Nonlinear Structural Control Using Neural Networks
Publication: Journal of Engineering Mechanics
Volume 124, Issue 3
Abstract
Recently, Ghaboussi and Joghataie presented a structural control method using neural networks, in which a neurocontroller was developed and applied for linear structural control when the response of the structure remained within the linearly elastic range. One of the advantages of the neural networks is that they can learn nonlinear as well as linear control tasks. In this paper, we study the application of the previously developed neurocontrol method in nonlinear structural control problems. First, we study the capabilities of the linearly trained neurocontrollers in nonlinear structural control. Next, we train a neurocontroller on the nonlinear data and study its capabilities. These studies are done through numerical simulations, on models of a three-story steel frame structure. The control is implemented through an actuator and tendon system in the first floor. The sensor is assumed to be a single accelerometer on the first floor. The acceleration of the first floor as well as the ground acceleration are used as feedback. In the numerical simulations we have considered the actuator dynamics and used a coupled model of the actuator-structure system. A realistic sampling period and an inherent time delay in the control loop have been used.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Ash, T. (1989). “Dynamics node creation in backpropagation networks.”ICS Rep. 8901, Inst. for Cognitive Sci., Univ. of California, San Diego, Calif.
2.
Baber, T. T., and Wen, Y. K.(1981). “Random vibration of hysteretic degrading systems.”J. Engrg. Mech. Div., ASCE, 107(6), 1069–1087.
3.
Bani-Hani, K., and Ghaboussi, J. (1997). “Neural networks for structural control of a benchmark problem, active tendon system.” Special Issue of a Benchmark Comparison, J. Earthquake Engrg. and Struct. Dyn.
4.
Chen, H. M., Tsai, K. H., Qi, G. Z., and Yang, J. C. S.(1995). “Neural network for structural control.”J. Computing in Civil Engrg., ASCE, 9(2), 168–176.
5.
Demeter, G. F., and Lee, C. “Inelastic response of variable stiffness members under cyclic loading.”J. Engrg. Mech., ASCE, 118(7), 1406–1422.
6.
Desilva, C. W. (1989). Control sensors and actuators. Prentice-Hall, Inc., Englewood Cliffs, N.J.
7.
Dyke, S. J., Spencer, B. F., Quast, B., and Sain, M. K.(1995). “The role of control—structure interaction in protective system design.”J. Engrg. Mech., ASCE, 121(2), 322–338.
8.
Enrico, S., Ciampi, V., and Filippou, F. C. (1992). “A beam element for seismic damage analysis.”Rep. No. UCB/EERC-92/07, Earthquake Engrg. Res. Ctr., Univ. of California, Berkeley, Richmond, Calif.
9.
Fahlman, S. E. (1988). “Faster learning variations on error backpropagation: an empirical study.”Proc. of the 1988 Connectionist Models Summer School, Morgan Kaufmann Publishers, Inc., Los Altos, Calif., 38–51.
10.
Ghaboussi, J. (1994). “Some applications of neural networks in structural engineering.”Proc., Structures Congress '94, ASCE, Atlanta, Ga.
11.
Ghaboussi, J., and Joghataie, A.(1995). “Active control of structures using neural networks.”J. Engrg. Mech., ASCE, 121(4), 555–567.
12.
Gullion, M. (1969). Hydraulic servo systems. Butterworth's, London.
13.
Joghataie, A., and Ghaboussi, J. (1994). “Neural networks and fuzzy logic in structural control.”Proc. of First World Conf. on Struct. Control, IASC, Los Angeles, Calif.
14.
Joghataie, A., Ghaboussi, J., and Wu, X. (1995). “Learning and architecture determination through automatic node generation.”Proc., Int. Conf. on Artificial Neural Networks in Engrg., ASME Press, New York, N.Y.
15.
Masri, S. F., Bekey, G. A., and Caughey, T. K. (1981). “Optimum pulse control of flexible structures.”J. Appl. Mech., 48(September), 617–626.
16.
Masri, S. F., Bekey, G. A., and Caughey, T. K. (1982). “On-line control of nonlinear flexible structures.”J. Appl. Mech., 49(December), 871–884.
17.
Miller, R. K., Masri, S. F., Dehghanyar, T., and Caughey, T. K.(1988). “Active vibration control of large civil structures.”J. Engrg. Mech., ASCE, 114(9), 1542–1570.
18.
Nikzad, K., and Ghaboussi, J. (1991). “Application of multi-layered feedforward neural networks in digital vibration control.”Proc., of the Int. Joint Conf. on Neural Networks, II-A1004, IEEE, Inc., New York, N.Y.
19.
Nikzad, K., Ghaboussi, J., and Paul, S.(1996). “A study of actuator dynamics and delay compensation using neuro-controllers.”J. Engrg. Mech., ASCE, 122(10), 966–975.
20.
Pantelides, C. P., and Nelson, P. A.(1995). “Continuous pulse control of structures with material non-linearity.”Earthquake Engrg. and Struct. Dyn., 24(2), 263–282.
21.
Reinhorn, A. M., Manolis, A. M., and Wen, C. Y.(1987). “Active control of inelastic structures.”J. Engrg. Mech., ASCE, 113(3), 315–333.
22.
Soong, T. T., Reinhorn, A. M., and Yang, J. N. (1987). “A standardized model for structural control experiments and some experimental results.”Proc. of the 2nd Int. Symp. on Struct. Control, Martinus Nijhoff Publishers, Amsterdam, The Netherlands.
23.
Wen, Y. K.(1989). “Method for random vibration for inelastic structures.”J. Appl. Mech. Div., 42(2), 39–52.
24.
Wilson, E. L., Farhoomand, I., and Bathe, K. J.(1972). “Nonlinear dynamic analysis of complex structures.”Int. J. Earthquake Engrg. and Struct. Dyn., 1(2), 241–252.
25.
Yang, J. N., Li, Z., and Vongchavalkal, S.(1994a). “Generalization of optimal control theory: linear and nonlinear control.”J. Engrg. Mech., ASCE, 120(2), 266–283.
26.
Yang, J. N., Li, Z., Wu, J. C., and Hsu, I. R.(1994b). “Control of sliding-isolated buildings using dynamics linearization.”Engrg. Struct., 16(6), 437–444.
27.
Yang, J. N., Long, F. X., and Wong, D.(1988). “Optimal control of nonlinear structures.”J. Appl. Mech., 55(4), 931–938.
Information & Authors
Information
Published In
Copyright
Copyright © 1998 American Society of Civil Engineers.
History
Published online: Mar 1, 1998
Published in print: Mar 1998
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.