OPTIMAL STRUCTURAL CONTROL USING NEURAL NETWORKS

An optimal control algorithm using neural networks is proposed. The controller neural network is trained by a training rule developed to minimize cost function. Both the linear structure and the nonlinear structure can be controlled by the proposed neurocontroller. A bilinear hysteretic model is used to simulate nonlinear structural behavior. Three main advantages of the neurocontroller can be summarized as follows. First, it can control a structure with unknown dynamics. Second, it can easily be applied to nonlinear structural control. Third, external disturbances can be considered in the optimal control. Examples show that structural vibration can be controlled successfully.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/07339399
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Kim, J-T
  • Jung, H-J
  • Lee, I-W
• Publication Date: 2000-2

Language

• English

Media Info

• Features: Appendices; Figures; References;
• Pagination: p. 201-205
• Serial:
  • Journal of Engineering Mechanics
  • Volume: 126
  • Issue Number: 2
  • Publisher: American Society of Civil Engineers
  • ISSN: 0733-9399
  • EISSN: 1943-7889
  • Serial URL: http://ascelibrary.org/journal/jenmdt

Subject/Index Terms

• TRT Terms: Algorithms; Control; Costs; Degrees of freedom; Earthquakes; Hysteresis; Machine learning; Neural networks; Optimization; Seismicity; Structures; Vibration control
• Uncontrolled Terms: Structural control
• Subject Areas: Bridges and other structures; Design; Finance; Highways; I24: Design of Bridges and Retaining Walls;

Filing Info

• Accession Number: 00783864
• Record Type: Publication
• Contract Numbers: CMS-9696241, RTA-59A169, CMS 95-00301
• Files: TRIS
• Created Date: Feb 28 2000 12:00AM