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

• Published in: Acta geotechnica Vol. 18; no. 7; pp. 3825 - 3848
• Main Authors: Chen, Cheng, Seo, Hyungjoon
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.07.2023; Springer Nature B.V
• Subjects: Accuracy; Additives; Algorithms; Artificial neural networks; Bayesian analysis; Bayesian theory; Classifiers; Complex Fluids and Microfluidics; Data acquisition; Decision trees; Deep learning; Dredging; Engineering; Excavation; Foundations; Geoengineering; Geotechnical Engineering & Applied Earth Sciences; Hydraulics; Long short-term memory; Machine learning; Mathematical models; Model accuracy; Neural networks; Optimization; Outliers (landforms); Outliers (statistics); Parameters; Prediction models; Probability theory; Research Paper; Soft and Granular Matter; Soil Science & Conservation; Solid Mechanics; Support vector machines; Rock mass prediction; SHAP; Xgboost; Bayesian optimization; Ground condition prediction; TBM
• ISSN: 1861-1125; 1861-1133; 1861-1133
• DOI: 10.1007/s11440-022-01779-z

In this paper, field construction data from the Singapore Metro Line project were used to study the mapping relationship and establish the prediction model between TBM operation data and the ground condition ahead of the excavation face. The study presents a multi-classifier competition mechanism to construct ten separate classifiers, including logistic regression, support vector machine, random forest, extremely randomized trees, adaptive boosting machine, extreme gradient boosting (Xgboost), light gradient boosting (LightGBM), categorical boosting, long short-term memory and convolutional neural network. The acquired data were used to select 28 key TBM operating parameters by a correlation-based feature selection method, and the selected parameters in the stabilization phase after removing the outliers were calculated as the input to the classifier, and a relatively balanced training set was obtained by the synthetic minority oversampling technique. The hyperparameters of each classifier were optimized using tree Parzen estimator Bayesian optimization. The prediction results show that LightGBM presents the best results among ten different machine and deep learning algorithms with an accuracy of 96.22%, precision of 96.94%, recall of 97.33% and F1-score of 97.33%. In addition, the effect of the input parameters of the LightGBM model on the prediction accuracy of the model was analyzed using Shapley additive explanations, and the effect of sample imbalance on the prediction performance was discussed.