Reinforcement Learning for the Face Support Pressure of Tunnel Boring Machines

被引:7
作者
Soranzo, Enrico [1 ]
Guardiani, Carlotta [1 ]
Wu, Wei [1 ]
机构
[1] Univ Nat Resources & Life Sci, Inst Geotech Engn, A-1180 Vienna, Austria
关键词
tunnelling; tunnel boring machine; support pressure; face stability; reinforcement learning; machine learning; Deep-Q-Network; SHALLOW TUNNELS; SHIELD TUNNEL; STABILITY; GO; SIMULATION; SHOGI; CHESS; MODEL; GAME; SOIL;
D O I
10.3390/geosciences13030082
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
In tunnel excavation with boring machines, the tunnel face is supported to avoid collapse and minimise settlement. This article proposes the use of reinforcement learning, specifically the deep Q-network algorithm, to predict the face support pressure. The algorithm uses a neural network to make decisions based on the expected rewards of each action. The approach is tested both analytically and numerically. By using the soil properties ahead of the tunnel face and the overburden depth as the input, the algorithm is capable of predicting the optimal tunnel face support pressure whilst minimising settlement, and adapting to changes in geological and geometrical conditions. The algorithm reaches maximum performance after 400 training episodes and can be used for random geological settings without retraining.
引用
收藏
页数:23
相关论文
共 96 条
  • [91] Supervised Machine Learning Techniques to the Prediction of Tunnel Boring Machine Penetration Rate
    Xu, Hai
    Zhou, Jian
    Asteris, Panagiotis G.
    Armaghani, Danial Jahed
    Tahir, Mahmood Md
    [J]. APPLIED SCIENCES-BASEL, 2019, 9 (18):
  • [92] Yu C, 2020, Arxiv, DOI arXiv:1908.08796
  • [93] Zai A., 2020, Deep reinforcement learning in action, DOI DOI 10.3139/9783446466081
  • [94] Real-time prediction of shield moving trajectory during tunnelling using GRU deep neural network
    Zhang, Nan
    Zhang, Ning
    Zheng, Qian
    Xu, Ye-Shuang
    [J]. ACTA GEOTECHNICA, 2022, 17 (04) : 1167 - 1182
  • [95] Reinforcement learning based optimizer for improvement of predicting tunneling-induced ground responses
    Zhang, Pin
    Li, Heng
    Ha, Q. P.
    Yin, Zhen-Yu
    Chen, Ren-Peng
    [J]. ADVANCED ENGINEERING INFORMATICS, 2020, 45
  • [96] State-of-the-art review of soft computing applications in underground excavations
    Zhang, Wengang
    Zhang, Runhong
    Wu, Chongzhi
    Goh, Anthony Teck Chee
    Lacasse, Suzanne
    Liu, Zhongqiang
    Liu, Hanlong
    [J]. GEOSCIENCE FRONTIERS, 2020, 11 (04) : 1095 - 1106