Neural Networks for Multiobjective Adaptive Structural Control
Publication: Journal of Structural Engineering
Volume 127, Issue 2
Abstract
The concept of using neural networks to predict future values of constrained performance variables as part of an adaptive structural controller is proposed. Neural networks are first trained using simulated responses and then they are used in simulations with input disturbances having different frequency contents. Because of this, as well as other factors, one or more prespecified constraints may be violated. The neural networks are designed to permit predictions of these unsafe vibration levels, stresses, actuator saturations, etc., before they can occur. To prevent their occurrence, the control laws may be adaptively tuned, maximizing safety and reliability. To illustrate the proposed methodology, numerical examples are shown using linear quadratic Gaussian control of a simple example three-story building model subjected to earthquake excitation, with an active brace used for control. Elman neural networks are chosen, filtered white noise is used as the input disturbance for training, and actual earthquake records are used as input disturbances for testing the neural networks and finally the adaptive controller.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Ankireddi, S., and Yang, H. T. Y. (1997). “Multiple objective LQC control of wind-excited buildings.”J. Struct. Engrg., ASCE, 123(7), 943–951.
2.
Ankireddi, S., and Yang, H. T. Y. (1999). “Neural networks for sensor fault correction in structural control.”J. Struct. Engrg., ASCE, 125(9), 1056–1064.
3.
Brown, A. S. ( 2000). “Multiobjective civil structural control incorporating neural networks.” PhD thesis, University of California at Santa Barbara, Calif.
4.
Brown, A. S., Ankireddi, S., and Yang, H. T. Y. (1999). “Actuator and sensor placement for multiobjective control of structures.”J. Struct. Engrg., ASCE, 125(7), 757–765.
5.
Chen, H. M., Tsai, K. H., Qi, G. Z., Yang, J. C. S., and Amini, F. (1995). “Neural network for structure control.”J. Comp. in Civ. Engrg., ASCE, 9(2), 168–176.
6.
Demuth, H., and Beale, M. ( 1995). Neural network toolbox for use with Matlab user's guide, The MathWorks, Inc., Natick, Mass.
7.
Dorey, A. P., and Moore, J. H. ( 1995). Advances in actuators, Institute of Physics Publishing.
8.
Elman, J. L. ( 1990). “Finding structure in time.” Cognitive Sci., 14(2), 179–211.
9.
Ghaboussi, J., and Joghataie, A. (1995). “Active control of structures using neural networks.”J. Engrg. Mech., ASCE, 121(4), 555–567.
10.
Koike, Y., et al. ( 1998). “Application of V-shaped hybrid mass damper to high-rise buildings and verification of damper performance.” Struct. Engrg. Worldwide 1998 Proc., Struct. Engrs. World Congr., Elsevier Science, New York.
11.
Rodellar, J., Chung, L. L., Soong, T. T., and Reinhorn, A. M. (1989). “Experimental digital control of structures.”J. Engrg. Mech., ASCE, 115(6), 1245–1261.
12.
Samali, B., Yang, J. N., and Yeh, C. T. (1985). “Control of lateral-torsional motion of wind-excited buildings.”J. Engrg. Mech., ASCE, 111(6), 777–796.
13.
Spencer, B. F., Dyke, S. J., and Deoskar, H. S. ( 1998a). “Benchmark problems in structural control: Part I—Active mass driver system.” Earthquake Engrg. and Struct. Dynamics, 27(11), 1127–1139.
14.
Spencer, B. F., Dyke, S. J., and Deoskar, H. S. ( 1998b). “Benchmark problems in structural control: Part II—Active tendon system.” Earthquake Engrg. and Struct. Dynamics, 27(11), 1141–1147.
15.
Spencer, B. F. J., and Sain, M. K. ( 1997). “Controlling buildings: A new frontier in feedback.” IEEE Control Sys. Mag., 17(6), 19–35.
Information & Authors
Information
Published In
History
Received: Aug 20, 1999
Published online: Feb 1, 2001
Published in print: Feb 2001
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.