Perception model of surrounding rock geological conditions based on TBM operational big data and combined unsupervised-supervised learning

• Published in: Tunnelling and underground space technology Vol. 120; p. 104285
• Main Authors: Yin, Xin, Liu, Quansheng, Huang, Xing, Pan, Yucong
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01-02-2022; Elsevier BV
• Subjects: Algorithms; Big Data; Boring machines; Clustering; Data analysis; Data mining; Engineering; Feature extraction; Geology; Impact analysis; Kalman filters; Machine learning; Mathematical models; Model accuracy; Optimization; Outliers (statistics); Parameter identification; Perception; Perception model; Performance evaluation; Rocks; Supervised learning; Surrounding rock class; TBM; Tunnels; Unsupervised learning; Supervised learning; Surrounding rock class; TBM; Unsupervised learning; Perception model
• ISSN: 0886-7798; 1878-4364
• DOI: 10.1016/j.tust.2021.104285

•A novel intelligent perception model of surrounding rock class was proposed.•TBM cutterhead torque, thrust, penetration rate and rotational speed were chosen to conduct the study.•A complete perception framework was presented from data preprocessing to model construction.•Feature importance and class imbalance were discussed.
The perception of surrounding rock geological conditions ahead the tunnel face is essential for TBM safe and efficient tunnelling. This paper developed a perception approach of surrounding rock class based on TBM operational big data and combined unsupervised-supervised learning. In data preprocessing, four data mining techniques (i.e., Z-score, K-NN, Kalman filtering, and wavelet packet decomposition) were used to detect outliers, substitute outliers, suppress noise, and extract features, respectively. Then, GMM was used to revise the original surrounding rock class through clustering TBM load parameters and performance parameters in view of the shortcomings of the HC method in the TBM-excavated tunnel. After that, five various ensemble learning classification models were constructed to identify the surrounding rock class, in which model hyper-parameters were automatically tuned by Bayes optimization. In order to evaluate model performance, balanced accuracy, Kappa, F1-score, and training time were taken into account, and a novel multi-metric comprehensive ranking system was designed. Engineering application results indicated that LightGBM achieved the most superior performance with the highest comprehensive score of 6.9066, followed by GBDT (5.9228), XGBoost (5.4964), RF (3.7581), and AdaBoost (0.9946). Through the weighted purity reduction algorithm, the contributions of input features on the five models were quantitatively analyzed. Finally, the impact of class imbalance on model performance was discussed using the ADASYN algorithm, showing that eliminating class imbalance can further improve the model's perception ability.