A Structural Identification Method Based on Recurrent Neural Network and Auto-Regressive and Moving Average Model

Abstract:

The work presented a structural identification method based on recurrent neural network and auto-regressive and moving average model. The proposed approach involves two steps. The first step is to build a recurrent neural network to map the complex nonlinear relation between the excitations and responses of the structure-unknown system by on-line learning . The second step is to propose a procedure to determine the modal parameters of the structure from the trained neural networks. The dynamic characteristics of the structure are directly evaluated from the weighting matrices of the trained recurrent neural network. Furthermore, a illustrative example demonstrates the feasibility of using the proposed method to identify modal parameters of structure-unknown systems.

• Periodical: Applied Mechanics and Materials (Volumes 256-259)
• Pages: 2261-2265
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.256-259.2261
• Online since: December 2012
• Authors: Jing Xu*, Xiu Li Wang
• Keywords: Auto-Regressive and Moving Average Model, Nonlinear Mapping, Recurrent Neural Networks, Structural Identification

References

[1] S. R. IBRAHIM and R. S. PAPPA, Large modal survey testing using the Ibrahim time domain identify technique, The AIAA Journal of Spacecraft and Rockets 19, 459-465,1982.

DOI: 10.2514/3.62285

[2] L. ZHANG AND H. KANDA, The algorithm and application of a new multi-input-multi-output modal parameter identification method, Shock and Vibration Bulletin, 11-17, 1988.

[3] JER-JAN JUANG, Mathematical correlation of modal parameter identification methods via system realization theory, Journal of Modal Analysis, 1, 1-18,(1987)

[4] U. KADAKAL and O. YUZUGULLU, A comparative study on the identification methods for the auto-regressive modeling from the ambient vibration records, Aoil Dynamics and Earthquake Engineering15, 45-49, 1996.

DOI: 10.1016/0267-7261(95)00022-4

[5] C. Y. Kao, Shih-Lin Hung, Detection of structural damage via free vibration responses generated by approximating artificial neural networks, Computers & Structures 81, 2631-2644, 2003.

DOI: 10.1016/s0045-7949(03)00323-7

[6] Huang CS, Structural identification from ambient vibration measurement using the multivariate AR model, Journal of Sound and Vibration 241(3),337-359,(2001)

DOI: 10.1006/jsvi.2000.3302

[7] Cybenko G. , Approximations by super positions of a sigmoid function. Math Control, Signals Systems, 2:303-14,(1989)