A practical reliability assessment approach and its application for pile-stabilized slopes using FORM and support vector machine

被引:18
|
作者
Lu, Qing [1 ]
Xu, Bin [1 ]
Yu, Yang [2 ]
Zhan, Wei [3 ]
Zhao, Yu [1 ]
Zheng, Jun [1 ]
Ji, Jian [4 ]
机构
[1] Zhejiang Univ, Coll Civil Engn & Architecture, Hangzhou 310058, Peoples R China
[2] Zhejiang Univ, Ocean Coll, Zhoushan 316021, Peoples R China
[3] Zhejiang Sci Res Inst Transport, Hangzhou 310023, Peoples R China
[4] Hohai Univ, Key Lab, Minist Educ Geomech & Embankment Engn, Nanjing 210098, Peoples R China
基金
中国国家自然科学基金;
关键词
Pile-stabilized slope; Soil-pile interaction; FORM; Support vector machine; Uniform design; ROCK TUNNEL; DESIGN; ROW; EXCAVATION; REGRESSION; BEHAVIOR;
D O I
10.1007/s10064-021-02312-4
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Many uncertainties exist in pile-stabilized slopes which make their design substantially complicated. In this paper, a first-order reliability method (FORM) based on a support vector machine (SVM) and uniform design (UD) is proposed to investigate the reliability of a pile-stabilized slope. A deterministic model considering soil-pile interaction and using a strength reduction method based on the displacement criterion is employed to calculate the factor of safety and the corresponding pile-bending moment. The uncertainties involved in both the soil and the stabilizing pile are taken into consideration in the proposed method. Two typical failure modes, namely the insufficient factor of safety of a pile-stabilized slope and the insufficient flexural bearing capacity of stabilizing piles, are investigated from a probabilistic viewpoint. The proposed method is illustrated with an artificial homogeneous slope and a real slope engineering case. The influence of stabilizing pile installation locations on the reliability results were studied. The sensitivity of random variability was also investigated. The results of the proposed method show high accuracy while having a smaller computational time requirement when compared with the polynomial response surface method. The case study of a real highway slope shows the feasibility of the proposed method applied to practical engineering problems.
引用
收藏
页码:6513 / 6525
页数:13
相关论文
共 26 条
  • [21] Seismic reliability assessment of RC structures including soil-structure interaction using wavelet weighted least squares support vector machine
    Khatibinia, Mohsen
    Fadaee, Mohammad Javad
    Salajegheh, Javad
    Salajegheh, Eysa
    RELIABILITY ENGINEERING & SYSTEM SAFETY, 2013, 110 : 22 - 33
  • [22] Identification of Migratory Insects from their Physical Features using a Decision-Tree Support Vector Machine and its Application to Radar Entomology
    Hu, Cheng
    Kong, Shaoyang
    Wang, Rui
    Long, Teng
    Fu, Xiaowei
    SCIENTIFIC REPORTS, 2018, 8
  • [23] Identification of Migratory Insects from their Physical Features using a Decision-Tree Support Vector Machine and its Application to Radar Entomology
    Cheng Hu
    Shaoyang Kong
    Rui Wang
    Teng Long
    Xiaowei Fu
    Scientific Reports, 8
  • [24] Support Vector Machine for Short-Term Traffic Flow Prediction and Improvement of Its Model Training using Nearest Neighbor Approach
    Trinh Dinh Toan
    Viet-Hung Truong
    TRANSPORTATION RESEARCH RECORD, 2021, 2675 (04) : 362 - 373
  • [25] Forest fire susceptibility assessment under small sample scenario: A semi-supervised learning approach using transductive support vector machine
    Ma, Tianwu
    Wang, Gang
    Guo, Rui
    Chen, Liang
    Ma, Junfei
    JOURNAL OF ENVIRONMENTAL MANAGEMENT, 2024, 359
  • [26] A comparative and practical approach using quantum machine learning (QML) and support vector classifier (SVC) for Light emitting diodes mediated in vitro micropropagation of black mulberry (Morus nigra L.)
    Aasim, Muhammad
    Katirci, Ramazan
    Acar, Alpaslan Sevket
    Ali, Seyid Amjad
    INDUSTRIAL CROPS AND PRODUCTS, 2024, 213