The Construction and Application of a Deep Learning-Based Primary Support Deformation Prediction Model for Large Cross-Section Tunnels

被引:3
作者
Zhang, Junling [1 ]
Mei, Min [1 ]
Wang, Jun [2 ]
Shang, Guangpeng [3 ]
Hu, Xuefeng [3 ]
Yan, Jing [2 ]
Fang, Qian [2 ]
Plebankiewicz, Edyta
机构
[1] Rd & Bridge Int Co Ltd, Beijing 100081, Peoples R China
[2] Beijing Jiaotong Univ, Sch Civil Engn, Beijing 100044, Peoples R China
[3] Beijing & Hebei Construct & Dev Co Ltd, Chengde 067300, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 02期
基金
中国国家自然科学基金;
关键词
tunnel; deformation prediction; deep learning; performance metrics; SOFT ROCK TUNNELS; EXCAVATION; MASS;
D O I
10.3390/app14020912
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
The deformation of tunnel support structures during tunnel construction is influenced by geological factors, geometrical factors, support factors, and construction factors. Accurate prediction of tunnel support structure deformation is crucial for engineering safety and optimizing support parameters. Traditional methods for tunnel deformation prediction have often relied on numerical simulations and model experiments, which may not always meet the time-sensitive requirements. In this study, we propose a fusion deep neural network (FDNN) model that combines multiple algorithms with a complementary tunnel information encoding method. The FDNN model utilizes Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to extract features related to tunnel structural deformation. FDNN model is used to predict deformations in the Capital Ring Expressway, and the predictions align well with monitoring results. To demonstrate the superiority of the proposed model, we use four different performance evaluation metrics to analyze the predictive performance of FDNN, DNN, XGBoost, Decision Tree Regression (DTR), and Random Forest Regression (RFR) methods. The results indicate that FDNN exhibits high precision and robustness. To assess the impact of different data types on the predictive results, we use tunnel geometry data as the base and combine geological, support, and construction data. The analysis reveals that models trained on datasets comprising all four data types perform the best. Geological parameters have the most significant impact on the predictive performance of all models. The findings of this research guide predicting tunnel construction parameters, particularly in the dynamic design of support parameters.
引用
收藏
页数:15
相关论文
共 34 条
  • [1] Mechanisms of large deformation in soft rock tunnels: a case study of Huangjiazhai Tunnel
    Bian, Kang
    Liu, Jian
    Liu, Zhenping
    Liu, Shangge
    Ai, Fei
    Zheng, Xiaoqing
    Ni, Shaohu
    Zhang, Wei
    [J]. BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2019, 78 (01) : 431 - 444
  • [2] Bourquin J, 1997, Pharm Dev Technol, V2, P111, DOI 10.3109/10837459709022616
  • [3] XGBoost: A Scalable Tree Boosting System
    Chen, Tianqi
    Guestrin, Carlos
    [J]. KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, : 785 - 794
  • [4] Eberhart R., 1995, MHS 95, P39, DOI [DOI 10.1109/MHS.1995.494215, 10.1109/MHS.1995.494215]
  • [5] Fang Q., 2016, Chin. J. Rock Mech. Eng
  • [6] Intelligent back analysis using clonal selection algorithm in calculating equivalent top loading curve using O-cell test data
    Fang, Qian
    Wang, Jun
    Wang, Gan
    Li, Qian-qian
    Ma, Wei-bin
    [J]. JOURNAL OF CENTRAL SOUTH UNIVERSITY, 2023, 30 (10) : 3481 - 3498
  • [7] Smart Tunnel and Dynamic Risk Analysis
    Focaracci, Alessandro
    Greco, Giacomo
    Martirano, Luigi
    [J]. IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2020, 56 (03) : 2338 - 2347
  • [8] Greedy function approximation: A gradient boosting machine
    Friedman, JH
    [J]. ANNALS OF STATISTICS, 2001, 29 (05) : 1189 - 1232
  • [9] A finite strain numerical procedure for a circular tunnel in strain-softening rock mass with large deformation
    Guan, Kai
    Zhu, Wancheng
    Wei, Jiong
    Liu, Xige
    Niu, Leilei
    Wang, Xinrong
    [J]. INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES, 2018, 112 : 266 - 280
  • [10] Construction of large cross-section double-tier Metropolitan Inter-City Highway (Ken-O-Do) Ome Tunnel by NATM
    Haruyama, K
    Teramoto, S
    Taira, K
    [J]. TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY, 2005, 20 (02) : 111 - 119