JOURNAL OF ROCK MECHANICS

JOURNAL OF ROCK MECHANICS

Assessing the Impact of TBM Operational Parameters on Penetration Rate through Machine Learning and Multi-Stage Feature Selection

Document Type : Original Article

Authors
Armin Fallahi 1
Seyed Mosleh Eftekhari 2
Ehsan Taheri 1
1 Faculty of Mining and Materials, Tarbiat Modares University, Tehran, Iran
2 Faculty of Engineering, Tarbiat Modares University, Tehran, Iran.
10.22034/irsrm.2025.539943.1053
Abstract
In recent years, machine learning (ML) models have garnered increasing attention for predicting the penetration rate (PR) of tunnel boring machines (TBMs), a key performance indicator in mechanized tunneling projects. However, many previous studies have been limited to comparing a few algorithms and have lacked a comprehensive sensitivity analysis regarding operational parameters. In this study, four ML algorithms—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF)—were evaluated for predicting the PR of a TBM based on real-world operational data from the long Zagros tunnel. To enhance model performance, effective features were selected from an initial set of 17 parameters using a hybrid approach combining mutual information and the Binary Grey Wolf Optimizer (BGWO). The models were then trained and assessed using performance metrics such as RMSE, MAE, and the coefficient of determination (R²). Among the models, the RF algorithm demonstrated the highest prediction accuracy and generalization capability. In the final stage, a multivariate sensitivity analysis was conducted using the RF model to investigate the individual and combined effects of controllable operational parameters—namely thrust force, torque, and cutterhead rotation speed—on the PR. The findings highlight the critical role of balanced parameter tuning in optimizing TBM performance and suggest that ML models can serve as valuable decision-support tools in mechanized tunneling operations.
Keywords
Tunnel Boring Machine (TBM)
Machine Learning
Penetration Rate Prediction
Sensitivity Analysis
Feature Selection
Operational Parameters
Subjects
1.            Maidl B, Schmid L, Ritz W, Herrenknecht M. Hardrock tunnel boring machines. John Wiley & Sons; 2008.
2.            Askilsrud OG. Development of TBM technology for hard rock conditions. Norwegian TBM Tunnelling. 1998:35.
3.            Rostami J. Design optimization, performance prediction and economic analysis of tunnel boring machines for the construction of the proposed yucca mountain nuclear waste repository. 1992.
4.            Gong Q, Jiao Y, Zhao J. Numerical modelling of the effects of joint spacing on rock fragmentation by TBM cutters. Tunnelling and Underground Space Technology. 2006;21(1):46-55.
5.            Eftekhari S, Baghbanan A, Bagherpour R. Numerical modeling of the effect of geometrical parameters of fractures on penetration rate of TBM in fractured rock mass. Journal of Mining Engineering. 2013;8(18):1-12.
6.            Eftekhari M, Baghbanan A, Bagherpour R. The effect of fracture patterns on penetration rate of TBM in fractured rock mass using probabilistic numerical approach. Arabian Journal of Geosciences. 2014;7(12):5321-5331.
7.            Pourhashemi SM, Ahangari K, Hassanpour J, Eftekhari SM. Evaluating the influence of engineering geological parameters on TBM performance during grinding process in limestone strata. Bulletin of Engineering Geology and the Environment. 2021;80(4):3023-3040.
8.            Pourhashemi SM, Ahangari K, Hassanpour J, Eftekhari SM. TBM performance analysis in very strong and massive rocks; case study: Kerman water conveyance tunnel project, Iran. Geomechanics and Geoengineering. 2022;17(4):1110-1122.
9.            Pourhashemi SM, Ahangari K, Hassanpour J, Eftekhari SM. Penetration rate analysis for tunnel boring machine in grinding conditions. Journal of Mining Engineering. 2021;16(52):79-88.
10.          Pourhashemi SM, Ahangari K, Hassanpour J, Eftekhari SM. Analysis of Grinding and Chipping Processes beneath Disc Cutters of Hard Rock Tunnel Boring Machines (Case study: Uma-Oya water Conveyance Tunnel, SriLanka). Journal of Mining and Environment. 2021;12(1):281-297.
11.          Eftekhari SM, Bastami M. Effect of the replacement of cutting tools on the performance of TBM in Tehran metro line 6. Journal of Analytical and Numerical Methods in Mining Engineering. 2020;10(24):63-76.
12.          Bruland A. Hard rock tunnel boring advance rate and cutter wear. Trondheim: Norwegian Institute of Technology. 1999.
13.          Ozdemir L. CSM computer model for TBM performance prediction. Colorado School of Mines. 2003.
14.          Nilsen B, Ozdemir L. Hard rock tunnel boring prediction and field performance. Paper presented at: Proceedings of the rapid excavation and tunneling conference1993.
15.          Barton N. TBM performance estimation in rock using QTBM. T & T international. 1999;31(9):30-34.
16.          Sapigni M, Berti M, Bethaz E, Busillo A, Cardone G. TBM performance estimation using rock mass classifications. International Journal of Rock Mechanics and Mining Sciences. 2002;39(6):771-788.
17.          Hamidi JK, Shahriar K, Rezai B, Rostami J. Performance prediction of hard rock TBM using Rock Mass Rating (RMR) system. Tunnelling and Underground Space Technology. 2010;25(4):333-345.
18.          Farrokh E, Rostami J, Laughton C. Study of various models for estimation of penetration rate of hard rock TBMs. Tunnelling and Underground Space Technology. 2012;30:110-123.
19.          Eftekhari M, Baghbanan A, Bayati M. Predicting penetration rate of a tunnel boring machine using artificial neural network. Paper presented at: ISRM International Symposium-Asian Rock Mechanics Symposium2010.
20.          Yagiz S, Karahan H. Prediction of hard rock TBM penetration rate using particle swarm optimization. International Journal of Rock Mechanics and Mining Sciences. 2011;48(3):427-433.
21.          Maher J. A Machine learning approach to predicting and maximizing penetration rates in Earth Pressure Balance Tunnel Boring Machines. Special Interest Group in Computer Science Education (SIGCSE). 2013.
22.          Mokhtarian M, Eftekhari M, Baghbanan A. Application of principal component analysis in prediction of penetration rate of TBM using artificial neural networks. Journal of Analytical and Numerical Methods in Mining Engineering. 2014;3(6):33-43.
23.          Yagiz S, Karahan H. Application of various optimization techniques and comparison of their performances for predicting TBM penetration rate in rock mass. International Journal of Rock Mechanics and Mining Sciences. 2015;80:308-315.
24.          Xu H, Zhou J, G. Asteris P, Jahed Armaghani D, Tahir MM. Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate. Applied sciences. 2019;9(18):3715.
25.          Yang H, Wang Z, Song K. A new hybrid grey wolf optimizer-feature weighted-multiple kernel-support vector regression technique to predict TBM performance. Engineering with Computers. 2022;38(3):2469-2485.
26.          Li J, Li P, Guo D, Li X, Chen Z. Advanced prediction of tunnel boring machine performance based on big data. Geoscience Frontiers. 2021;12(1):331-338.
27.          Yang J, Yagiz S, Liu Y-J, Laouafa F. Comprehensive evaluation of machine learning algorithms applied to TBM performance prediction. Underground space. 2022;7(1):37-49.
28.          Eftekhari M, Eftekhari N. A predictive model for estimating the TBM penetration rate based on hybrid ICA-ANN and DEA-AHP algorithms. Geotechnical and Geological Engineering. 2022;40(6):3191-3209.
29.          Latif K, Sharafat A, Seo J. Digital Twin-Driven Framework for TBM Performance Prediction, Visualization, and Monitoring through Machine Learning. Applied Sciences. 2023;13(20):11435.
30.          Yu Z, Li C, Zhou J. Tunnel Boring Machine Performance Prediction Using Supervised Learning Method and Swarm Intelligence Algorithm. Mathematics. 2023;11(20):4237.
31.          Hu W, Wu K, Liu H, Luo W, Li X, Guan P. Interpretable machine learning approach for TBM tunnel crown convergence prediction with Bayesian optimization. Frontiers in Earth Science. 2025;13:1608468.
32.          Li L, Liu Z, Fang X, Qi W. Multi-step real-time prediction of hard-rock TBM penetration rate combining temporal convolutional network and squeeze-and-excitation block. Scientific Reports. 2024;14(1):14326.
33.          Zhang M, Ji A, Zhou C, Ding Y, Wang L. Real-time prediction of TBM penetration rates using a transformer-based ensemble deep learning model. Automation in Construction. 2024;168:105793.
34.          Kilic K, Narihiro O, Ikeda H, Adachi T, Kawamura Y. Soft ground micro TBM jack speed and torque prediction using machine learning models through operator data and micro TBM-log data synchronization. Scientific Reports. 2024;14:9728.
35.          Abbasi M, Namadchi AH, Abbasi M, Abbasi M. Evaluation of machine learning algorithms in tunnel boring machine applications: a case study in Mashhad metro line 3. International Journal of Geo-Engineering. 2024;15(1):28.
36.          Ghorbani E, Yagiz S. Estimating the penetration rate of tunnel boring machines via gradient boosting algorithms. Engineering Applications of Artificial Intelligence. 2024;136:108985.
37.          Liu J, Liang F, Wei K, Zuo C. Prediction Model for Cutterhead Rotation Speed Based on Dimensional Analysis and Elastic Net Regression. Applied Sciences. 2025;15(3):1298.
38.          ساحل مم. مهندسین مشاور ساحل، مطالعات زمین‌شناسی مهندسی مسیر تونل، گزارش.2026، 1386. .
39.          Peng H, Long F, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on pattern analysis and machine intelligence. 2005;27(8):1226-1238.
40.          Singh H, Saxena S, Sharma H, et al. An integrative TLBO-driven hybrid grey wolf optimizer for the efficient resolution of multi-dimensional, nonlinear engineering problems. Scientific Reports. 2025;15(1):11205.
41.          Cover T, Hart P. Nearest neighbor pattern classification. IEEE transactions on information theory. 1967;13(1):21-27.
42.          Quinlan JR. Induction of decision trees. Machine learning. 1986;1(1):81-106.
43.          Cortes C, Vapnik V. Support-vector networks. Machine learning. 1995;20(3):273-297.
44.          Breiman L. Random forests. Machine learning. 2001;45(1):5-32.
JOURNAL OF ROCK MECHANICS
Volume 9, Issue 1
Spring 2025
Pages 61-79