Share Email Print
cover

Proceedings Paper

Structural system identification based on multibranch BPNN
Author(s): Hongnan Li; Hao Yang; Dongsheng Li
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

System identification is especially important for structural health monitoring and vibration control. It is one of the critical factors to control structural vibration with high quality and evaluate whether control method can be applied or not. In this paper, a kind of multi-branch BPNN model is proposed to identify structural dynamic system. In this model, the primary factors that affect structure's dynamic response, namely structure state variables and seismic inputs, are separately treated as the branches of the model, which is expected to enhance prediction precision. The aim of identification is to make the trained model be able to accurately predict structure's future dynamic response. When the model is established, it can be trained with collected dynamic response and seismic wave data. The vibration law of the structure is deposited in the weights of the trained multi-branch BPNN model. Then the model can be used to predict structure's future dynamic response. In this paper, a numerical example is given. The analytic result turns out that the proposed identification model can accurately predict structure's future dynamic response after being trained.

Paper Details

Date Published: 29 July 2004
PDF: 8 pages
Proc. SPIE 5391, Smart Structures and Materials 2004: Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems, (29 July 2004); doi: 10.1117/12.539095
Show Author Affiliations
Hongnan Li, Dalian Univ. of Technology (China)
Hao Yang, Shenyang Architectural and Civil Engineering Institute (China)
Dongsheng Li, Dalian Univ. of Technology (China)


Published in SPIE Proceedings Vol. 5391:
Smart Structures and Materials 2004: Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems
Shih-Chi Liu, Editor(s)

© SPIE. Terms of Use
Back to Top