In tunneling a reliable prediction of advance rates is essential for calculating budget and construction time. Estimation of penetration rate is expressed as the basis for predicting advance rate in underground excavation using Tunnel Boring Machine. In this study the obtained data from 10KM of excavated Zagros tunnel project in Iran were subjected to statistical analyses using MATLAB for ANN modeling. When the neural network has been successfully trained, its performance is tested on a separate testing data set. Finally, the penetration rate was predicted by the trained neural network. The results show that the developed ANN method is efficient for predicting the PR in Zagros tunnel. The ANN model for next 0.5 KM which is recently excavated is well compatible with the real calculated PR of TBM in the field with 79% confident level. Result of sensibility analysis on the effect of Thrust and Torque on the PR shows that the maximum PR in given ground condition occurred in the optimum limits of Thrust and Torque.


Since the first Tunnel Boring Machine (TBM) was built, the performance analysis and the development of accurate prediction models of the machines have been the ultimate goals of many research works [1–9]. A reliable prediction of TBM performance is needed for time planning and budget control of projects. Both penetration rate (PR) and advance rate (AR) are estimated in performance prediction of TBM. Penetration rate is defined as the distance excavated divided by the operating time during a continuous excavation phase, while advance rate is the actual distance mined and supported divided by the total time [10]. The AR includes downtimes for TBM maintenance, machine breakdown and tunnel failure. Even in stable rock, the rate of advance is considerably lower than the net rate of penetration and utilization coefficients (U%=(AR/PR)×100) is estimated about 30–50% mainly due to a TBM daily maintenance. When low quality rocks are excavated, the penetration rate could potentially be very high. However it demands a strong support pattern and face to rock jams and gripper bearing failure which results a relatively low advance rate with utilization coefficients about 5- 10% [11]. According to the literature, important parameters in TBM performance could be categorized in two major parts as follows:

  1. Ground Condition: It includes characteristic parameters of intact rock and rock mass properties. Mostly reported important properties of intact rock in TBM performance are Uniaxial Compressive Strength (UCS), Brazilian Tensile Strength (BTS) and Point load index (Is50). In terms of Rock Mass properties, discontinuity spacing (Js), Rock Quality Designation (RQD), the angle between the tunnel axis and the planes of weakness (Discontinuity Dip and Dip Direction), rock mass quality using classification system such as RMR, Q and GSI have significant impact on TBM performance.

  2. TBM operational parameters such as value of thrust, torque, Round Per Minute (RPM) and disc specifications have great influence on TBM performance. Tarkoy (1973) presented a model to predict penetration rate of TBM using only total hardness of intact rocks.

This content is only available via PDF.
You can access this article if you purchase or spend a download.