Computational & Technology Resources
an online resource for computational,
engineering & technology publications
PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON SOFT COMPUTING TECHNOLOGY IN CIVIL, STRUCTURAL AND ENVIRONMENTAL ENGINEERING
Edited by: Y. Tsompanakis, J. Kruis and B.H.V. Topping
Double-Loop Optimization and Soft Computing Based Inverse Analysis Approaches for Performing Reliability-based Design
D. Lehký, O. Slowik and D. Novák
Institute of Structural Mechanics, Brno University of Technology, Czech Republic
D. Lehký, O. Slowik, D. Novák, "Double-Loop Optimization and Soft Computing Based Inverse Analysis Approaches for Performing Reliability-based Design", in Y. Tsompanakis, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Fourth International Conference on Soft Computing Technology in Civil, Structural and Environmental Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 6, 2015. doi:10.4203/ccp.109.6
Keywords: inverse reliability problem, artificial neural network, double-loop reliability-based optimization, latin hypercube sampling, first order reliability method.
Two alternative approaches to solve an inverse reliability problem are presented in this paper. The first approach is based on utilization of an artificial neural network and small-sample simulation technique. The second approach considers the inverse reliability task as a reliability-based optimization task using a double-loop optimization method based on a small-sample simulation. The efficiency of both approaches is tested using numerical examples of structural design. Advantages and disadvantages of both approaches are discussed.
purchase the full-text of this paper (price £20)