Journal
APPLIED MATHEMATICAL MODELLING
Volume 40, Issue 11-12, Pages 6105-6120Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.apm.2016.01.050
Keywords
Slope reliability; Support vector regression; Spencer's method; Probabilistic analysis; Artificial bee colony algorithm
Funding
- National Natural Science Foundation of China [51109028]
- State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology [GZ15207]
- Fundamental Research Funds for the Central Universities [DUT15LK11]
- State Scholarship Fund of China [201208210208]
Ask authors/readers for more resources
Surrogate model methods are attractive ways to improve the efficiency of Monte Carlo simulation (MCS) for structural reliability analysis. An intelligent surrogate model based method for slope system reliability analysis is presented in this study. The novel machine learning technique nu-support vector machine (nu-SVM) is adopted to establish the surrogate model to predict the factor of safety via the samples generated by Latin hypercube sampling. Global optimization algorithms particle swarm optimization and artificial bee colony algorithm are adopted to select the hyper-parameters of nu-SVM model. The applicability of the nu-SVM based surrogate model for slope system reliability analysis is tested on four examples with obvious system effects. It is found that the proposed surrogate model combined with MCS can achieve accurate system failure probability evaluation using fewer deterministic slope stability analyzes than other approaches. (C) 2016 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available