Neural Network for Structural Dynamic Model Identification
Publication: Journal of Engineering Mechanics
Volume 121, Issue 12
Abstract
The identification and modeling of linear and nonlinear dynamic systems through the use of measured experimental data is a problem of considerable importance in engineering. Among the identification methods, the artificial neural network is a newly developed technique. Due to its attributes, such as parallelism, adaptability, robustness, and the inherent ability to handle nonlinearity, artificial neural networks have shown great promise in function mapping, pattern recognition, image processing, and so on. However, dynamic function mapping, including the structural dynamic model identification, is still a challenging topic in neural network applications. A neural network approach for structural dynamic model identification is presented in this paper. The neural network is trained, tested, and verified by using the responses recorded in a real apartment building during earthquakes. The results show that the dynamic behaviors of the building can be very well modeled by the trained neural network. The results also indicate the great potential of using neural networks in structural dynamic model identification.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Albus, J.(1975). “A new approach to manipulator control: the cerebeller model articulation control.”J. Dynamics, Systems, Measurements and Control, 97, 220–227.
2.
Barto, A. G., Sutton, R., and Anderson, C. (1993). “Neuronlike elements that can solve difficult learning control problem.”IEEE Trans. System, Man and Cybernetics, 15(5).
3.
Bhat, N. V., and McAvoy, T. J. (1989). “Use of neural nets for dynamic modeling and control of chemical process systems.”Proc., Am. Control Conf., Pittsburgh, Pa., 1336–1341.
4.
Billings, S., and Chen, S. (1992). “Chapter 9: Neural networks and system identification.”Neural networks for control and systems, K. Warivick, G. W. Irwin, and K. J. Hunt, eds., 181–205.
5.
Chassiakos, A. G., Kosmatopoulos, E. B., and Christodoulou, M. A. (1991). “Identification of robot dynamics by neural networks with dynamic neurons.”Proc., Workshop on Neural Networks in Robotics, Oct.
6.
Chu, S. R., Shoureshi, R., and Tenorio, M. (1990). “Neural networks for system identification.”IEEE Control Systems Magazine, Apr., 31–34.
7.
Cybenko, G.(1989). “Approximation by superpositions of a sigmoidal functions.”Mathematics of Control, Signals and Systems, 2, 303–314.
8.
Hopfield, J. J. (1979). “Neural networks and physical system with emergent collective computational abilities.”Proc., Nat. Academy Sci., 2554–2558.
9.
Kosmatopoulos, E. B., Chassiakos, A. G., and Christodoulou, M. A. (1991). “Identification of robot dynamics by neural networks.”IEEE 30th Conf. on Des. and Control, IEEE, New York, N.Y.
10.
Liu, S. C., and Yao, J. T. P.(1978). “Structural identification concept.”J. Struct. Div., ASCE, 104(12), 1845–1858.
11.
Ljung, L., and Soderstorm, T. (1983). Theory and practice of recursive identification, MIT Press, Cambridge, Mass.
12.
Masri, S. F., Chassiakos, A. G., and Caughey, T. K.(1992). “Structure-unknown nonlinear dynamic systems: Identification through neural networks.”Smart Struct., 1, 45–56.
13.
Masri, S. F., Chassiakos, A. G., and Caughey, T. K.(1993). “Identification of nonlinear dynamic systems using neural networks.”J. Appl. Mech., 60, 123–133.
14.
“Morgan Hill earthquake of April 24, 1984.” (1984). Tape: MORGANHILL84-S, Structure-Response Records, California Dept. of Conservation, Div. of Mines and Geol., Office of Strong Motion Studies, Calif.
15.
“Mt. Lewis earthquake of March 31, 1986.” (1986). Tape: MTLEWIS86, Structure-Response Records, California Dept. of Conservation, Div. of Mines and Geol., Office of Strong Motion Studies, Calif.
16.
Narendra, K. S., and Parthasarathy, K.(1990). “Identification and control of dynamical system using neural networks.”IEEE Trans. on Neural Networks, 1, 4–27.
17.
Nisar, A., and Werner, S. D.(1992). “Assessment of UBC seismic design provisions using recorded building motions.”Proc., Tenth Earthquake Engrg. Conf., 13, 5723–5728.
18.
Qi, G. Z., Yang, J. C. S., and Kan, C. D. (1990). “A new system identification technique for on-line nondestructive evaluation.”Intelligent Structure, K. P. Chong, S. C. Liu, and J. C. Li, eds., Elsever Applied Science, New York, N.Y., 368–376.
19.
Rumelhart, D. E., and McClelland, J. L. (1986). Parallel distributed processing, Vol. 1: Foundations . MIT Press, Cambridge, Mass.
20.
“San Jose—10-story residential bldg., Loma Prieta earthquake of 17 October, 1989.” (1989). Strong-Motion Data, CSMIP, California Dept. on Conservation, Div. of Mines and Geol., Office of Strong Motion Studies, Calif.
21.
Shinozuka, M., and Deodatis, G.(1991). “Simulation of stochastic processes by spectral representation.”Appl. Mech. Rev., 44(4), 191–203.
22.
Shinozuka, M.(1993). “Summary—distribution systems.”Appl. Mech. Rev., 46(5), 187–195.
23.
Udwadia, F. E.(1987). “Response of uncertain dynamic system I & II.”Appl. Mathematics and Computation, 22, 115–187.
24.
Werbos, P. (1988). “Backpropagation: past and future.”Proc., IEEE Int. Conf. on Neural Networks, Vol. 1, IEEE, New York, N.Y., 343–353.
25.
Werbos, P. (1990). “Chapter 22: Neurocontrol and related techniques.”Handbook of neural computing application, A. J. Maren, ed., Academic Press, New York, N.Y., 345.
26.
Werbos, P. (1992). “Neurocontrol and supervised learning: an overview and evaluation.”Handbook of intelligent control. Van Nostrand Reinhold, New York, N.Y., 65–89.
Information & Authors
Information
Published In
Copyright
Copyright © 1995 American Society of Civil Engineers.
History
Published online: Dec 1, 1995
Published in print: Dec 1995
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.