Machine learning forecasting models of disc cutters life of tunnel boring machine

Abstract This study aims to propose four Machine Learning methods of Gaussian process regression (GPR), support vector regression (SVR), decision trees (DT), and K-nearest neighbors (KNN) to predict disc cutter's life of TBM. 200 datasets monitored during the Alborz service tunnel construction in Iran, including TBM operational parameters, geometry, and geological conditions, were applied in the models. The 5-fold cross-validation method was considered to investigate the prediction performance of the models. Finally, the GPR model with R2 = 0.8866/RMSE = 107.3554, was the most accurate model to predict TBM disc cutter's life. KNN model with R2 = 0.1753/RMSE = 288.9277, produced the minimum accuracy. To assess each parameter's contribution in the prediction problem, the backward selection method was used. The results showed that TF, RPM, PR, and Qc parameters significantly contribute to TBM disc cutter's life. However, RPM and PR parameters were more and less significant compared to the others.

[1]  Bing Zhang,et al.  The Derivation and Validation of TBM Disc Cutter Wear Prediction Model , 2018, Geotechnical and Geological Engineering.

[2]  M. Monjezi,et al.  Study of the influence of geotechnical parameters on the TBM performance in Tehran–Shomal highway project using ANN and SPSS , 2013, Arabian Journal of Geosciences.

[3]  Anthony T. C. Goh,et al.  Multivariate adaptive regression splines and neural network models for prediction of pile drivability , 2016 .

[4]  Ryan P. Adams,et al.  Gradient-based Hyperparameter Optimization through Reversible Learning , 2015, ICML.

[5]  Wengang Zhang,et al.  Reliability assessment on stability of tunnelling perpendicularly beneath an existing tunnel considering spatial variabilities of rock mass properties , 2019, Tunnelling and Underground Space Technology.

[6]  Jin Dalong,et al.  Effect of Spatial Variability on Disc Cutters Failure During TBM Tunneling in Hard Rock , 2020, Rock Mechanics and Rock Engineering.

[7]  J. Hassanpour.  Development of an empirical model to estimate disc cutter wear for sedimentary and low to medium grade metamorphic rocks , 2018 .

[8]  Ahmad Basheer Hassanat,et al.  Solving the Problem of the K Parameter in the KNN Classifier Using an Ensemble Learning Approach , 2014, ArXiv.

[9]  Adam Glowacz,et al.  Acoustic fault analysis of three commutator motors , 2019, Mechanical Systems and Signal Processing.

[10]  B. Park,et al.  Choice of neighbor order in nearest-neighbor classification , 2008, 0810.5276.

[11]  Mokhtar Mohammadi,et al.  Dynamic reduction of time and cost uncertainties in tunneling projects , 2021 .

[12]  Annan Zhou,et al.  Optimization of EPB Shield Performance with Adaptive Neuro-Fuzzy Inference System and Genetic Algorithm , 2019, Applied Sciences.

[13]  Tarik A. Rashid,et al.  Updating ground conditions and time-cost scatter-gram in tunnels during excavation , 2019, Automation in Construction.

[14]  Yang Xiao,et al.  Determination of earth pressure balance tunnel-related maximum surface settlement: a multivariate adaptive regression splines approach , 2018, Bulletin of Engineering Geology and the Environment.

[15]  T. N. Michalakopoulos,et al.  The influence of steel styli hardness on the Cerchar abrasiveness index value , 2006 .

[16]  Yoshua Bengio,et al.  Algorithms for Hyper-Parameter Optimization , 2011, NIPS.

[18]  Yimin Xia,et al.  Design Optimization of TBM Disc Cutters for Different Geological Conditions , 2015 .

[19]  Haiqing Yang,et al.  Effects of joints on the cutting behavior of disc cutter running on the jointed rock mass , 2018, Tunnelling and Underground Space Technology.

[20]  Kurosch Thuro,et al.  Testing conditions and geomechanical properties influencing the CERCHAR abrasiveness index (CAI) value , 2003 .

[21]  Wengang Zhang,et al.  Investigation on passive pile responses subject to adjacent tunnelling in anisotropic clay , 2020 .

[22]  Hunar Farid Hama Ali,et al.  Forecasting tunnel geology, construction time and costs using machine learning methods , 2020, Neural Computing and Applications.

[23]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[24]  Rabar H. Faraj,et al.  Decision-making in tunneling using artificial intelligence tools , 2020 .

[25]  Shui-Long Shen,et al.  Prediction of Disc Cutter Life During Shield Tunneling with AI via the Incorporation of a Genetic Algorithm into a GMDH-Type Neural Network , 2020 .

[26]  Tristan Mary-Huard,et al.  Theoretical Analysis of Cross-Validation for Estimating the Risk of the $k$-Nearest Neighbor Classifier , 2015, J. Mach. Learn. Res..

[27]  S. Shen,et al.  Analytical approach for time‐dependent groundwater inflow into shield tunnel face in confined aquifer , 2018 .

[28]  Adam Glowacz,et al.  Fault diagnosis of electric impact drills using thermal imaging , 2021 .

[29]  Xiao-Ping Zhang,et al.  A Wear Rule and Cutter Life Prediction Model of a 20-in. TBM Cutter for Granite: A Case Study of a Water Conveyance Tunnel in China , 2017, Rock Mechanics and Rock Engineering.

[30]  Defang Zou,et al.  Theoretical Research and Simulation Analysis on the Cutter Spacing of Double Disc Cutters Breaking Rock , 2019, KSCE Journal of Civil Engineering.

[31]  A. Mahmoodzadeh,et al.  Artificial intelligence forecasting models of uniaxial compressive strength , 2020 .

[32]  Mokhtar Mohammadi,et al.  Tunnel geomechanical parameters prediction using Gaussian process regression , 2021 .

[33]  A. Mahmoodzadeh,et al.  Dynamic prediction models of rock quality designation in tunneling projects , 2021 .

[34]  Mikhail Bilenko,et al.  Lazy Paired Hyper-Parameter Tuning , 2013, IJCAI.

[35]  Cong Li,et al.  Theoretical prediction of wear of disc cutters in tunnel boring machine and its application , 2019, Journal of Rock Mechanics and Geotechnical Engineering.

[36]  Mokhtar Mohammadi,et al.  Forecasting sidewall displacement of underground caverns using machine learning techniques , 2021 .

[37]  Qing Tan,et al.  Performance Prediction of TBM Disc Cutting on Marble Rock under Different Load Cases , 2018 .

[38]  Rebaz Mohammed Dler Omer,et al.  Forecasting maximum surface settlement caused by urban tunneling , 2020 .