Assessment of rate of penetration of a tunnel boring machine in the longest railway tunnel of Turkey

Abstract

One of the most important issues in tunnels to be constructed with tunnel boring machines (TBMs) is to predict the excavation time. Excavation time directly affects tunnel costs and feasibility. For this reason, studies on the prediction of TBM performance have always been interesting for tunnel engineers. Therefore, the purpose of the study is to develop models to predict the rate of penetration (ROP) of TBMs. In accordance with the purpose of the study, a new database including 5334 cases is obtained from the longest railway tunnel of Turkey. Each case includes uniaxial compressive strength, Cerchar Abrasivity Index, α angle, weathering degree and water conditions as input or independent variables. Two multiple regression models and two ANN models are developed in the study. The performances of the ANN models are considerably better than those of the multiple regression equations. Before deep tunnel construction in a metamorphic rock medium, the ANN models developed in the study are reliable and can be used. In contrast, the performances of the multiple regression equations are promising, but they predict lower ROP values than the measured ROP values. Consequently, the prediction models for ROP are open to development depending on the new data and new prediction algorithms.

Prediction of the Undrained Shear Strength of the Remolded Soil with Non-Linear Regression, Fuzzy Logic and Artificial Neural Network

“…Table6indicate that Fuzzy logic (FL) and artificial neuron network gave more accurate results (𝑅𝑀𝑆𝐸, 𝑀𝐴𝐸 and 𝑅 2 ) than traditional non-linear regression analyses. Similar finding has been reported by several researchers(Işık 2009;Akan and Keskin 2019;Taleb Bahmed et al 2019;Mbarak et al 2020;Akbay Arama et al 2021;Gökçeoğlu 2022;Saadat and Bayat 2022) for prediction of geotechnical engineering parameters. The best performance was observed in Eq.…”

“…In this study, the experimental data set is divided randomly such that 70 % of samples were used for training, 15% for validation and, 15 % for testing. Similar percent of training, validation and testing have been recommended by several researchers(Kalkan et al 2009;Dehghanbanadaki et al 2019;Moayedi and Hayati 2019;Taleb Bahmed et al 2019;Abu-Farsakh and Mojumder 2020;Moayedi et al 2020;Akbay Arama et al 2021;Tabarsa et al 2021;Armaghani et al 2022;Gökçeoğlu 2022;Lin et al 2022).The average coefficient of correlation values (𝑅) from ANN model were determined as 0.9761, 0.9778, 0.9663, and 0.9748 for training, validation, test and finally using complete dataset, respectively as presented in Fig.6.…”

“…where 𝑅 𝑀 is an emprical coefficient (30 for kaolin and 100 for montmorillonite). and rock mechanics and tunneling (Mohamad et al 2018;Naghadehi et al 2019;Gökçeoğlu 2022).…”

A Geotechnical Perspective on a Complex Geological Environment in a High-Speed Railway Tunnel Excavation (A Case Study from Türkiye)

“…In the last decade, Türkiye has started to construct high-speed railways among the largest cities such as Ankara-Istanbul, Ankara-Sivas, and Ankara-Izmir. During these construction efforts, several tunnels have been constructed [17][18][19][20]. One of these tunnels is the T26 tunnel in the Ankara-Istanbul High-Speed Railway construction project.…”

6 February 2023 Kahramanmaraş – Türki̇ye Earthquakes: A General Overview

“…For this reason, some segments of the EAFZ were seismic gaps, and hence, the region was a high seismic potential. Consequently, some severe earthquakes were expected in the region (Nalbant et al, 2002;Gokceoglu, 2022;Can et al, 2022).…”