All Issue

2025 Vol.27, Issue 1 Preview Page

Research Paper

XGBoost machine learning-based prediction for ground settlement by a shield TBM tunnelling

XGBoost 머신러닝 기반 쉴드 TBM 지반침하 예측

Jae-Woo Shin1
,
Yun-Hee Kim2
,
So-Yi Lee3
,
Bumjoo Kim4*
신 재우1
,
김 윤희2
,
이 소이3
,
김 범주4*
1Ph.D. Student, Dept. of Civil and Environmental Engineering, Dongguk University
2Post-Doctoral Researcher, Dept. of Civil and Environmental Engineering, Dongguk University
3Master Student, Dept. of Civil and Environmental Engineering, Dongguk University
4Professor, Dept. of Civil and Environmental Engineering, Dongguk University
1학생회원, 동국대학교 건설환경공학과 박사과정
2정회원, 동국대학교 건설환경공학과 박사 후 연구원
3학생회원, 동국대학교 건설환경공학과 석사과정
4정회원, 동국대학교 건설환경공학과 교수
*Corresponding Author
31 January 2025. pp. 59-79
PDF XML Citation
Abstract

This study developed an XGBoost (eXtreme Gradient Boosting) machine learning model to predict ground settlement during urban shield TBM (tunnel boring machine) tunnel construction and evaluated its performance. While previous studies have primarily focused on predicting ground settlement behind the tunnel, this study used real-time shield TBM construction data to predict both rear and forward settlement. For this purpose, field data from a TBM tunnel construction project in Hong Kong, provided by a local construction company, was analyzed. This data included information on ground conditions, TBM advancement, and tunnel geometry. A total of 17 input variables were selected for the machine learning model, which were grouped into three prediction ranges: the forward range (25 segment rings ahead of the tunnel face, CASE 1), the central section (upper part of the TBM body, CASE 2), and the rear range (25 segment rings behind the tunnel face, CASE 3). The relationships between the input variables and settlement were analyzed for each of these ranges. For each case (forward, central, and rear positions), an XGBoost model was developed to predict ground settlement, with hyperparameters optimized through Bayesian optimization and 5-fold cross-validation. The results showed that the rear settlement model performed the best, achieving a coefficient of determination (R2) of 0.82, while the forward settlement model had a lower performance, with an R2 of 0.52. These results suggest that rear settlement predictions are more accurate than forward predictions, with the latter being more affected by ground variability and excavation factors, resulting in lower accuracy. Overall, the findings highlight that machine learning models can be effective tools for predicting ground settlement during TBM tunnel construction, especially for rear settlement. However, further research is needed to enhance the accuracy of forward settlement predictions.

Keywords
Shield TBM
XGBoost
Machine learning
Ground settlement

본 연구에서는 도심지 쉴드 TBM (tunnel boring machine) 터널 시공 중 발생하는 지반침하를 예측하기 위한 XGBoost (eXtreme Gradient Boosting) 머신러닝 모델을 개발하고, 그 성능을 평가하였다. 기존 연구들에서 주로 터널 후방의 침하를 예측하는 연구가 많았던 반면, 본 연구에서는 실시간 쉴드 TBM 시공 데이터를 활용하여 터널의 후방 침하뿐 아니라 전방 침하에 대한 예측도 시도하였다. 이를 위해 이수가압식 쉴드 TBM으로 시공한 터널 현장 데이터를 제공받아 지반 조건, TBM 굴진자료 , 터널 기하 조건 등을 분석하고 17개의 머신러닝 모델 입력변수를 선정하였다. 선정된 17개의 입력변수에 대해 쉴드 TBM 본체를 기준으로 전방 예측 범위(세그먼트 25링 전방, CASE 1), 중앙부(TBM 본체 상부, CASE 2), 후방 예측 범위(세그먼트 25링 후방, CASE 3) 등 세 범위로 구분하고 각 범위에 대하여 입력변수와 침하량 간의 상관관계를 분석하였다. 그리고 각 CASE별로, 즉 터널 전방(CASE 1), 중앙(CASE 2), 후방(CASE 3) 위치에 대해서 XGBoost 머신러닝 알고리즘을 적용한 지반침하 예측 모델을 구축하고 베이지안 최적화와 5겹 교차 검증을 통해 하이퍼파라미터를 최적화하였다. 모델 평가결과, 후방 침하 예측 모델은 결정계수(R2)값이 0.82로 가장 높은 성능을 보인 반면, 전방 침하 예측 모델의 결정계수는 0.52로 상대적으로 낮은 성능을 나타내었다. 이러한 결과는 후방 침하 예측 정확도가 전방 예측보다 우수하고, 전방 예측의 경우 지반의 불확실성과 굴착 변수의 영향을 더 많이 받아 정확도가 낮아질 수 있음을 시사한다. 머신러닝 모델이 TBM 터널 시공 중 발생하는 지반침하, 특히 막장면 후방의 침하를 예측하는 데 효과적인 도구이나 아직 전방 침하의 예측 정확도를 높이기 위해서는 많은 추가 연구가 이루어져야 함을 확인하였다.

키워드
쉴드 TBM
XGBoost
머신러닝
지반침하
References
1

Bergstra, J., Bengio, Y. (2012), "Random search for hyper-parameter optimization", Journal of Machine Learning Research, Vol. 13, No. 2, pp. 281-305.

2

Broere, W. (2016), "Urban underground space: Solving the problems of today's cities", Tunnelling and Underground Space Technology, Vol. 55, pp. 245-248.

10.1016/j.tust.2015.11.012
3

Chen, X.X., Yang, J., He, G.F., Huang, L.C. (2023), "Development of an LSTM-based model for predicting the long-term settlement of land reclamation and a GUI-based tool", Acta Geotechnica, Vol. 18, No. 7, pp. 3849-3862.

10.1007/s11440-022-01749-5
4

Frazier, P.I. (2018), "A tutorial on Bayesian optimization", arXiv:1807.02811.

10.1287/educ.2018.0188
5

Fu, X., Zhang, L. (2021), "Spatio-temporal feature fusion for real-time prediction of TBM operating parameters: A deep learning approach", Automation in Construction, Vol. 132, 103937.

10.1016/j.autcon.2021.103937
6

Jung, J.H., Kim, B.K., Chung, H., Kim, H.M., Lee, I.M. (2019), "A ground condition prediction ahead of tunnel face utilizing time series analysis of shield TBM data in soil tunnel", Journal of Korean Tunnelling and Underground Space Association, Vol. 21, No. 2, pp. 227-242.

10.9711/KTAJ.2019.21.2.227
7

Kasali, G., Clough, G.W. (1983), Development of a design technology for ground support for tunnels in soil: Vol. II. Three dimensional finite element analysis of advanced and conventional shield tunneling, No. UMTA-MA-06-0100-82-2, United States, Urban Mass Transportation Administration.

8

Kim, D. (2022), Machine learning approach to predict surface settlements induced by TBM tunnel construction, Ph.D. Thesis, Korea University, pp. 153-164.

9

Kim, D., Kwon, K., Pham, K., Oh, J.Y., Choi, H. (2022a), "Surface settlement prediction for urban tunneling using machine learning algorithms with Bayesian optimization", Automation in Construction, Vol. 140, 104331.

10.1016/j.autcon.2022.104331
10

Kim, D., Pham, K., Oh, J.Y., Lee, S.J., Choi, H. (2022b), "Classification of surface settlement levels induced by TBM driving in urban areas using random forest with data-driven feature selection", Automation in Construction, Vol. 135, 104109.

10.1016/j.autcon.2021.104109
11

Kim, D., Pham, K., Park, S., Oh, J.Y., Choi, H. (2020), "Determination of effective parameters on surface settlement during shield TBM", Geomechanics and Engineering, Vol. 21, No. 2, pp. 153-164.

10.12989/gae.2020.21.2.153
12

Kim, Y., Hong, J., Shin, J., Kim, B. (2022c), "Shield TBM disc cutter replacement and wear rate prediction using machine learning techniques", Geomechanics and Engineering, Vol. 29, No. 3, pp. 249-258.

10.12989/gae.2022.29.3.249
13

Kim, Y., Shin, J., Kim, B. (2024), "Analysis of disc cutter replacement based on wear patterns using artificial intelligence classification models", Geomechanics and Engineering, Vol. 38, No. 6, pp. 633-645.

10.12989/gae.2024.38.6.633
14

Lai, J., Zhu, J., Guo, Y., Xie, Y., Hu, Y., Wang, P. (2024), "A multi-factor-driven approach for predicting surface settlement caused by the construction of subway tunnels by undercutting method", Environmental Earth Sciences, Vol. 83, No. 15, 442.

10.1007/s12665-024-11729-5
15

Mori, A., Akagi, H. (1985), "Effects of backfilling at shield work in soft cohesive soil", Proceedings of the International Conference on Soil Mechanics and Foundation Engineering, Vol. 11, Sanfrancisco, pp. 1667-1670.

16

O'Reilly, M.P., New, B.M. (1982), "Settlements above tunnels in the United Kingdom - their magnitude and prediction", Proceedings of the Tunnelling '82, London, pp. 173-181.

17

Peck, R.B. (1969), "Deep excavations and tunneling in soft ground", Proceedings of the 7th International Conference on Soil Mechanic sand Foundation engineering, Mexico City, State of the Art 3, pp. 225-290.

18

Samadi, H., Hassanpour, J., Farrokh, E. (2021), "Maximum surface settlement prediction in EPB TBM tunneling using soft computing techniques", Journal of Physics, Vol. 1973, No. 1, 012195.

10.1088/1742-6596/1973/1/012195
19

Shahriari, B., Swersky, K., Wang, Z., Adams, R.P., De Freitas, N. (2016), "Taking the human out of the loop: A review of Bayesian optimization", Proceedings of the IEEE, Vol. 104, No. 1, pp. 148-175.

10.1109/JPROC.2015.2494218
20

Snoek, J., Larochelle, H., Adams, R.P. (2012), "Practical bayesian optimization of machine learning algorithms", Advances in Neural Information Processing Systems, Vol. 25, pp. 2951-2959.

21

Suwansawat, S., Einstein, H.H. (2006), "Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling", Tunnelling and Underground Space Technology, Vol. 21, No. 2, pp.133-150.

10.1016/j.tust.2005.06.007
22

Yu, G., Jin, Y., Hu, M., Li, Z., Cai, R., Zeng, R., Sugumaran, V. (2024), "Improved machine learning model for urban tunnel settlement prediction using sparse data", Sustainability, Vol. 16, No. 11, 4693.

10.3390/su16114693
23

Zhang, N., Shen, S.L., Zhou, A., Jin, Y.F. (2021), "Application of LSTM approach for modelling stress-strain behaviour of soil", Applied Soft Computing, Vol. 100, 106959.

10.1016/j.asoc.2020.106959
24

Zhou, X., Zhao, C., Bian, X. (2023), "Prediction of maximum ground surface settlement induced by shield tunneling using XGBoost algorithm with golden-sine seagull optimization", Computers and Geotechnics, Vol. 154, 105156.

10.1016/j.compgeo.2022.105156
Information
  • Publisher :Korean Tunneling and Underground Space Association
  • Publisher(Ko) :한국터널지하공간학회
  • Journal Title :Journal of Korean Tunnelling and Underground Space Association
  • Journal Title(Ko) :한국터널지하공간학회 논문집
  • Volume : 27
  • No :1
  • Pages :59-79
  • Received Date : 2024-12-24
  • Revised Date : 2025-01-05
  • Accepted Date : 2025-01-06
  • DOI :https://doi.org/10.9711/KTAJ.2025.27.1.059
Journal Informaiton Journal of Korean Tunnelling and Underground Space Association Journal of Korean Tunnelling and Underground Space Association
Online Submission & Review System
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close