Detecting soil mixing, grain size distribution, and clogging potential of tunnel excavation face by classification-regression algorithms using EPBM operational data

Abstract

Earth pressure balance machine (EPBM) operation is sensitive to the properties of the excavated soil due to the requirements of proper soil conditioning and maintenance of necessary chamber pressure. However, soil properties are invariably only available at a limited number of borehole explorations and soil samplings conducted during the subsoil investigation. Thus, it is crucial to identify properties of the tunnel excavation face, such as clay-sand mixed conditions, grain size distributions, and clogging potential along the whole alignment beside the few borehole locations to attain optimally efficient EPBM operation. Therefore, this paper presents the development of machine learning prediction models (i.e., classifiers and regressors) to estimate the properties of the tunnel excavation face using EPBM operational data collected during the tunneling operation as input features. Geotechnical data collected from boreholes and soil samples can be used to validate prediction models and calibrate them. To develop such models, the Northgate Link Extension (N125) tunneling project, constructed in Seattle, Washington, the USA, is used to capture and identify the true ground conditions. The results indicate successful prediction performances by the models, providing indication that EPBM parameters are crucial pointers of the tunnel excavation face properties to help attain optimally efficient EPBM operation.

Keywords

EPBM tunneling / Mixed soil / Grain size / Clogging / Machine learning / Stochastic hill climbing-adaptive steps

Data availability

The data that support the findings of this study are available from the corresponding author upon reasonable request.

CRediT authorship contribution statement

Sharmin Sarna: Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing - original draft. Marte Gutierrez: Funding acquisition, Resources, Supervision, Writing - review & editing.

Declaration of competing interest

Marte Gutierrez is an editorial board member for Underground Space and was not involved in the editorial review or the decision to publish this article. All authors declare that there are no competing interests.

Acknowledgement

Support from the University Transportation Center for Underground Transportation Infrastructure (UTC-UTI) at the Colorado School of Mines for funding this research under Grant No. 69A3551747118 from the U.S. Department of Transportation (DOT) is gratefully acknowledged. The opinions expressed in this paper are those of the authors and not of the DOT.

References

[1] Blindheim, O. T., Grov, E., & Nilsen, B. J. O. R. N. (2002). The effect of mixed face conditions (MFC) on hard rock TBM performance. In ITA General Assembly (28th: 2002: Sydney, NSW) (pp. 440-446). Sydney: Institution of Engineers.

[2] Caballero, L., Jojoa, M., & Percybrooks, W. S. (2020). Optimized neural networks in industrial data analysis. SN Applied Sciences, 2(2), 1-8.

[3] Cruz, R., Costa, J. F. P., & Cardoso, J. S. (2019). Automatic augmentation by hill climbing. In International conference on artificial neural networks (pp.115-124). Springer.

[4] Efnarc (2005). Specifications and guidelines for the use of specialist products for mechanized tunnelling (TBM) in soft ground and hard rock>. EFNARC.

[5] Elbaz, K., Shen, S.-L., Cheng, W.-C., & Arulrajah, A. (2018). Cutter-disc consumption during earth pressure balance tunnelling in mixed strata. Proceedings of the Institution of Civil Engineers-Geotechnical Engineering, 171(4), 363-376.

[6] Elrahman, S. M., & Abraham, A. (2013). A review of class imbalance problem. Journal of Network and Innovative Computing, 1(2013), 332-340.

[7] Elsken, T., Metzen, J. H., & Hutter, F. (2019). Neural architecture search: A survey. The Journal of Machine Learning Research, 20(1), 1997-2017.

[8] Erharter, G. H., & Marcher, T. (2021). On the pointlessness of machine learning based time delayed prediction of TBM operational data. Automation in Construction, 121, 103443.

[9] Erharter, G., H., Marcher, T., & Reinhold, C. (2020). Artificial neural network based online rockmass behavior classification of TBM data. In A. G. Correia, J. Tinoco, P. Cortez, & L. Lamas (Eds.), Information technology in geo-engineering (pp. 178-188). Springer International Publishing.

[10] Galli, M., & Thewes, M. (2014). Investigations for the application of EPB shields in difficult grounds/Untersuchungen für den Einsatz von Erddruckschilden in schwierigem Baugrund. Geomechanics and Tunnelling, 7(1), 31-44.

[11] Garg, A., & Tai, K. (2013). Comparison of statistical and machine learning methods in modelling of data with multicollinearity. International Journal of Modelling, Identification and Control, 18(4), 295-312.

[12] Géron, A. (2019). Hands-On Machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O’Reilly Media Inc.

[13] Ghasemi, E., & Gholizadeh, H. (2019). Prediction of squeezing potential in tunneling projects using data mining-based techniques. Geotechnical and Geological Engineering, 37(3), 1523-1532.

[14] Goldstein, A., Kapelner, A., Bleich, J., & Pitkin, E. (2015). Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. Journal of Computational and Graphical Statistics, 24(1), 44-65.

[15] Golpasand, M. B., Nikudel, M. R., & Uromeihy, A. (2013). Predicting the occurrence of mixed face conditions in tunnel route of Line 2 Tabriz metro, Tabriz, Iran. London: Global View of Engineering Geology and the Environment (pp. 487-492). London: Global View of Engineering Geology and the Environment.

[16] Hollmann, F. S., & Thewes, M. (2013). Assessment method for clay clogging and disintegration of fines in mechanised tunnelling. Tunnelling and Underground Space Technology, 37, 96-106.

[17] Jacobs, A. (2013). Northgate Link extension light rail project contract N125: TBM tunnels (UW to Maple Leaf Portal) geotechnical baseline report. Seattle: SoundTransit.

[18] Jeong, H., Kim, M., Lee, M., & Jeon, S. (2019). Analysis of advanced rate and downtime of a shield TBM encountering mixed ground and fault zone: A case study. Tunnel and Underground Space, 29(6), 394-406.

[19] Jeong, H., Zhang, N., & Jeon, S. (2018). Review of technical issues for shield TBM tunneling in difficult grounds. Tunnel and Underground Space, 28(1), 1-24.

[20] Jung, J. H., Chung, H., Kwon, Y. S., & Lee, I. M. (2019). An ANN to predict ground condition ahead of tunnel face using TBM operational data. KSCE Journal of Civil Engineering, 23(7), 3200-3206.

[21] Kelleher, J. D., Namee, B. M., & D’Arcy, A. (2020). Fundamentals of machine learning for predictive data analytics, second edition: algorithms, worked examples, and case studies. MIT Press.

[22] Koller, D., & Friedman, N. (2009). Probabilistic graphical models: principles and techniques. MIT Press.

[23] Lehmann, G., Käsling, H., Hoch, S., & Thuro, K. (2024). Analysis and prediction of small-diameter TBM performance in hard rock conditions. Tunnelling and Underground Space Technology, 143, 105442.

[24] Liu, Q. S., Wang, X. Y., Huang, X., & Yin, X. (2020). Prediction model of rock mass class using classification and regression tree integrated AdaBoost algorithm based on TBM driving data. Tunnelling and Underground Space Technology, 106, 103595.

[25] Ma, H. S., Yin, L. J., Gong, Q. M., & Wang, J. (2015). TBM tunneling in mixed-face ground: problems and solutions. International Journal of Mining Science and Technology, 25(4), 641-647.

[26] Maidl, U. (2003). Geotechnical and mechanical interactions using the earth-pressure balanced shield technology in difficult mixed face and hard rock conditions. Vortrag RETC.

[27] Merrie, M. (2009). Trials and tribulations-An overview of slurry tunnelling in challenging ground conditions. In Proceeding of underground Singapore 2009 (pp. 12-32).

[28] Mokhtari, S., & Mooney, M. A. (2020). Predicting EPBM advance rate performance using support vector regression modeling. Tunnelling and Underground Space Technology, 104, 103520.

[29] Mokhtari, S., Navidi, W., & Mooney, M. (2020). White-box regression (elastic net) modeling of earth pressure balance shield machine advance rate. Automation in Construction, 115, 103208.

[30] Mooney, M. A., Wu, Y., Parikh, D., & Mori, L. (2017). EPB granular soil conditioning under pressure. Geotechnical Aspects of Underground Construction in Soft Ground, 33-46.

[31] Mori, L., Alavi, E., & Mooney, M. (2017). Apparent density evaluation methods to assess the effectiveness of soil conditioning. Tunnelling and Underground Space Technology, 67, 175-186.

[32] Mosavat, K. (2015). Examination of excavation chamber pressure behavior on a 17.5 m diameter earth pressure balance tunnel boring machine [Master’s thesis, Colorado School of Mines]. The Mines Repository.

[33] 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(3), 1263-1276.

[34] Oliveira, D. G. G., Thewes, M., Diederichs, M. S., & Langmaack, L. (2018). EPB tunnelling through clay-sand mixed soils: proposed methodology for clogging evaluation. Geomechanics and Tunnelling, 11(4), 375-387.

[35] Oliveira, D. G., Thewes, M., Diederichs, M. S., & Langmaack, L. (2019). Consistency index and its correlation with EPB excavation of mixed clay-sand soils. Geotechnical and Geological Engineering, 37(1), 327-345.

[36] Ong, C. W., Ee, J. P., Su, T., Yong, K. Y., & Kulaindran, A. (2016). A case study of twin bored tunnelling under mixed-face soil-Bendemeer MRT station project (Downtown Line 3), Singapore. Japanese Geotechnical Society Special Publication, 2(2), 176-181.

[37] Page, E. S. (1954). Continuous inspection schemes. Biometrika, 41(1-2), 100-115.

[38] Panichella, A. (2021). A systematic comparison of search-based approaches for LDA hyperparameter tuning. Information and Software Technology, 130, 106411.

[39] Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12(85), 2825-2830.

[40] Probst, P., Bischl, B., & Boulesteix, A. -L. (2018). Tunability: importance of hyperparameters of machine learning algorithms. ArXiv:1802.09596 [Stat].

[41] Qin, C., Liu, M., Zhang, Z., Yu, H., Jin, Y., Sun, H., Tao, J., & Liu, C. (2023). An adaptive operating parameters decision-making method for shield machine considering geological environment. Tunnelling and Underground Space Technology, 141, 105372.

[42] Ray, S., & Page, D. (2001). Multiple instance regression. In Proceedings of the eighteenth international conference on machine learning, ICML ’01 (pp. 425-432). Morgan Kaufmann Publishers Inc..

[43] Sarna, S., Gutierrez, M., Mooney, M., & Zhu, M. Q. (2022). Predicting upcoming collapse incidents during tunneling in rocks with continuation length based on influence zone. Rock Mechanics and Rock Engineering, 55(10), 5905-5931.

[44] Shan, F., He, X., Armaghani, D. J., Zhang, P., & Sheng, D. (2022). Success and challenges in predicting TBM penetration rate using recurrent neural networks. Tunnelling and Underground Space Technology, 130, 104728.

[45] Shan, F., He, X., Armaghani, D. J., Zhang, P., & Sheng, D. (2023). Response to discussion on ‘‘Success and challenges in predicting TBM penetration rate using recurrent neural networks” by Georg H Erharter, Thomas Marcher. Tunnelling and Underground Space Technology incorporating Trenchless Technology Research, 139, 105064.

[46] Sheil, B. (2021). Discussion of “on the pointlessness of machine learning based time delayed prediction of TBM operational data” by Georg H. Erharter and Thomas Marcher. Automation in Construction, 124, 103559.

[47] Sousa, R. L., & Einstein, H. H. (2012). Risk analysis during tunnel construction using Bayesian Networks: Porto Metro case study. Tunnelling and Underground Space Technology, 27(1), 86-100.

[48] Steingrıómsson, J. H., Grøv, E., & Nilsen, B. (2002). The significance of mixed face conditions for TBM performance. World Tunneling, 15(9), 435-441.

[49] Su, T. (2015). Study on ground behaviour associated with tunnelling in mixed-face soil condition [Ph. D Thesis, National University of Singapore]. NUS Libraries.

[50] Tóth, Á., Gong, Q., & Zhao, J. (2013). Case studies of TBM tunneling performance in rock-soil interface mixed ground. Tunnelling and Underground Space Technology, 38, 140-150.

[51] Vergara, I. M., & Saroglou, C. (2017). Prediction of TBM performance in mixed-face ground conditions. Tunnelling and Underground Space Technology, 69, 116-124.

[52] Wang, X., Zhu, H., Zhu, M., Zhang, L., & Ju, J. W. (2021). An integrated parameter prediction framework for intelligent TBM excavation in hard rock. Tunnelling and Underground Space Technology, 118, 104196.

[53] Wang, Z., Zoghi, M., Hutter, F., Matheson, D., & De Freitas, N. (2013). Bayesian optimization in high dimensions via random embeddings. In Twenty-third international joint conference on artificial intelligence (pp.1778-1784). AAAI Press/International Joint Conferences on Artificial Intelligence.

[54] Xie, X. Y., Wang, Q., Huang, Z. H., & Qi, Y. (2018). Parametric analysis of mixshield tunnelling in mixed ground containing mudstone and protection of adjacent buildings: Case study in Nanning metro. European Journal of Environmental and Civil Engineering, 22(sup1), s130-s148.

[55] Xu, Q. H., Huang, X., Zhang, B. G., Zhang, Z. X., Wang, J. H., & Wang, S. F. (2023). TBM performance prediction using LSTM-based hybrid neural network model: Case study of Baimang River tunnel project in Shenzhen, China. Underground Space, 11, 130-152.

[56] Yi, K. H., Tong, S. Y., Casasuó s, A., Tang, S. K., & Yoon, J. W. (2014). Tunnelling in mixed ground condition-a challenge to design and construction. World tunnel congress 2014- tunnels for a better life.

[57] Yu, H. J., & Mooney, M. (2023). Characterizing the as-encountered ground condition with tunnel boring machine data using semisupervised learning. Computers and Geotechnics, 154, 105159.

[58] Yu, H. J. (2021). Using TBM-generated data for pressure modeling, ground characterization and optimal control in earth pressure balance tunneling [Ph. D Thesis, Colorado School of Mines]. The Mines Repository.

[59] Yu, H. J., Mooney, M., & Bezuijen, A. (2020). A simplified excavation chamber pressure model for EPBM tunneling. Tunnelling and Underground Space Technology, 103, 103457.

[60] Zhang, Q. L., Liu, Z. Y., & Tan, J. R. (2019). Prediction of geological conditions for a tunnel boring machine using big operational data. Automation in Construction, 100, 73-83.

[61] Zhang, Z. Q., Zhang, K. J., Dong, W. J., & Zhang, B. (2020). Study of rock-cutting process by disc cutters in mixed ground based on threedimensional particle flow model. Rock Mechanics and Rock Engineering, 53(8), 3485-3506.

[62] Zhao, J., Gong, Q. M., & Eisensten, Z. (2007). Tunnelling through a frequently changing and mixed ground: A case history in Singapore. Tunnelling and Underground Space Technology, 22(4), 388-400.

[63] Zhao, J. H., Shi, M. L., Hu, G., Song, X. G., Zhang, C., Tao, D. C., & Wu, W. (2019). A data-driven framework for tunnel geological-type prediction based on TBM operating data. IEEE Access, 7, 66703-66713.

[64] Zhao, Y., Lehman, B., Ball, R., Mosesian, J., & de Palma, J.-F. (2013). Outlier detection rules for fault detection in solar photovoltaic arrays. In 2013 twenty-eighth annual IEEE applied power electronics conference and exposition (APEC) (pp. 2913-2920). IEEE.

[65] Zhou, C., Gao, Y. Y., Chen, E. J., Ding, L. Y., & Qin, W. B. (2023). Deep learning technologies for shield tunneling: challenges and opportunities. Automation in Construction, 154, 104982.

[66] Zhu, M. Q., Gutierrez, M., Zhu, H. H., Ju, J. W., & Sarna, S. (2021). Performance Evaluation Indicator (PEI): A new paradigm to evaluate the competence of machine learning classifiers in predicting rockmass conditions. Advanced Engineering Informatics, 47, 101232.