Assessing small failure probabilities by combined subset simulation and Support Vector Machines

被引:338
|
作者
Bourinet, J-M. [1 ]
Deheeger, F. [1 ,2 ]
Lemaire, M. [1 ,2 ]
机构
[1] Clermont Univ, IFMA, EA 3867, Lab Mecan & Ingn, F-63000 Clermont Ferrand, France
[2] Phimeca Engn, F-63800 Cournon Dauvergne, France
关键词
Reliability; Subset simulation; Support Vector Machine; Active learning; RELIABILITY ESTIMATION; DIMENSIONS;
D O I
10.1016/j.strusafe.2011.06.001
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Estimating small probabilities of failure remains quite a challenging task in structural reliability when models are computationally demanding. FORM/SORM are very suitable solutions when applicable but, due to their inherent assumptions, they sometimes lead to incorrect results for problems involving for instance multiple design points and/or nonsmooth failure domains. Recourse to simulation methods could therefore be the only viable solution for these kinds of problems. However, a major shortcoming of simulation methods is that they require a large number of calls to the structural model, which may be prohibitive for industrial applications. This paper presents a new approach for estimating small failure probabilities by considering subset simulation proposed by S.-K. Au and J. Beck from the point of view of Support Vector Machine (SVM) classification. This approach referred as (2)SMART ("Two SMART') is detailed and its efficiency, accuracy and robustness are assessed on three representative examples. A specific attention is paid to series system reliability and problems involving moderately large numbers of random variables. (C) 2011 Elsevier Ltd. All rights reserved.
引用
收藏
页码:343 / 353
页数:11
相关论文
共 50 条
  • [11] Estimating accurate multi-class probabilities with Support Vector Machines
    Milgram, J
    Cheriet, M
    Sabourin, R
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), VOLS 1-5, 2005, : 1906 - 1911
  • [12] Feature subset selection for support vector machines using confident margin
    Kugler, M
    Aoki, K
    Kuroyanagi, S
    Iwata, A
    Nugroho, AS
    Proceedings of the International Joint Conference on Neural Networks (IJCNN), Vols 1-5, 2005, : 907 - 912
  • [13] Combined outputs framework for twin support vector machines
    Shao, Yuan-Hai
    Hua, Xiang-Yu
    Liu, Li-Ming
    Yang, Zhi-Min
    Deng, Nai-Yang
    APPLIED INTELLIGENCE, 2015, 43 (02) : 424 - 438
  • [14] Combined outputs framework for twin support vector machines
    Yuan-Hai Shao
    Xiang-Yu Hua
    Li-Ming Liu
    Zhi-Min Yang
    Nai-Yang Deng
    Applied Intelligence, 2015, 43 : 424 - 438
  • [15] Adaptive Kriging-based probabilistic subset simulation method for structural reliability problems with small failure probabilities
    Wang, Tianzhe
    Chen, Zequan
    Li, Guofa
    He, Jialong
    Shi, Rundong
    Liu, Chao
    STRUCTURES, 2024, 70
  • [16] Asymptotic subset simulation: An efficient extrapolation tool for small probabilities approximation
    Rashki, Mohsen
    Faes, Matthias G. R.
    Wei, Pengfei
    Song, Jingwen
    RELIABILITY ENGINEERING & SYSTEM SAFETY, 2025, 260
  • [17] Design and simulation of support vector machines generalized observer
    School of Chemical Engineering and Environment, Beijing Institute of Technology, Beijing 100081, China
    不详
    Shiyou Hiagong Gaodeng Xuexiao Xuebao, 2008, 4 (95-98):
  • [18] Stock Market Simulation Using Support Vector Machines
    Rosillo, Rafael
    Giner, Javier
    De la Fuente, David
    JOURNAL OF FORECASTING, 2014, 33 (06) : 488 - 500
  • [19] Feature subset selection for support vector machines by incremental regularized risk minimization
    Fröhlich, H
    Zell, A
    2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2004, : 2041 - 2045
  • [20] Towards optimal descriptor subset selection with support vector machines in classification and regression
    Fröhlich, H
    Wegner, JK
    Zell, A
    QSAR & COMBINATORIAL SCIENCE, 2004, 23 (05): : 311 - 318