Iterative Algorithm for Structure Reliability Analysis Based on Support Vector Classification Method

Abstract:

For reliability analysis of structure with implicit limit state function, an iterative algorithm is presented on the basis of support vector classification machine. In the present method, the support vector classification machine is employed to construct surrogate of the implicit limit state function. By use of the proposed rational iteration and sampling procedure, the constructed support vector classification machine can converge to the actual limit state function at the important region, which contributes to the failure probability significantly. Then the precision of the reliability analysis is improved. The implementation of the presented method is given in detail, and the feasibility and the efficiency are demonstrated by the illustrations.

• Periodical: Key Engineering Materials (Volumes 353-358)
• Pages: 1009-1012
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.353-358.1009
• Online since: September 2007
• Authors: Chao Ma, Zhen Zhou Lu
• Keywords: Implicit Limit State Function, Structural Reliability, Support Vector Machine (SVM)

References

[1] S. H. Kim, S.W. Na: Struct. Safety. Vol. 19 (1997), p.3.

[2] J. Deng, D. S. Gu, X.B. Li: Struct. Safety. Vol. 27 (2005), p.25.

[3] I. Kaymaz: Struct. Safety. Vol. 27 (2005), p.133.

[4] J.E. Hurtado: Struct. Safety. Vol. 26 (2004), p.271.

[5] V.N. Vapnik: The Nature of Statistical Learning Theory ( Springer-Verlag, New York 1995).

[6] C.M. Rocco, J.A. Moreno: Reliab. Eng. Syst. Safety Vol. 76 (2002), p.237.

[7] J.E. Hurtado, D.A. Alvarez: J. Struct. Eng. Vol. 129 (2003), p.1141.