Adaptive Importance Sampling

by A. Karamchandani, Dep of Civil Engineering, United States,
P. Bjerager, Dep of Civil Engineering, United States,
C. A. Cornell, Dep of Civil Engineering, United States,



Document Type: Proceeding Paper

Part of: Structural Safety and Reliability

Abstract:

An adaptive importance sampling scheme is presented which is based on the idea that as one samples, the knowledge of the failure domain increases. If one keeps modifying the importance sampling density to reflect this increasing state of knowledge, one can develop a good sampling density and estimate the failure probability efficiently. The efficiency of one such method is shown through simple component examples. Examples are also used to study the effect of factors like level of failure probabilty, non-linearity of the failure surface and number and relative importance of random variables. The method is also applied to problems that involve intersections and unions of components.

Subject Headings: Failure analysis | Structural reliability | Structural analysis | System reliability | Probability | Structural systems | Adaptive systems

Services: Buy this book/Buy this article

 

Return to search