Effectiveness of Saliency-Based Methods in Optimization of Neural State Estimators of the Drive System With Elastic Couplings

This paper deals with the optimization problem of internal structure of neural-network (NN)-based state estimators of the drive system with elastic joints. Saliency-based optimization methods, developed in the NN theory, are tested in this paper to obtain the high-quality estimation of torsional torque and load-machine speed. The optimal brain damage and optimal brain surgeon methods are compared in this application. The state variables estimated by the optimized NN are used in feedback paths in the two-mass drive structure with a state controller. The simulation results show good accuracy of both presented neural estimators for a wide range of changes of the reference speed and the load torque. The simulation results are verified by laboratory experiments.

[1]  Peter J. B. Hancock,et al.  Pruning Neural Nets by Genetic Algorithm , 1992 .

[2]  Babak Hassibi,et al.  Second Order Derivatives for Network Pruning: Optimal Brain Surgeon , 1992, NIPS.

[3]  Gregory J. Wolff,et al.  Optimal Brain Surgeon and general network pruning , 1993, IEEE International Conference on Neural Networks.

[4]  Lars Kai Hansen,et al.  Structure learning by pruning in independent component analysis , 2008, Neurocomputing.

[5]  T. Orlowska-Kowalska,et al.  Optimization of neural state estimators of the two-mass system using OBD method , 2008, 2008 IEEE International Symposium on Industrial Electronics.

[6]  Seung-Ki Sul,et al.  Kalman filter and LQ based speed controller for torsional vibration suppression in a 2-mass motor drive system , 1995, IEEE Trans. Ind. Electron..

[7]  Yoichi Hori,et al.  Slow resonance ratio control for vibration suppression and disturbance rejection in torsional system , 1999, IEEE Trans. Ind. Electron..

[8]  Bimal K. Bose,et al.  Neural Network Applications in Power Electronics and Motor Drives—An Introduction and Perspective , 2007, IEEE Transactions on Industrial Electronics.

[9]  Ferdinand Hergert,et al.  Improving model selection by nonconvergent methods , 1993, Neural Networks.

[10]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[11]  Junji Furusho,et al.  Speed control of two-inertia system by PI/PID control , 1999, Proceedings of the IEEE 1999 International Conference on Power Electronics and Drive Systems. PEDS'99 (Cat. No.99TH8475).

[12]  Teresa Orlowska-Kowalska,et al.  Damping of Torsional Vibrations in Two-Mass System Using Adaptive Sliding Neuro-Fuzzy Approach , 2008, IEEE Transactions on Industrial Informatics.

[13]  David E. Rumelhart,et al.  BACK-PROPAGATION, WEIGHT-ELIMINATION AND TIME SERIES PREDICTION , 1991 .

[14]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[15]  Teresa Orlowska-Kowalska,et al.  Application of the OBD method for optimization of neural state variable estimators of the two-mass drive system , 2009, Neurocomputing.

[16]  Ehud D. Karnin,et al.  A simple procedure for pruning back-propagation trained neural networks , 1990, IEEE Trans. Neural Networks.

[17]  Teresa Orlowska-Kowalska,et al.  Vibration Suppression in a Two-Mass Drive System Using PI Speed Controller and Additional Feedbacks—Comparative Study , 2007, IEEE Transactions on Industrial Electronics.

[18]  Tim Andersen,et al.  Cross validation and MLP architecture selection , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

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

[20]  Teresa Orlowska-Kowalska,et al.  Neural-Network Application for Mechanical Variables Estimation of a Two-Mass Drive System , 2007, IEEE Transactions on Industrial Electronics.

[21]  Geoffrey E. Hinton.  Learning Translation Invariant Recognition in Massively Parallel Networks , 1987, PARLE.