Neural Networks for Sensor Fault Correction in Structural Control
Publication: Journal of Structural Engineering
Volume 125, Issue 9
Abstract
Two neural network architectures are proposed for use in structural control applications: a Failure Detection Neural Network and a Failure Accommodation Neural Network. The Failure Detection Network monitors structural responses and automatically detects sensor failures that can reduce control performance and effectiveness, while the Failure Accommodation Network accounts for the failed sensors. Together, the networks are a step toward development of an expert diagnostic system for structural applications. Examples of two simple structures are used to illustrate the features of the networks. Sensor failures are simulated during control operation, and the ability of the networks to detect and accommodate the failures is examined. The numerical results reveal that these networks show promise for automated intelligent fault detection, identification, classification, and accommodation, and as such may have potential use in real civil structures. Although the networks have been used to detect and account for sensor faults alone, they may also be trained for other kinds of failures. Thus, they may have potential for incorporation into an intelligent structural monitoring system.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Boyd, S. P., and Barratt, C. H. (1991). Linear controller design: Limits of performance. Prentice-Hall, Englewood Cliffs, N.J.
2.
Chen, C. W., Juang, J. N., and Huang, J. K. (1993). “Adaptive linear system identification and state estimation.” Control and dynamic systems, 57, 331–367.
3.
Chung, L. L., Lin, C. C., and Lu, H. K. (1995). “Time delay control of structures.” Earthquake Engrg. and Struct. Dyn., 24(5), 687–701.
4.
Ghaboussi, J., Garrett, J. H., and Wu, X. (1991). “Knowledge-based modeling of material behavior using neural networks.”J. Engrg. Mech., ASCE, 117(1), 132–153.
5.
Ghaboussi, J., and Joghataie, A. (1995). “Active control of structures using neural networks.”J. Engrg. Mech., ASCE, 121(4), 555–567.
6.
Ghaboussi, J., and Lin, C. J. (1998). “A new method of generating earthquake accelerograms using neural networks.” Earthquake Engrg. Struct. Dyn., 124(4), 528–532.
7.
Kazlas, P. T., Monsen, P. T., and LeBlanc, M. J. (1993). “Neural network-based helicopter gearbox health monitoring system.” Proc., IEEE Workshop on Neural Networks for Signal Processing, III, IEEE, New York, 431–440.
8.
Kramer, M. A. (1991). “Nonlinear principal component analysis using autoassociative neural networks.” AIChE J., 37(2), 233–243.
9.
Kramer, M. A. (1992). “Autoassociative neural networks.” Comp. Chem. Engrg., 16(4), 313–328.
10.
Kuczewski, R. M., and Eames, D. R. (1992). “Helicopter fault detection and classification with neural networks.” Proc., Int. Joint Conf. on Neural Networks, II, IEEE, New York, 947–956.
11.
Monsen, P. T., Dzwonczyk, P. M., and Manolakos, E. S. (1994). “Analog neural network-based helicopter gearbox health monitoring system.” J. Acoustical Soc. America, 4(2), 241–257.
12.
Monsen, P. T., Manolakos, E. S., and Dzwonczyk, M. (1993). “Helicopter gearbox fault detection and diagnosis using analog neural networks.” Proc., 27th Asilomar Conf. on Signals, Sys. and Comp., I, IEEE Comput. Soc. Press, Los Alamitos, CA, 381–385.
13.
Napolitano, M. R., Chen, C. I., and Naylon, S. (1993). “Aircraft failure detection and identification using neural networks.” J. Guidance, Control and Dyn., ASME, 16(6), 999–1009.
14.
Nikzad, K., Ghaboussi, J., and Paul, S. L. (1996). “Actuator dynamics and delay compensation using neural networks.”J. Engrg. Mech., ASCE, 122(10), 966–975.
15.
Ogata, K. (1987). Modern control engineering, Prentice-Hall, New York.
16.
Oppenheim, A. V., and Schafer, R. W. (1989). Discrete-time signal processing. Prentice-Hall, Englewood Cliffs, N.J.
17.
Soong, T. T. (1990). Active structural control: Theory and practice. Longman's, New York.
18.
Widrow, B., and Lehr, M. A. (1990). “30 years of adaptive neural networks: Perceptron, Madaline, and Backpropagation.” Proc., IEEE, 78(9), 1415–1442.
Information & Authors
Information
Published In
Journal of Structural Engineering
Volume 125 • Issue 9 • September 1999
Pages: 1056 - 1064
History
Received: Aug 26, 1998
Published online: Sep 1, 1999
Published in print: Sep 1999
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.