MECHANISED TUNNELLING | TECHNICAL
of cutting forces required on disc cutter to achieve certain penetration into rock. It offers the advantages of being able to consider geometry (diameter and tip geometry of the disc, and the spacing or distance between the grooves). However, the original model does not consider natural discontinuities in the rock mass, which have a major impact on net speed of progress of a TBM. To overcome this shortcoming, Yagiz (2002) and Ramezanzadeh (2005) modified the CSM model by adding some rock mass properties as input parameters, but with limited success. Bruland (1998) updated and improved the NTNU
model (originally proposed in 1978), based on field data from Norway and around the world. The method uses some rock property indices such as Drilling Rate Index (DRI), estimated from rock brittleness ‘S20 hardness index ‘SJ’, and also joint conditions to develop
’ and
the estimated rate of TBM penetration (Blindheim 1979). It requires specialised tests not commonly performed in many projects. FPI was introduced by Nelson et al. (1983) and
used subsequently for predicting TBM performance. For instance, Hassanpour et al. (2011, 2016, 2021), Pourhashemi et al. (2021), and Goodarzi et al. (2021) used FPI estimated as a function of uniaxial compressive strength (UCS) and rock quality designation (RQD) to develop new equations and charts. Apart from empirical and theoretical models, the use
of ML techniques has received widespread attention. As a branch of artificial intelligence (AI), ML develops algorithms to generalise behaviours from sampled information. It is an inductive knowledge strategy (Salimi 2021, Coimbra et al. 2014), and its capabilities and opportunities for use in tunnel construction have been discussed by Marcher et al. (2020) and Morgenroth et al. (2019). The flexible nature of AI techniques makes them powerful tools in approximating and solving engineering
problems more specifically when the problem is highly complex and non-linear. However, while the results of most studies show high correlation between predicted rates and actual machine performance, they cannot be used to estimate on other projects as their related programs are not available to end users. Further, most ML methods are difficult to apply as they need large quantities of data for the parameters, either provided or estimated. Consequently, while they can predict the value of a target variable depending on data used, the rules or implicit patterns within the model cannot be interpreted. In the area of rock engineering/tunnelling, the suitability of data mining techniques is closely related to the applicability of the resulting model (Salimi 2021). The main goal of the present work is to develop new
models to estimate TBM performance using FPI via statistical analysis (regression analysis), as well as ML including tree-based-regression model such as CART. More attention is paid to introduce new models that incorporate the similarities in rock texture, cementation and grain size.
PROJECTS IN TBM PERFORMANCE DATABASE For the study, field data were compiled from eight tunnelling projects: Zagros water conveyance tunnel (Lot 2), Iran; Ghomrood water conveyance tunnel (Lots 3 & 4), Iran; Karaj water conveyance tunnel, (Lot 1), Iran; Golab conveyance water tunnel, Iran; Maroshi-Ruparel water supply tunnel, in Mumbai, India; Manapouri second tailrace tunnel, New Zealand; Deep Tunnel Sewerage System (DTSS), in Singapore; and, Lötschberg Base Tunnel, Switzerland. TBM performance data from the projects, with the
different rock mass conditions, were compiled into a TBM field performance database. For this investigation, the data cover a total length of 92.93km of bored tunnel, (See Table 1).
Table 1: Main characteristics of tunnelling projects Projects
TBM-D1
Ghomrood water conveyance tunnel, Lots 3 and 4 (Iran)
Manapouri second tailrace tunnel (New Zealand)
Golab conveyance water tunnel (Iran)
supply tunnel Mumbai, (India)
Zagros water conveyance tunnel, Lot 2 (Iran)
Karaj water conveyance tunnel, Lot 1 (Iran)
Lötschberg Base Tunnel (Switzerland)
Deep Tunnel Sewerage System (Singapore)
1 Diameter; 2 Length; 3 Available Data; 4 Maroshi-Ruparel water 4.525 10.5 4.495 3.6 6.73 4.65 9.43 4.82–4.45 Maroshi-Vakola; 5
(m) Tunnel-L2 21.5 10 10 12.24 26 15.9 36.4 38.5
(km) AD3
(km) 15 9.7 8 5.834 15 8.7 8.55 22.26 Steg lateral adit, Main southern; 6
TBM type Double shield (Wirth) (Robbins, Kvaerner-Markham) Double shield (Wirth) Hard rock Gripper TBM (Wirth) Double shield (Herrenknecht) Double shield (Herrenknecht) Gripper TBM (Herrenknecht)
Hard rock shield TBM-EPB (Herrenknecht)
Only hard rock conditions (T05 and T06) Main beam open TBM
Lithology
Limestone, Shale and Sandstone, Slate, Phyllite, Schist with quartzitic veins
Gneiss, Calc-silicate and quartzite and the intrusive rocks (Gabbro and Diorite)
Periodic series of argillite shale and metamorphic sandstone, schist and amphibolite
Xxxx
Fine compact basalt, Porphyritic basalt, Amygdaloidal basalt Pyroclastic rocks (Tuff, Tuff breccia) & Intertrappeans (Shale)...
Limestone, Shale and Limy Shales Tuffs, Shaly and Sandy Tuffs, Agglomerate
Crystalline Gneiss, Granodiorite & Granite, Granitic Gneiss, Amphibolite
Bukit Timah granite (slightly to completely decomposed granite, silt, sandstone...)
July 2024 | 17
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116 |
Page 117 |
Page 118 |
Page 119 |
Page 120 |
Page 121 |
Page 122 |
Page 123 |
Page 124 |
Page 125 |
Page 126 |
Page 127 |
Page 128 |
Page 129 |
Page 130 |
Page 131 |
Page 132 |
Page 133 |
Page 134 |
Page 135 |
Page 136 |
Page 137
