Response Surface Method for Reliability Analysis Based on Iteratively-Reweighted-Least-Square Extreme Learning Machines

被引：3
|
作者：
Ou, Yanjun [1 ]
Wu, Yeting [1 ]
Cheng, Jun [2 ]
Chen, Yangyang [3 ]
Zhao, Wei [1 ]
机构：
[1] Jinan Univ, Sch Mech & Construction Engn, MOE Key Lab Disaster Forecast & Control Engn, Guangzhou 510632, Peoples R China
[2] China Construction First Grp Fifth Construction Co, Beijing 100024, Peoples R China
[3] Guangzhou Univ, Earthquake Engn Res & Test Ctr, Guangzhou 510405, Peoples R China
来源：
ELECTRONICS | 2023年 / 12卷 / 07期
基金：
中国国家自然科学基金;
关键词：
iteratively reweight; least square method; extreme learning machines; reliability analysis; Monte Carlo simulation; STRUCTURAL RELIABILITY; MONTE-CARLO; VECTOR MACHINE;
D O I：
10.3390/electronics12071741
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
A response surface method for reliability analysis based on iteratively-reweighted-least-square extreme learning machines (IRLS-ELM) is explored in this paper, in which, highly nonlinear implicit performance functions of structures are approximated by the IRLS-ELM. Monte Carlo simulation is then carried out on the approximate IRLS-ELM for structural reliability analysis. Some numerical examples are given to illustrate the proposed method. The effects of parameters involved in the IRLS-ELM on accuracy in reliability analysis are respectively discussed. The results exhibit that a proper number of samples and neurons in hidden layer nodes, an appropriate regularization parameter, and the number of iterations for reweighting are of important assurance to obtain reasonable precision in estimating structural failure probability.
引用
收藏
页数：15
相关论文
共 50 条
  • [1] Iteratively reweighted least squares based learning
    Warner, BA
    Misra, M
    IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 1327 - 1331
  • [2] INCREMENTAL LOCALIZATION ALGORITHM BASED ON REGULARIZED ITERATIVELY REWEIGHTED LEAST SQUARE
    Yan, Xiaoyong
    Yang, Zhong
    Liu, Yu
    Xu, Xiaoduo
    Li, Huijun
    FOUNDATIONS OF COMPUTING AND DECISION SCIENCES, 2016, 41 (03) : 183 - 196
  • [3] Incremental localization algorithm based on regularized iteratively reweighted least square
    Yan, Xiaoyong
    Song, Aiguo
    Liu, Yu
    He, Jian
    Zhu, Ronghui
    2015 IEEE INTERNATIONAL CONFERENCE ON SMART CITY/SOCIALCOM/SUSTAINCOM (SMARTCITY), 2015, : 729 - 733
  • [4] Robust regularized extreme learning machine for regression using iteratively reweighted least squares
    Chen, Kai
    Lv, Qi
    Lu, Yao
    Dou, Yong
    NEUROCOMPUTING, 2017, 230 : 345 - 358
  • [5] A generalized moving least square–based response surface method for efficient reliability analysis of structure
    Sounak Kabasi
    Atin Roy
    Subrata Chakraborty
    Structural and Multidisciplinary Optimization, 2021, 63 : 1085 - 1097
  • [6] A generalized moving least square-based response surface method for efficient reliability analysis of structure
    Kabasi, Sounak
    Roy, Atin
    Chakraborty, Subrata
    STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2021, 63 (03) : 1085 - 1097
  • [7] Fast iteratively reweighted least squares algorithms for analysis-based sparse reconstruction
    Chen, Chen
    He, Lei
    Li, Hongsheng
    Huang, Junzhou
    MEDICAL IMAGE ANALYSIS, 2018, 49 : 141 - 152
  • [8] Total Variation Regularization Based on Iteratively Reweighted Least-Squares Method for Electrical Resistance Tomography
    Shi, Yanyan
    Rao, Zuguang
    Wang, Can
    Fan, Yue
    Zhang, Xinsong
    Wang, Meng
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2020, 69 (06) : 3576 - 3586
  • [9] Pruning Method in The Architecture of Extreme Learning Machines Based on Partial Least Squares Regression
    Vitor, P.
    IEEE LATIN AMERICA TRANSACTIONS, 2018, 16 (12) : 2864 - 2871
  • [10] Reliability analysis of locomotive and car parts based on weighted least square method
    Wang, Hua-Sheng
    Tiedao Xuebao/Journal of the China Railway Society, 2001, 23 (06):
12345