Gaussian Process-Based Response Surface Method for Slope Reliability Analysis
A new response surface method (RSM) for slope reliability analysis was proposed based on Gaussian process (GP) machine learning technology. The method involves the approximation of limit state function by the trained GP model and estimation of failure probability using the first-order reliability me...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Advances in Civil Engineering |
| Online Access: | http://dx.doi.org/10.1155/2019/9185756 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551503781429248 |
|---|---|
| author | Bin Hu Guo-shao Su Jianqing Jiang Yilong Xiao |
| author_facet | Bin Hu Guo-shao Su Jianqing Jiang Yilong Xiao |
| author_sort | Bin Hu |
| collection | DOAJ |
| description | A new response surface method (RSM) for slope reliability analysis was proposed based on Gaussian process (GP) machine learning technology. The method involves the approximation of limit state function by the trained GP model and estimation of failure probability using the first-order reliability method (FORM). A small amount of training samples were firstly built by the limited equilibrium method for training the GP model. Then, the implicit limit state function of slope was approximated by the trained GP model. Thus, the implicit limit state function and its derivatives for slope stability analysis were approximated by the GP model with the explicit formulation. Furthermore, an iterative algorithm was presented to improve the precision of approximation of the limit state function at the region near the design point which contributes significantly to the failure probability. Results of four case studies including one nonslope and three slope problems indicate that the proposed method is more efficient to achieve reasonable accuracy for slope reliability analysis than the traditional RSM. |
| format | Article |
| id | doaj-art-f9bac3cd8bc94772b39322fb279c7250 |
| institution | Kabale University |
| issn | 1687-8086 1687-8094 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Civil Engineering |
| spelling | doaj-art-f9bac3cd8bc94772b39322fb279c72502025-02-03T06:01:27ZengWileyAdvances in Civil Engineering1687-80861687-80942019-01-01201910.1155/2019/91857569185756Gaussian Process-Based Response Surface Method for Slope Reliability AnalysisBin Hu0Guo-shao Su1Jianqing Jiang2Yilong Xiao3School of Resource and Environmental Engineering, Wuhan University of Science and Technology, P.O. Box 430081, Wuhan, ChinaKey Laboratory of Disaster Prevention and Structural Safety of Ministry of Education, School of Civil and Architecture Engineering, Guangxi University, Nanning, Guangxi 530004, ChinaKey Laboratory of Disaster Prevention and Structural Safety of Ministry of Education, School of Civil and Architecture Engineering, Guangxi University, Nanning, Guangxi 530004, ChinaKey Laboratory of Disaster Prevention and Structural Safety of Ministry of Education, School of Civil and Architecture Engineering, Guangxi University, Nanning, Guangxi 530004, ChinaA new response surface method (RSM) for slope reliability analysis was proposed based on Gaussian process (GP) machine learning technology. The method involves the approximation of limit state function by the trained GP model and estimation of failure probability using the first-order reliability method (FORM). A small amount of training samples were firstly built by the limited equilibrium method for training the GP model. Then, the implicit limit state function of slope was approximated by the trained GP model. Thus, the implicit limit state function and its derivatives for slope stability analysis were approximated by the GP model with the explicit formulation. Furthermore, an iterative algorithm was presented to improve the precision of approximation of the limit state function at the region near the design point which contributes significantly to the failure probability. Results of four case studies including one nonslope and three slope problems indicate that the proposed method is more efficient to achieve reasonable accuracy for slope reliability analysis than the traditional RSM.http://dx.doi.org/10.1155/2019/9185756 |
| spellingShingle | Bin Hu Guo-shao Su Jianqing Jiang Yilong Xiao Gaussian Process-Based Response Surface Method for Slope Reliability Analysis Advances in Civil Engineering |
| title | Gaussian Process-Based Response Surface Method for Slope Reliability Analysis |
| title_full | Gaussian Process-Based Response Surface Method for Slope Reliability Analysis |
| title_fullStr | Gaussian Process-Based Response Surface Method for Slope Reliability Analysis |
| title_full_unstemmed | Gaussian Process-Based Response Surface Method for Slope Reliability Analysis |
| title_short | Gaussian Process-Based Response Surface Method for Slope Reliability Analysis |
| title_sort | gaussian process based response surface method for slope reliability analysis |
| url | http://dx.doi.org/10.1155/2019/9185756 |
| work_keys_str_mv | AT binhu gaussianprocessbasedresponsesurfacemethodforslopereliabilityanalysis AT guoshaosu gaussianprocessbasedresponsesurfacemethodforslopereliabilityanalysis AT jianqingjiang gaussianprocessbasedresponsesurfacemethodforslopereliabilityanalysis AT yilongxiao gaussianprocessbasedresponsesurfacemethodforslopereliabilityanalysis |