The issue of settlement poses a big threat to underground excavation, especially in urban areas where the smallest of ground movements has the potential to lead to a catastrophic disaster. It is therefore crucial to understand the factors that play a role in causing surface settlement during the excavation process. Numerous approaches including empirical, numerical and analytical have already been established to map the relationships that exist between tunneling and ground deformation. It has also been established in previous studies that surface settlement is not caused by one factor or the other but is more of a combination of factors. Artificial Intelligence methods (AI) have the ability to relate several parameters to surface settlement quickly and efficiently given the proper skills and understanding. In this study, dimensional analysis is used to normalize the factors that affect surface settlement and then the influence of these normalized excavation factors on the prediction of surface settlement is investigated using AI. Three sets of analyses are run on RapidMiner Studio v9.2 using four different algorithms, decision trees, artificial neural networks, random forests and support vector machines. The first set of analyses were done with no indices, the second included the thrust index (Th/(D^2 q_u )) and the last set included the depth index (H/D). The results of the predictions are then compared to the field measurements to see if including these indices in the analysis benefits the prediction or not. The study shows that the thrust index does in fact improve the prediction accuracy while the influence of the depth index in inconclusive.

The issue of settlement poses a big threat to underground excavation, especially in urban areas where the smallest of ground movements has the potential to lead to a catastrophic disaster. It is therefore crucial to understand the factors that play a role in causing surface settlement during the excavation process. Numerous approaches including empirical, numerical and analytical have already been established to map the relationships that exist between tunneling and ground deformation. It has also been established in previous studies that surface settlement is not caused by one factor or the other but is more of a combination of factors. Artificial Intelligence methods (AI) have the ability to relate several parameters to surface settlement quickly and efficiently given the proper skills and understanding. In this study, dimensional analysis is used to normalize the factors that affect surface settlement and then the influence of these normalized excavation factors on the prediction of surface settlement is investigated using AI. Three sets of analyses are run on RapidMiner Studio v9.2 using four different algorithms, decision trees, artificial neural networks, random forests and support vector machines. The first set of analyses were done with no indices, the second included the thrust index (Th/(D^2 q_u )) and the last set included the depth index (H/D). The results of the predictions are then compared to the field measurements to see if including these indices in the analysis benefits the prediction or not. The study shows that the thrust index does in fact improve the prediction accuracy while the influence of the depth index in inconclusive.

Abu-Farsakh, M. Y. & Voyiadjis, G.Z. (1999). Computational model for the simulation of the shield tunneling process in cohesive soils. International Journal for Numerical and Analytical Methods in Geomechanics, 23(1), 23-44.

Breiman, L. (2001). Random Forests. Mach. Learn., 45(1), 5-32. d

Buckingham, E. (1914). On Physically Similar Systems; Illustrations of the Use of Dimensional Equations. Physical Review, 4(4), 345-376.

Chapman, D. N. & Ichioka, Y. (1999). Prediction of jacking forces for microtunnelling operations. Tunnelling and Underground Space Technology, 14, 31-41.

Chen, L. H. (2001). Failure of rock under normal wedge indentation. (PhD Thesis), University of Minnesota, Minnesota.

Chen, Y. C, Chen, L. H., Lin, G. L., Yang, Z. X., Cheng, Y. H., Moriasi, H. & Jetmal, A. J. S. (2015). Normalized cutting indices to underground mechanical excvation. Paper presented at the International No-Dig Istanbul 2015, Istanbul.

Chen, L. H. & Labuz, J. F. (2006). Indentation of rock by wedge-shaped tools. International Journal of Rock Mechanics and Mining Sciences, 43(7), 1023-1033.

Clough, W., Sweeney, B. P., & Finno, R. (1981). Measured Soil Response to EPB Shield Tunneling (Vol. 109).

van Dijk, F. J. & Kaalberg, F. (1998). 3-D Geotechnical Model for the North/Southline in Amsterdam.

Dindarloo, S. R., & Siami-Irdemoosa, E. (2015). Maximum surface settlement based classification of shallow tunnels in soft ground. Tunnelling and Underground Space Technology, 49, 320-327.

Finno, R. J. & Clough, G. W. (1985). Evaluation of soil response to EPB shield tunneling. Journal of Geotechnical Engineering, 111(2), 155-173.

Han, X. (2006). The analysis and prediction of tunneling-induced building deformation. (PhD Thesis), Xi'an University of Technology, Xi'an.

Huang, H. (1999). Discrete element modelling of rock-tool interaction (PhD Thesis), University of Minnesota,

Huang, J. P. (2016). Quasi-static cutting mechanics of underground mechanical excavation and its suitable indices: Application to design and construction of straight/curved tunnel and pipeline system. (Masters Thesis ), National Taiwan University of Science and Technology, Taipei.

Kasper, T., & Meschke, G. (2004). A 3D finite element simulation model for TBM tunnelling in soft ground. International Journal for Numerical and Analytical Methods in Geomechanics, 28(14), 1441-1460.

Kohestani, V. R., Bazargan-Lari, M. R., & Asgari-marnani, J. (2017). Prediction of maximum surface settlement caused by earth pressure balance shield tunneling using random forest. Journal of AI and Data Mining, 5, 127-135.

Lee, K. M., & Rowe, R. K. (1991). An analysis of three-dimensional ground movements: the Thunder Bay tunnel. Canadian Geotechnical Journal, 28(1), 25-41.

Lee, K. M., & Rowe, R. K. (1990). Finite element modelling of the three-dimensional ground deformations due to tunnelling in soft cohesive soils: Part I — Method of analysis. Computers and Geotechnics, 10(2), 87-109.

Li, Ning (2017). Predicting underground tunnel hazards using machine learning techniques. (PhD Thesis), Universidad Politecnica de Madrid, Madrid.

Liaw, A., & Wiener, M. (2002). Classification and Regression by randomForest. Paper presented at the R news.

Lin, Y. X. (2007). Preliminary study of the relationship between contact and cracking behavior in granular material-numerical simulation and analysis. (Masters Thesis), National Taipei University of Technology, Taipei.

Lin, G. L. (2010). Study of generalized thrust system for underground tunneling. (Masters Thesis), National Taipei University of Technology, Taipei.

Loganathan, N., & Poulos H.G. (1998). Analytical Prediction for Tunneling-Induced Ground Movements in Clays. 124(9), 846-856

MLS. (26 May 2017). "Giant Subway Tunnel Boring Machine." Retrieved 14 February 2019, from https://www.mylittlesalesman.com/news/tag/giant-machines.

Nabil, K., & Ian, F. (1997). Artificial Neural Networks for Civil Engineers: Fundamentals and Applications: American Society of Civil Engineers.

North, M. (2012). Data mining for the masses. Lexington, Ky.: Global Text Project.

O'Reilly, M. P., & New, B. M. (1982). Settlements above tunnels in the United Kingdom - Their magnitude and prediction.
Ocak, I., & Seker, S. E. (2013). Calculation of surface settlements caused by EPBM tunneling using artificial neural network, SVM and Gaussian processes. Environmental Earth Sciences, 70, 1263 - 1276

Okari, H. M. (2015). Validation of a theoretical generalized tunneling thrust prediction model and mechanized underground excavation indices: Case studies. (Masters Thesis), National Taiwan University of Science and Technology, Taipei.

Peck, P. B. (1969). Deep Excavations and tunelling in soft ground. Paper presented at the 7th International Conference on Soil Mechanics and Foundation Engineering, Mexico City, Sociedad Mexicana de Mecanica de Suelos AC.

Press, W.H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (2007). Numerical Recipes 3rd Edition: The Art of Scientific Computing: Cambridge University Press.

Rowe, R. K., Lo, J., & Kack, G. J. (1983). A method of estimating surface settlement above tunnels constructed in soft clay (Vol. 20).

Sonin, A. A. (2001). The Physical Basis of DIMENSIONAL ANALYSIS (2nd ed.).

Su, Y. F (2008). Numerical approach to the effect of wear flat and lateral boundary conditions on indentation fracture in rock. (Masters Thesis), National Taipei University of Technology, Taipei.

Suwansawat, S., & Einstein, H. H. (2006). Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling. Tunneling and Underground Space Technology, 21, 133-150.

Tso, G. K. F., & Yau, K. K. W.. (2007). Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks. Energy, 32(9), 1761-1768.

Tunnelingjournal.com. (2012). TBM EPB SELI KISHANGANGA. Retrieved from https://tunnellingjournal.com/tbm-epb-seli-kishanganga/

VTS. (20 November 2018). Pipe Jacking Melbourne Trenchless Technology. Retrieved from http://www.victoriatrenchlesssolutions.com.au/pipe-jacking-melbourne-trenchless-technology/

Vu, M. N., Broere, W., & Bosch, J. (2016). Volume loss in shallow tunnelling. Tunnelling and Underground Space Technology, 59, 77-90.

Wang, S. Y. (2008). Coupled FLAC/PFC2D numerical simulation to indentation fracture in rock by double wedge indenters. (Masters Thesis), National Taipei University of Technology, Taipei.
Wang, L., Sun, W., Long, Y., & Yang, X. (2018). Reliability-Based Performance Optimization of Tunnel Boring Machine Considering Geological Uncertainties. IEEE Access, 6, 19086-19098. doi:10.1109/ACCESS.2018.2821190

Wu, Q. Y. (2009). Distinct Element Approach to the effect of wear flat and doubled-indenters on contact fracture and the study of coupled numerical method using Distinct/Finite Different Element. (Masters Thesis), National Taipei University of Technology, Taipei.

Zhou, J., Li, X. & Shi, X. (2012). Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines. Safety Science, 50(4), 629-644.

Zhu, C., & Li, N. (2016). Prediction and analysis of surface settlement due to shield tunneling for Xi'an Metro. Canadian Geotechnical Journal, 54, 529-546.