Accurate ground information of tunnel face is essential for earth pressure balance and TBM dual-mode shield tunneling control and mode changeover, and the cutterhead vibration is a direct response to the interaction between the dual-mode shield and the ground during tunneling, which presents significant characteristic differences under different ground conditions. The study relies on the construction section of the double-mode shield of Shenzhen Metro Line 12, Huai Fu, and the vibration data of the cutterhead during the tunneling process is collected by carrying a vibration monitoring system on the shield to create a database of vibration and ground types. The key features of the vibration signals were extracted and analyzed using signal processing techniques, and used as input to establish a model for recognition the ground types at the tunnel surface of the double-mode shield tunneling. The model uses Stacking integration technique, taking decision tree, K-nearest neighbor, support vector classification and AdaBoost as base learners and logistic regression as meta-learners. By testing the Huai Fu section dataset, the model achieved an accuracy of 95.7%, which was significantly better than traditional machine learning models such as DT, KNN, SVC, and AdaBoost, and obtained the key cutterhead vibration features that were most sensitive to ground types, including root mean square value, root mean square amplitude, and mean frequency domain. This study provides a new approach for real-time identification of geological types in shield tunnel construction in the future.
Wu You
,
Zhou Xiaoxiong
,
Cao Yuxin
,
Gong Qiuming
,
Wu Fan
. Ground Recognition Model of Dual-Mode Shield Tunneling Based on Cutterhead Vibration Features[J]. Chinese Journal of Underground Space and Engineering, 2024
, 20(S2)
: 629
-637
.
DOI: 10.20174/j.JUSE.2024.S2.14
[1] 龚秋明. 掘进机隧道掘进概论[M]. 北京:科学出版社, 2014.
[2] Huang X, Liu Q, Liu H, et al. Development and in-situ application of a real-time monitoring system for the interaction between TBM and surrounding rock[J].Tunnelling and Underground Space Technology, 2018, 81:187-208.
[3] Liu M, Liao S, Yang Y, et al. Tunnel boring machine vibration-based deep learning for the ground identification of working faces[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2021, 13(6): 1340-1357.
[4] Huo J, Sun X, Li G, et al. Multi-degree-of-freedom coupling dynamic characteristic of TBM disc cutter under shock excitation[J]. Journal of Central South University, 2015, 22(9): 3326-3337.
[5] Wu F, Gong Q, Li Z, et al. Development and application of cutterhead vibration monitoring system for TBM tunnelling[J]. International Journal of Rock Mechanics and Mining Sciences, 2021, 146: 104887.
[6] Henriquez P, Alonso J B, Ferrer M A, et al. Review of automatic fault diagnosis systems using audio and vibration signals[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2013, 44(5): 642-652.
[7] Amirat Y,Benbouzid M E H, Al-Ahmar E, et al. A brief status on condition monitoring and fault diagnosis in wind energy conversion systems[J]. Renewable and Sustainable Energy Reviews, 2009, 13(9): 2629-2636.
[8] Zhang C, Mousavi A A, Masri S F, et al. Vibration feature extraction using signal processing techniques for structural health monitoring: A review[J]. Mechanical Systems and Signal Processing, 2022, 177: 109175.
[9] Lei Y, He Z, Zi Y, et al. Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs[J]. Mechanical Systems and Signal Processing, 2007, 21(5): 2280-2294.
[10] Buckley T, Ghosh B,Pakrashi V. A feature extraction & selection benchmark for structural health monitoring[J]. Structural Health Monitoring, 2022, 22(85): 14759217221111141.
[11] 张娜, 李建斌, 荆留杰, 等. TBM 掘进参数智能控制系统的研究与应用[J]. 隧道建设(中英文), 2018, 38 (10): 1734-1740.
[12] Liu Z, Li L, Fang X, et al. Hard-rock tunnel lithology prediction with TBM construction big data using a global-attention-mechanism-based LSTM network[J]. Automation in Construction, 2021, 125: 103647.
[13] Guan Z, Deng T, Du S, et al. Markovian geology prediction approach and its application in mountain tunnels[J]. Tunnelling and Underground Space Technology, 2012, 31(5):61-67.
[14] 丁小彬, 谢宇轩, 薛皓文, 等. 基于神经网络的盾构滚刀磨损量预测方法探讨[J].地下空间与工程学报, 2023, 19(2): 560-570.
[15] 周小雄, 龚秋明, 殷丽君,等. 基于BLSTM-AM模型的TBM稳定段掘进参数预测[J]. 岩石力学与工程学报, 2020, 39(增2): 3505-3515.
[16] 刘诗洋, 陈祖煜, 张云旆, 等.基于卷积神经网络对 TBM 塌方段的反演分析[J]. 固体力学学报, 2021, 42(3): 287-301.
[17] Breiman L. Bagging predictors[J]. Machine Learning, 1996, 24(2): 123-140.
[18] Friedman J H. Greedy function approximation: A gradient boosting machine[J]. Annals of Statistics, 2001, 29(5): 1189-1232.
[19] Polikar R. Ensemble Machine Learning[J]. Scholarpedia, 2009, 4(1):2776.
