The magnetorheological (MR) damper is a newly developed semiactive control device that possesses unique advantages such as low power requirement and adequately fast response rate. The device has been previously tested in a laboratory to determine its dynamic properties and characterized by a system of nonlinear differential equations. This paper presents an alternative representation of the damper in terms of a multilayer perceptron neural network. A neural network model with 6 input neurons, one output neuron and twelve neurons in the hidden layer is used to simulate the dynamic behavior of the MR damper. Training of the model is done by a Gauss-Newton based Levenberg-Marquardt method using data generated from the numerical simulation of the nonlinear differential equations. An optimal brain surgeon strategy is adopted to prune the weights and optimize the neural networks. An optimal neural network is presented that satisfactorily represents dynamic behavior of the MR damper.
Get full access to this article
View all access options for this article.
References
1.
1. Shulman, Z. P. and Kordonsky, W. I."Structural, Physical Properties and Dynamics of Magnetorheological Suspensions."International Journal of Multiphase Flow, 12(6), 935-955, 1986.
2.
2. Kordonsky, W. I. and Shulman, Z. P."Physical Properties of Magnetizable Structure-Reversible Media."Journal of Magnetism and Magnetic Materials, 85, 114-120, 1990.
3.
3. Kordonsky, W. I."Elements and Devices Based on Magnetorheological Effect."Journal of Intelligent Material Systems and Structures, 4, 65-69, 1993.
4.
4. Carlson, J. D. and Weiss, K. D. "Magnetorheological Materials Based on Alloy Particles." U.S. Patent 5, 382-373, 1995.
5.
5. Ginder, J. M. and Davis, L. C."Shear Stresses in Magnetorheological Fluids: Role of Magnetic Saturation."Applied Physics Letters, 65,3410-3410. 1994.
6.
6. Kordonsky, W. I. and Demchuk, S. A."Additional Magnet Dispersed Phase Improves the MR-Fluid Properties."Journal of Intelligent Material Systems and Structures, 7, 522-525,1996.
7.
7. Carlson, J. D."Magnetorheological Fluid Actuators."Adaptronics and Smart Structures, Ed. by D. J. Jendritza and H. Janocha, Springer Verlag, 1997.
8.
8. Spencer Jr., B. F., Dyke, S. J., Sain, M. K. and Carlson, J. D."Phenomenological Model for Magnetorheological Dampers."Journal of Engineering Mechanics, ASCE, 123(3), 230-238, 1997.
9.
9. Dyke, S. J., Spencer Jr., B. F., Sain, M. K. and Carlson, J. D."Modeling and Control of Magnetorheological Dampers for Seismic Response Reduction."Smart Materials and Structures, 5,565-575, 1996.
10.
10. Dyke, S. J., Spencer Jr., B. F., Sain, M. K. and Carlson, J. D."Experimental Verification of Semi-Active Structural Control Strategies Using Acceleration Feedback."Proceedings of the Third International Conference on Motion and Vibration Control, Vol. 111, 291-296, 1996.
11.
11. Hansen, B. C., Gordaninejad, F., Saiidi, M. and Chang, F. K."Control of Bridges Using Magneto-Rheological Fluid Dampers."Proceedings of the First World Conference on Structural Control, Vol. 2, 81-90, 1994.
12.
12. Spencer Jr., B. F., Yang, G., Carlson, J. D. and Sain, M. K."Smart Dampers for Seismic Protection of Structures: A Full-Scale Study."Proceedings of the Second World Conference on Structural Control, Kyoto, Japan, June 18-July 1, 1998.
13.
13. Burton, S. A., Makris, N., Konstantopoulos, I. and Antsaklis, P. J."Modeling the Response of ER Damper: Phenomenology and Emulation."Journal of Engineering Mechanics, 122(9), Sept. 1996, 897-906.
14.
14. Goggio, T. and Girosi, F."Networks for Approximation and Learning."Proceedings of IEEE, 78, 1481-1497, 1990.
15.
15.Girosi, F. and Poggio, T."Neural Networks and the Best Approximation Property."Biological Cybernetics, 63, 169-176, 1990.
16.
16. Narendra, K. S. and Parthasasathy, K."Identification and Control of Dynamical Systems Using Neural Networks."IEEE Translations on Neural Networks, 1,4-27,1990.
17.
17. Cybenko, G."Approximation by Superpositions of a Sigmoidal Function."Mathematics Control Signal Systems, 2, 304-314, 1989.
18.
18. Ghaboussi, J. and Joghataie, A."Active Control of Structures Using Neural Networks."Journal of Engineering Mechanics, ASCE, 121(4), 555-567, 1995.
19.
19. Hassibi, B. and Stork, D. G."Second Order Derivatives for Network Pruning: Optimal Brain Surgeon," NIPS 5, Eds. S. J. Hanson et al., 164, San Mateo, Morgan Kaufmann, 1993.
20.
20. Hansen, L. K. and Pedersen, M. W."Controlled Growth of Cascade Correlation Nets."Proceedings ofICANN'94, Sorrento, Italy, Eds. M. Marinaro and P. G. Morasso, 797-800, 1994.
21.
21. Jacobs, R. A."Increased Rates of Convergence Through Learning Rate Adaptation."Neural Networks, 1,295-307, 1988.
22.
22. Rumelhart, D. E. and McClelland, J. L."Parallel Distributed Processing: Explorations in Microstructure of Cognition, 1: Foundations."MIT Press, Cambridge, MA, 1986.
23.
23. Soderstrom, T. and Stoica, P.System Identification, Prentice Hall, New York, 1989.
24.
24. Ljung, L.System Identification-Theoryfor the User, Prentice Hall, New York, 1987.
25.
25. Fletcher, R.Practical Methods of Optimization, John Wiley, New York, 1987.
26.
26. N0rgaard, M."Neural Network Based System Identification Toolbox." Technical Report 95-E-773, Department of Automation, Technical University of Denmark, Lyngby, Denmark.
27.
27. Demuth, H. and Beale, M."Neural Network Toolbox."The Mathworks, Inc., 1993.
28.
28. Sjoberg, J., Hjalmarsson, H. and Ljung, L."Neural Networks in System Identification."Preprints 10th IFAC Symposium on SYSID, Copenhagen, Denmark, Vol. 2, pp. 49-71, 1994.
29.
29. Hannan, E. J. and Krishnaiah, P. R."The Determination of the Order of an Autoregression,"Journal of the Royal Statistical Society, Series B, Vol. 41, 713-723, 1979.
30.
30. He, X. and Asada, H."A New Method for Identifying Orders of Input-Output Models for Nonlinear Dynamic Systems."Proceedings of the American Control Conference, San Francisco, California, 1993.
