Sage Journals: Discover world-class research

Abstract

This paper discusses a neural-network controller used to reduce the seismic response of building structures. The training process is carried out through a novel gradient-search technique that minimizes a desired cost function defined in terms of a set of structural response quantities. The proposed training approach does not require an additional neural network for the identification of the structural system. The training method is quite flexible with regard to the choice of the cost function to be minimized. A series of earthquake, base-acceleration time histories are considered to train the network. The effectiveness of the controller is demonstrated through several sets of numerical results obtained for a multistory building equipped with an active tuned mass damper.

Keywords

Neural-network control cost function gradient search seismic response reduction velocity-feedback control acceleration-feedback control

Get full access to this article

View all access options for this article.

References

Bani-Han, K. , Ghaboussi,J. , and Schneider, S.P. , 1998, "Experimental study of neural network based structural control," in 6th U.S. National Conference on Earthquake Engineering, Seattle, WA.

Chen, H.M. , Tsai, K.H. , Qi, G.Z. , Yang, J.C.S. , and Amini, F. , 1995, "Neural networks for structure control," Journal of Computing in Civil Engineering 9(2), 168-176.

Faravelli, L. and Venini, P. , 1994, "Active structural control by neural networks," Journal of Structural Control 1( 1-2), 79-101.

Haykin S. , 1994, Neural Networks: A Comprehensive Foundation, Macmillan College, New York.

He, Y-A. and Wu, J. , 1998, "Control of structural seismic response by self-recurrent neural network," Earthquake Engineering and Structural Dynamics 27, 641-648.

Joghataie, A. and Ghaboussi, J. , 1996, "A comparative study of learning methods and mathematical algorithms in structural control," in 11 th World Conference on Earthquake Engineering, Acapulco, Mexico, paper No. 1432.

Liut, D.A. , 1999, Neural-Network and Fuzzy-Logic Learningand Control of Linear and Nonlinear Dynamic Systems, Ph.D. dissertation, Virginia Polytechnic Institute and State University, Blacksburg, VA.

Liut, D.A. , Matheu, E.E. , Singh, M.P. , and Mook, D.T. , 1999, "An efficient training technique for a neural-network controller for seismically excited structures," in 17th International Modal Analysis Conference (IMAC 99), Orlando, FL, February 8-11, pp. 1813-1819.

Liut, D.A. , Mook, D.T. , VanLandingham, H.F. , and Nayfeh, A.H. , 1998, "Control of rolling in ships by means of active fins," in International Mechanical Engineering Congress, Anaheim, CA.

10.

Narendra, K.S. and Parthasarathy, K. , 1990, "Identification and control of dynamical systems using neural networks," IEEE Transactions on Neural Networks 1(1),4-27.

11.

Nguyen, D.H. and Widrow, B. , 1990, "Neural networks for self-learning control systems ," IEEE Control Systems Magazine, April, pp. 18-23.

12.

Rumelhart, D.E. , Hinton, G.E. , and Williams, R.J. , 1986, "Learning representations by back-propagation errors ," Nature (London)323, 533-536.

A Modified Gradient-Search Training Technique for Neural-Network Structural Control

Abstract

Keywords

Get full access to this article

References