Study on the Classification and Identification Methods of Surrounding Rock Excavatability Based on the Rock-Breaking Performance of Tunnel Boring Machines

Abstract

Rock mass conditions are extremely sensitive to tunnel boring machine (TBM) tunneling. Therefore, establishing a surrounding rock excavatability (SRE) classification system applicable to TBM tunnels. Accurately and intelligently identifying excavatability grades can also facilitate efficient TBM tunneling and intelligent construction. Specific excavation and penetration rates were used to evaluate SRE. Their correlations with geological and tunneling parameters were explored using the field data from two water conveyance tunnels in China with different lithologies. A high-precision empirical SRE classification system was constructed using TOPSIS for multi-objective decision-making, and it was verified using engineering cases. An intelligent identification model for SRE grades in the stable phase of a TBM excavation cycle was established using 12,382 TBM rock-breaking datasets and deep forest models. Ten characteristic parameters, e.g., total thrust, were selected as model input features. Hyperparameter optimization was achieved using the grid search method. Deep forest was compared with decision tree, random forest, support vector classifier, and deep neural network. The contribution of the model’s features was measured using random forest. The main conclusions are as follows: the proposed SRE classification method is feasible and matches well with the actual excavation. In the intelligent identification of SRE classification, the accuracy and F1 scores when using deep forest were 96.33% and 0.9581, respectively. Deep forest exhibited better grade identification performance than the four models. Among the ten input features, penetration is the most important feature for the model’s input, while the top shield cylinder rod’s chamber pressure is the least important. The findings can provide some references for SRE classification and prediction and intelligent TBM control.

Evaluation and Application of Surrounding Rock Stability Based on an Improved Fuzzy Comprehensive Evaluation Method

“…For example, the interval number of I1 to I3 is [3,5], which indicates that the expert considers the importance of the two indicators to range between moderately important and strongly important. The interpretation of other interval numbers follows a similar pattern.…”

“…In this case,  = 0.99 < 1 and  = 1.014 > 1, indicating that the weight calculation is qualified by the consistency test. And the subjective weight of each factor For example, the interval number of I 1 to I 3 is [3,5], which indicates that the expert considers the importance of the two indicators to range between moderately important and strongly important. The interpretation of other interval numbers follows a similar pattern.…”

“…Numerous scholars have developed different evaluation methods based on various theories, which can be classified into analytical, numerical, and machine-learning approaches. Analytical methods include the Protodyakonov coefficient (f), rock quality designation (RQD), Q, and rock mass rating (RMR) method [5]. The Protodyakonov coefficient is simple but may introduce errors due to changes in stress states resulting from laboratory measurements [6].…”

Safety Evaluation of Crossing Tunnel Engineering: A Case Study

“…However, both the on-site observation and physical models have drawbacks as are they costly and time-consuming [20]. The development of computer technology has led to the widespread adoption of numerical simulation in the field of safety assessment [21][22][23][24]. In the evaluation of tunnel support design, Kadir Yertutanol [25] employed a finite element numerical simulation analysis to predict the vertical displacements of a tunnel during its construction.…”