• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.4
• /
• pp.519-534
• /
• 2019

Mechanized tunneling methods, including shield TBM, have been increasingly used for tunnel construction because of their relatively low vibration and noise levels as well as low risk of rock-falling accidents. In the excavation using the shield TBM, it is important to design penetration rate appropriately. In present study, both subsurface investigation data and shield TBM excavation data, produced for and during ${\bigcirc}{\bigcirc}{\sim}{\bigcirc}{\bigcirc}$ high-speed railway construction, were analyzed and used to compare with shield TBM penetration rates calculated using existing penetrating rate prediction models proposed by several foreign researchers. The correlation between thrust force per disk cutter and uniaxial compressive strength was also examined and, based on the correlation analysis, a simple prediction model for penetration rate was derived. The prediction results using the existing prediction models showed approximately error rates of 50~500%, whereas the results from the simple model proposed from this study showed an error rate of 15% in average. It may be said, therefore, that the proposed model has higher applicability for shield TBM construction in similar ground conditions.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.575-589
• /
• 2020

In recent years, Shield TBM construction has been continuously increasing in domestic tunnels. The main excavation tool in the shield TBM construction is a disc cutter which naturally wears during the excavation process and significantly degrades the excavation efficiency. Therefore, it is important to know the appropriate time of the disc cutter replacement. In this study, it is proposed a predictive model that can determine yes/no of disc cutter replacement using machine learning algorithm. To do this, the shield TBM machine data which is highly correlated to the disc cutter wears and the disc cutter replacement from the shield TBM field which is already constructed are used as the input data in the model. Also, the algorithms used in the study were the support vector machine, k-nearest neighbor algorithm, and decision tree algorithm are all classification methods used in machine learning. In order to construct an optimal predictive model and to evaluate the performance of the model, the classification performance evaluation index was compared and analyzed.

• Magazine of korean Tunnelling and Underground Space Association
• /
• v.20 no.2
• /
• pp.12-16
• /
• 2018

• Magazine of korean Tunnelling and Underground Space Association
• /
• v.19 no.3
• /
• pp.6-12
• /
• 2017

• Magazine of korean Tunnelling and Underground Space Association
• /
• v.19 no.4
• /
• pp.11-16
• /
• 2017

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.255-264
• /
• 2023

As the demand for urban underground space increases recently, urban tunnel planning is actively progressing. In the urban area, a underground station is planned in consideration of the living environment of residents, and 2-arch tunnel is applied for the stability of existing structures and reduction of environmental damage. However, since the depth of weak rock mass is deeply distributed in the urban area due to severe weathering, careful planning is required to secure tunnel stability. In addition, if TBM mechanical excavation is applied as the main tunnel excavation method considering the composite ground in urban area, the construction connectivity with the 2-arch tunnel of the NATM concept may be deteriorated. In this study, the design case of applying TBM pre-excavation type 2-arch tunnel for the first time in Korea was mainly described. The main considerations for the segment design of TBM pre-excavation type 2-arch tunnel were explained for side tunnels. Also, a stability analysis was conducted to verify the effectiveness and adequacy of the TBM pre-excavation type 2-arch tunnel.

• Tunnel and Underground Space
• /
• v.29 no.6
• /
• pp.394-406
• /
• 2019

Difficult ground conditions (e.g., fault zone and mixed grounds) are highly probable to appear in subsea and urban tunnels because of the shallow working depth and alluvial characteristics. TBM usually experienced decrease of penetration rate and increase of downtime when it meets these difficult ground conditions. The problems are usually caused by the adverse geological conditions, and it is preferable to determine the optimal operational parameters of TBM based on the previous operational data obtained while excavating a preceding tunnel. This study carried out for efficient TBM excavation in fault zone and mixed grounds. TBM excavation data from the tunnel site in Singapore and the characteristics of the TBM excavation data was analyzed. The key operational parameters (i.e., thrust, torque, and RPM), penetration rate, and downtime were highly influenced by the presence of fault zones and mixed grounds, and the features was discussed. It is expected that the results and main discussions will be useful information for future tunneling projects in similar geological conditions.

• Tunnel and Underground Space
• /
• v.30 no.3
• /
• pp.214-225
• /
• 2020

Uniaxial compressive strength (UCS) of rock is one of the important factors to determine the advance speed during shield TBM tunnel excavation. UCS can be obtained through the Geotechnical Data Report (GDR), and it is difficult to measure UCS for all tunneling alignment. Therefore, the purpose of this study is to predict UCS by utilizing TBM machine driving data and machine learning technique. Several machine learning techniques were compared to predict UCS, and it was confirmed the stacking model has the most successful prediction performance. TBM machine data and UCS used in the analysis were obtained from the excavation of rock strata with slurry shield TBMs. The data were divided into 8:2 for training and test and pre-processed including feature selection, scaling, and outlier removal. After completing the hyper-parameter tuning, the stacking model was evaluated with the root-mean-square error (RMSE) and the determination coefficient (R²), and it was found to be 5.556 and 0.943, respectively. Based on the results, the sacking models are considered useful in predicting rock strength with TBM excavation data.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.6
• /
• pp.857-870
• /
• 2017

The use of shield TBM is gradually increasing due to the urbanization of social infrastructures. Reliable estimation of advance rate is very important for accurate construction period and cost. For this purpose, it is required to develop the prediction model of advance rate that can consider the ground properties reasonably. Based on the database collected from field, statistical prediction procedure for field penetration index (FPI) was modularized in this study to calculate penetration rate of shield TBM. As output parameter, FPI was selected and various systems were included in this module such as, procedure of eliminating abnormal dataset, preprocessing of dataset and ridge regression with best subset selection. And it was finally validated by using field dataset.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.16 no.2
• /
• pp.161-172
• /
• 2014

An earth pressure balanced shield TBM with the diameter of 4.4 m was designed and manufactured for a subsea discharge tunnel excavation. Its cutterhead was designed to be optimized for the strongest rock mass condition in the tunnel alignment, and then the applicability of the refurbished shield TBM was validated for its maximum capacity. Especially, the maximum cutter penetration depth for the strongest rock mass condition should be kept to be below 7 mm/rev in order to satisfy the allowable capacities of the shield TBM. From the analysis of TBM advance data, approximately 95% of field data showed the cutter penetration depth below 7 mm/rev. In addition, it was certified that the acting forces of every disc cutter, TBM thrust and torque during TBM driving were within the allowable capacities of the shield TBM and its disc cutters. When real acting forces of the disc cutters in the field were compared with those predicted by the CSM model, they showed the close relationships with each other even though the predictions by the CSM model were approximately 22~25% higher than field data.