in Helical Timing Belt Drives (Case of a Period of Pulley Pitch) , 2001 .

[20]  Lilong Cai,et al.  On the improvement of tracking performance of positioning tables , 1996, Proceedings of the 1996 IEEE IECON. 22nd International Conference on Industrial Electronics, Control, and Instrumentation.

[21]  Lilong Cai,et al.  Tracking control of a belt-driven position table using Fourier series based learning control scheme , 2003, IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, 2003. Proceedings. 2003.

[22]  K.J. Astrom,et al.  Revisiting the LuGre friction model , 2008, IEEE Control Systems.

[23]  Xinliang Zhang,et al.  A hybrid model for rate-dependent hysteresis in piezoelectric actuators , 2010 .

[24]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[25]  R.D. Lorenz,et al.  Neural network compensation of gear backlash hysteresis in position-controlled mechanisms , 1993, Conference Record of the 1993 IEEE Industry Applications Conference Twenty-Eighth IAS Annual Meeting.

[26]  Serge Abrate,et al.  Vibrations of belts and belt drives , 1992 .

[27]  P. Garcia,et al.  Saliency tracking-based, sensorless control of AC machines using structured neural networks , 2005, Fourtieth IAS Annual Meeting. Conference Record of the 2005 Industry Applications Conference, 2005..