Towards TBM Automation: On-The-Fly Characterization and Classification of Ground Conditions Ahead of a TBM Using Data-Driven Approach

Abstract

Pre-tunneling exploration for rock mass classification is a common practice in tunneling projects. This study proposes a data-driven approach that allows for rock mass classification. Two machine learning (ML) classification models, namely random forest (RF) and extremely randomized tree (ERT), are employed to classify the rock mass conditions encountered in the Pahang-Selangor Raw Water Tunnel in Malaysia using tunnel boring machine (TBM) operating parameters. Due to imbalance of rock classes distribution, an oversampling technique was used to obtain a balanced training dataset for unbiased learning of the ML models. A five-fold cross-validation approach was used to tune the model hyperparameters and validation-set approach was used for the model evaluation. ERT achieved an overall accuracy of 95%, while RF achieved 94% accuracy, in rightly classifying rock mass conditions. The result shows that the proposed approach has the potential to identify and correctly classify ground conditions of a TBM, which allows for early problem detection and on-the-fly support system selection based on the identified ground condition. This study, which is part of an ongoing effort towards developing reliable models that could be incorporated into TBMs, shows the potential of data-driven approaches for on-the-fly classification of ground conditions ahead of a TBM and could allow for the early detection of potential construction problems.

Prediction of rock mass class ahead of TBM excavation face by ML and DL algorithms with Bayesian TPE optimization and SHAP feature analysis

“…Kim et al [30] established a random forest (RF) model to predict surface settlement levels. Sebbeh-Newton et al [48] used RF and extremely randomized trees (ET) to classify geological conditions using TBM operational parameters. The accuracy of ET and RF reached 95% and 94%, respectively.…”

Failure in the Tension Zone around a Circular Tunnel Excavated in Saturated Porous Rock

“…These studies outlined that the influence of groundwater on the behavior of the rock mass surrounding a tunnel is very important because it can cause severe tunneling problems, such as due to either physical deterioration of the components of the rock mass or the reduction of the effective stress confinement due to pore water pressure [10,14,16,23].…”

“…This pore pressure induces negative effective stresses (Figure 1a), which result in a state of stress in the tension zone (Figure 1b) close to the boundary of the excavation. Rock mass classification schemes aim at classifying and characterizing the rock masses and provide a basis for estimating deformation and strength properties for the design of underground excavation and support [1,[23][24][25]. In some classification schemes, attempts are made to account for the influence of groundwater pressure or flow on the stability of underground excavations [1,[23][24][25][26].…”

FB2Droid: A Novel Malware Family-Based Bagging Algorithm for Android Malware Detection

“…In other words, the large number of samples of a certain type leads to the "bias" of the classifier towards such samples, thus affecting the detection effect. Traditional classification algorithms have achieved good results in the balanced datasets, but the actual datasets are often unbalanced, and the traditional algorithms are sensitive to unbalanced data and have poor detection effects, such as SVM [3,4] and RF [5,6].…”