0
TECHNICAL PAPERS

Robust Adaptive Neural Estimation of Restoring Forces in Nonlinear Structures

[+] Author and Article Information
E. B. Kosmatopoulos

School of Engineering, University of Southern California, Los Angeles, CA 90089-2563

A. W. Smyth

School of Engineering and Applied Science, Columbia University, New York, NY 10027-6699

S. F. Masri

School of Engineering, University of Southern California, Los Angeles, CA 90089-2531

A. G. Chassiakos

School of Engineering, California State University, Long Beach, CA 90840-5602

J. Appl. Mech 68(6), 880-893 (Jun 08, 2001) (14 pages) doi:10.1115/1.1408614 History: Received May 04, 2000; Revised June 08, 2001
Copyright © 2001 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
General structural system, with discrete response measurement locations. The system can experience force excitation, and multiple support motions.
Grahic Jump Location
Three-degree-of-freedom structural system, with discrete response measurement locations. The system can experience force excitation, and multiple support motions.
Grahic Jump Location
Block diagram of the Volterra Wiener neural network (VWNN)
Grahic Jump Location
Three-degree-of-freedom base excited structural system, with discrete response measurement locations
Grahic Jump Location
Time-history of actual (solid curve) and estimated (dashed curve) restoring forces when adaptation is on
Grahic Jump Location
Time-history of actual (solid curve) and estimated (dashed curve) accelerations when adaptation is on
Grahic Jump Location
Actual (left subplots) and estimated (right subplots) restoring forces versus relative displacements when adaptation is on
Grahic Jump Location
Time-history of Volterra/Wiener neural network (VWNN) adjustable parameters
Grahic Jump Location
Time-history of actual (solid curve) and estimated (dashed curve) restoring forces after training for the same base acceleration as in Figs. 5–8
Grahic Jump Location
Time-history of actual (solid curve) and estimated (dashed curve) restoring forces after training for different base acceleration than that of Figs. 5678
Grahic Jump Location
Time-history of actual (solid curve) and estimated (dashed curve) restoring forces when adaptation is on, γ=0.9
Grahic Jump Location
Time-history of actual (solid curve) and estimated (dashed curve) restoring forces after training for different base acceleration than that of Figs. 11, γ=0.9
Grahic Jump Location
Concrete structure: restoring forces and their estimates during the first training iteration
Grahic Jump Location
Concrete structure: restoring forces and their estimates after training
Grahic Jump Location
Steel structure: restoring forces and their estimates during the first training iteration
Grahic Jump Location
Steel structure: restoring forces and their estimates after training

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In