• Journal of Korean Tunnelling and Underground Space Association
• /
• v.16 no.1
• /
• pp.13-24
• /
• 2014

This paper presents development of artificial neural network(ANN) based prediction method for section forces of TBM tunnel segment lining in an effort to develop an automatized design technique. A series of design cases were first developed and subsequently analyzed using the two-ring beam finite element model. The results were then used to form a database for use as training and validation data sets for ANN development. Using the database, optimized ANNs were developed that can readily be used to predict maximum sectional forces and their distributions. It is shown that the compute maximum section forces and their distributions by the developed ANNs are almost identical to the computed by the two-ring beam finite element model, implying that the developed ANNs can be used as design tools which expedite routine design calculation process. The results of this study indicate that the neural network model can be effectively used as a reliable and simple predictive tool for the prediction of segment sectional forces for design.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.17 no.1
• /
• pp.49-63
• /
• 2015

In this paper, the results of evaluation on the member forces in the virtual subsea tunnel lining segments and optimal thickness of the segment with changes in depth were presented. To evaluate member forces on the hypothetical subsea tunnelling cases were developed and the segmental lining member forces were calculated by performing structural analysis using the 2-Ring Beam model. Through a preliminary reinforcement design review of the cross-section using calculated member force, optimal reinforcement design was selected. Based on the results, the variations of member forces with construction conditions such as the cover depth and the hydraulic pressure are presented. In addition, optimum segment lining designs were developed for various tunnelling conditions.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.18 no.2
• /
• pp.195-211
• /
• 2016

This paper concerns a study of a knowledge-based NATM tunnel lining design for subsea tunnels. Concept for tunnel automation designing system, the development of Artificial Neural Network based technology of the tunnel design system, the learning process and verification of the technology forecasting member forces were described. The design system is the series of process which can predict segmental lining member forces by ANN(artificial neural network system), analyze suitable section for the designated ground, construction and tunnel conditions using a FEM(finite element analysis). The lining member forces are predicted based on the ANN quickly and it helps designers determine its segmental lining dimension easily.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.14 no.3
• /
• pp.159-181
• /
• 2012

The segment lining which consists of segments and joints are main component of shield tunnel. There are a number of methods that are being used in design which compute the sectional forces of a ring of segment lining. The traditional design methods which do not consider the effect of joints have been commonly used for design procedure without a specific verification of structural analysis. This paper presents the result of a comparative study for analytical and numerical models of the shield tunnel segment lining. For the traditional methods, the elastic equation method and the Duddeck & Erdmann method were considered. The ring-beam and the continuum analysis model were also considered as the numerical model.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.18 no.3
• /
• pp.319-329
• /
• 2016

Underground structures such as subsea tunnel having large section should be stable against seismic loads. In general, underground structures show more stable behavior due to the limited dynamic motion and force, and considerable energy dissipation; however, severe damage was reported from recent earthquakes. Therefore, more sophisticated and analytic approach is required to investigate the seismic response of underground structure like subsea tunnel. In this study, seismic analysis of virtual Honam-Jeju subsea tunnel are performed. Consequently, stresses and forces of tunnel lining increased at fractured and/or weak rock zones. Stresses and forces of tunnel lining also increased at large section under axially deformed condition; however, decrease under transversely deformed condition.

• Journal of the Korean Geosynthetics Society
• /
• v.17 no.4
• /
• pp.251-265
• /
• 2018

This paper concerns the development of an optimized NATM secondary lining design system for a subsea tunnel. The subsea tunnel is normally laid down under the sea water and submarine ground which consists of soil or rock. The design system is the series of process which can predict lining member forces by ANN (artificial neural network system), analyze suitable section for the designated ground, construction and tunnel conditions. Finally, this lining design system aims to be connected for designing the subsea tunnel automatically. The lining member forces are predicted based on the ANN which was calculated by a FEM (finite element analysis) and it helps designers determine its lining dimension easily without any further FEM calculations.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.17 no.3
• /
• pp.363-382
• /
• 2015

This paper presents a numerical study on the effect of segment assembly characteristics on the TBM segmental lining member section forces. Analyses have been carried out through the two-ring beam finite element model by Midas civil 2012+. TBM segment lining member forces are determined by various joint characteristics. In this study, the segmental member forces were investigated with various joint number and orientation at fixed values of joint stiffness, ground spring parameters. The numerical results were used to identify trends of the member forces in the tunnel lining with the segment assembly characteristics.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.16 no.3
• /
• pp.321-339
• /
• 2014

This paper concerns the development of a knowledge-based tunnel design system within the framework of artifical neural networks(ANNs). The system is aimed at expediting a routine tunnel design works such as computation of segment lining body forces and stability analysis of selected cross section. A number of sub-modules for computation of segment lining body forces and stability analysis were developed and implemented to the system. It is shown that the ANNs trained with the results of 3D numerical analyses can be generalized with a reasonable accuracy, and that the ANN based tunnel design concept is a robust tool for tunnel design optimization. The details of the system architecture and the ANNs development are discussed in this paper.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.17 no.3
• /
• pp.227-236
• /
• 2015

In impermeable ground, water pressure is applied due to discontinuity such as joint or fissure. Therefore, water pressure should be considered in design regardless of ground condition. However, when the shape of segmental lining is circular, water pressure may reduce the lining member force, so it is important to define the assumption and the concept of design in case of high water pressure. This paper presents the concepts of design of the lining of shield tunnel at high water pressure and in impermeable ground condition. In addition, the member forces in various load conditions were compared in this study. (elastic equation, closed form solutions, beam-spring model).

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.3 no.2
• /
• pp.13-22
• /
• 2001

In this study, numerical analyses on cut-and-cover tunnel linings were performed using different modeling methods based on both structural and geotechnical engineering. The purpose was to find a relatively more reasonable modeling method and boundary conditions. The results of the study revealed problems associated with each modeling method and factors influencing the behavior of cut-and-cover tunnel lining. A method was proposed allowing the simulation of field condition in a more rational way. It was indicated that, under the given conditions, displacements and member forces occurring on concrete lining could be different as much as 53% depending on the type of modeling method applied; and 32% depending on the boundary conditions employed. Determination of boundary conditions properly simulating actual field conditions and verification of prediction based on instrumentation are essential for rational design and analysis.