Introducing tree-based-regression models for prediction of hard rock TBM performance with consideration of rock type

Abstract

Prediction of machine performance is a fundamental step for planning, cost estimation/control and selection of the machine type when using a tunnel boring machine (TBM). Penetration rate (PR) and machine utilization (U) are the two principal measures of TBM performance for evaluating the feasibility of using a machine in a given ground condition. However, despite the widespread use of TBMs and established track records, accurate estimation of machine performance could still be a challenge, particularly in complex geological conditions. Since different types of rocks have varied texture (cementation and grain size), and respond differently to cutting forces in the TBM tunnelling, incorporating the effects of rock type in performance prediction models can improve the accuracy of the estimates. The aim of this study was to develop models for predicting penetration rate of hard rock TBMs in different types of rock based on field penetration index (FPI), using multivariable regression analysis and machine learning algorithm, including classification and regression tree (CART). The proposed models offer estimated FPIs in different rock types, rock strength, and rock mass properties in the form of graphs (diagrams), which can be used to estimate TBM penetration rate. The proposed models have been developed based on the analysis of a comprehensive database of TBM performance in various rock types and offers more accurate estimates of machine performance by incorporating many of the key parameters available in typical geotechnical reports and contract documents. The models also exhibit sensitivity to rock mass parameters for predicting the penetration rate.