• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.469-484
• /
• 2021

Rock mass classification results have a great influence on construction schedule and budget as well as tunnel stability in tunnel design. A total of 3,526 tunnels have been constructed in Korea and the associated techniques in tunnel design and construction have been continuously developed, however, not many studies have been performed on how to assess rock mass quality and grade more accurately. Thus, numerous cases show big differences in the results according to inspectors' experience and judgement. Hence, this study aims to suggest a more reliable rock mass classification (RMR) model using machine learning algorithms, which is surging in availability, through the analyses based on various rock and rock mass information collected from boring investigations. For this, 11 learning parameters (depth, rock type, RQD, electrical resistivity, UCS, V_p, V_s, Young's modulus, unit weight, Poisson's ratio, RMR) from 13 local tunnel cases were selected, 337 learning data sets as well as 60 test data sets were prepared, and 6 machine learning algorithms (DT, SVM, ANN, PCA & ANN, RF, XGBoost) were tested for various hyperparameters for each algorithm. The results show that the mean absolute errors in RMR value from five algorithms except Decision Tree were less than 8 and a Support Vector Machine model is the best model. The applicability of the model, established through this study, was confirmed and this prediction model can be applied for more reliable rock mass classification when additional various data is continuously cumulated.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.3
• /
• pp.247-262
• /
• 2022

In domestic tunnels, it is mandatory to install CCTVs in tunnels longer than 200 m which are also recommended by installation of a CCTV-based automatic accident detection system. In general, the CCTVs in the tunnel are installed at a low height as well as near by the moving vehicles due to the spatial limitation of tunnel structure, so a severe perspective effect takes place in the distance of installed CCTV and moving vehicles. Because of this effect, conventional CCTV-based accident detection systems in tunnel are known in general to be very hard to achieve the performance in detection of unexpected accidents such as stop or reversely moving vehicles, person on the road and fires, especially far from 100 m. Therefore, in this study, the region of interest is set up and a new concept of inverse perspective transformation technique is introduced. Since moving vehicles in the transformed image is enlarged proportionally to the distance from CCTV, it is possible to achieve consistency in object detection and identification of actual speed of moving vehicles in distance. To show this aspect, two datasets in the same conditions are composed with the original and the transformed images of CCTV in tunnel, respectively. A comparison of variation of appearance speed and size of moving vehicles in distance are made. Then, the performances of the object detection in distance are compared with respect to the both trained deep-learning models. As a result, the model case with the transformed images are able to achieve consistent performance in object and accident detections in distance even by 200 m.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.4
• /
• pp.327-339
• /
• 2022

The purpose of this study is to present the effective smoke control flow rate and mode for securing safety through quantitative risk assessment according to the smoke control flow rate and mode (supply or exhaust) of the platform when a train fire occurs at the subway platform. To this end, a fire outbreak scenario was created using a side platform with a central staircase as a model and fire analysis was performed for each scenario to compare and analyze fire propagation characteristics and ASET, evacuation analysis was performed to predict the number of deaths. In addition, a fire accident rate (F)/number of deaths (N) diagram (F/N diagram) was prepared for each scenario to compare and evaluate the risk according to the smoke control flow rate and mode. In the ASET analysis of harmful factors, carbon monoxide, temperature, and visible distance determined by performance-oriented design methods and standards for firefighting facilities, the effect of visible distance is the largest, In the case where the delay in entering the platform of the fire train was not taken into account, the ASET was analyzed to be about 800 seconds when the air flow rate was 4 × 833 m³/min. The estimated number of deaths varies greatly depending on the location of the vehicle of fire train, In the case of a fire occurring in a vehicle adjacent to the stairs, it is shown that the increase is up to three times that of the vehicle in the lead. In addition, when the smoke control flow rate increases, the number of fatalities decreases, and the reduction rate of the air supply method rather than the exhaust method increases. When the supply flow rate is 4 × 833 m³/min, the expected number of deaths is reduced to 13% compared to the case where ventilation is not performed. As a result of the risk assessment, it is found that the current social risk assessment criteria are satisfied when smoke control is performed, and the number of deaths is the flow rate 4 × 833 m³/min when smoke control is performed at 29.9 people in 10,000 year, It was analyzed that it decreased to 4.36 people.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.11 no.4
• /
• pp.327-351
• /
• 2009

Laboratory tests are performed in this paper to investigate the brittle failure characteristics of over-stressed rocks taken in deep depth. Also, numerical simulation performed using that the so-called CWFS(Cohesion Weakening Frictional Strengthening) model is known to predict brittle failure phenomenon reasonably well. The most typical rock types of Korean peninsula - granite and gneiss - were used for testing. Results of uniaxial compression tests showed that the crack initiation stress was about 41 % to 42% of the uniaxial compressive strength regardless of rock types, where as, the crack damage stress of granite was about 75%, and that of gneiss was about 97%. Through the damage-controlled test, strength parameters of each rock were obtained as a function of damage degree. After the peak, the crack damage stress and the maximum stress were decreased, The cohesion was decreased and the friction angle was increased with increase of rock damage. Before reaching the peak, the elastic modulus was slightly increased, while decreased after the peak. Poisson's ratio was increased as the damage of rock proceeds. Comparison of uniaxial compression tests and damage-controlled tests shows the crack initiation stress estimated from the damage-controlled test fluctuated within the range of crack initiation stress obtained from the uniaxial compression test; the crack damage stress was less than that estimated from the uniaxial compression test. In order to predict the critical depth that brittle failure occurs, numerical simulations using the CWFS model were performed for an example site. Material parameters obtained from the laboratory tests mentioned above were used for CWFS simulation. Comparison between the critical depth predicted from the numerical simulation using the CWFS model and that predicted by using the damage index proposed by Martin et al.(l999), showed that critical depth cannot be reasonably predicted by the currently used damage index except for circular tunnels. A modified damage index was proposed by the author which takes the shape of tunnels other than circular into account.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.4
• /
• pp.261-283
• /
• 2023

This study aimed to review the performance stability of PET (Polyethylene terephthalate) fiber reinforcing materials among the synthetic fiber types for which the application of performance reinforcing materials to fiber-reinforced concrete is being reviewed by examining short-term and long-term performance changes. To this end, the residual performance was analyzed after exposing the PET fiber to an acid/alkali environment, and the flexural strength and equivalent flexural strength of the PET fiber-reinforced concrete mixture by age were analyzed, and the surface of the PET fiber collected from the concrete specimen was examined using a scanning microscope (SEM). The changes in were analyzed. As a result of the acid/alkali environment exposure test of PET fiber, the strength retention rate was 83.4~96.4% in acidic environment and 42.4~97.9% in alkaline environment. It was confirmed that the strength retention rate of the fiber itself significantly decreased when exposed to high-temperature strong alkali conditions, and the strength retention rate increased in the finished yarn coated with epoxy. In the test results of the flexural strength and equivalent flexural strength of the PET fiber-reinforced concrete mixture, no reduction in flexural strength was found, and the equivalent flexural strength result also did not show any degradation in performance as a fiber reinforcement. Even in the SEM analysis results, no surface damage or cross-sectional change of the PET reinforcing fibers was observed. These results mean that no damage or cross-section reduction of PET reinforcing fibers occurs in cement concrete environments even when fiber-reinforced concrete is exposed to high temperatures in the early stage or depending on age, and the strength of PET fibers decreases in cement concrete environments. The impact is judged to be of no concern. As the flexural strength and equivalent flexural strength according to age were also stably expressed, it could be seen that performance degradation due to hydrolysis, which is a concern due to the use of PET fiber reinforcing materials, did not occur, and it was confirmed that stable residual strength retention characteristics were exhibited.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.4
• /
• pp.305-330
• /
• 2023

Unlike NATM tunnels, Shield TBM tunnels have split linings. Therefore, the stress distribution of the lining is different even if the lining is under the same load. Representative methods for analyzing the stress generated in lining in Shield TBM tunnels include Non-joint Mode that does not consider connections and a 2-ring beam-spring model that considers ring-to-ring joints and segment connections. This study is an analysis method by Break-joint Mode. However, we do not consider the structural role of segment lining connections. The effectiveness of the modeling is verified by analyzing behavioral characteristics against vibration loads by modeling with segment connection interfaces to which vertical stiffness and shear stiffness, which are friction components, are applied. Unlike the Non-joint mode, where the greatest stress occurs on the crown for static loads such as earth pressure, the stress distribution caused by contact between segment lining and friction stiffness produced the smallest stress in the crown key segment where segment connections were concentrated. The stress distribution was clearly distinguished based on segment connections. The results of static analysis by earth pressure, etc., produced up to seven times the stress generated in Non-joint mode compared to the stress generated by Break-joint Mode. This result is consistent with the stress distribution pattern of the 2-ring beam-spring model. However, as for the stress value for the train vibration load, the stress of Break-joint Mode was greater than that of Non-joint mode. This is a different result from the static mechanics concept that a segment ring consisting of a combination of short members is integrated in the circumferential direction, resulting in a smaller stress than Non-joint mode with a relatively longer member length.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.11 no.1
• /
• pp.57-70
• /
• 2009

Considerable advance has been made on research on effect of steel pipe Umbrella Arch Method (UAM) and mechanical reinforcement mechanism through numerical analyses and experiments. Due to long analysis time of three-dimensional analysis and its complexity, un-quantitative two-dimensional analysis is dominantly used in the design and application, where equivalent material properties of UAM reinforced area and ground are used, For this reason, development of reasonable, theoretical, quantitative and easy to use design and analysis method is required. In this study, both field UAM tests and laboratory tests were performed in the residual soil to highly weathered rock; field tests to observe the range of reinforcement, and laboratory tests to investigate the change of material properties between prior to and after UAM reinforcement. It has been observed that the increase in material property of neighboring ground is negligible, and that only stiffness of steel pipe and cement column formed inside the steel pipe and the gap between steel pipe and borehole contributes to ground reinforcement. Based on these results and concept of Convergence Confinement Method (CCM), two dimensional axisymmetric analyses have been performed to obtain the longitudinal displacement profile (LDP) corresponding to arching effect of tunnel face, UAM effect and effect of supports. In addition, modified load distribution method in two dimensional plane-strain analysis has been suggested, in which effect of UAM is transformed to internal pressure and modified load distribution ratios are suggested. Comparison between the modified method and conventional method shows that larger displacement occur in the conventional method than that in the modified method although it may be different depending on ground condition, depth and size of tunnel, types of steel pipe and initial stress state. Consequently, it can be concluded that the effect of UAM as a beam in a longitudinal direction is not considered properly in the conventional method.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.423-446
• /
• 2023

Shield TBM tunnel linings are segmented into segments and rings. This study investigates the response characteristics of the stress and displacement of the segment lining under seismic waves through modeling that considers the interface behavior between segments by applying a shell interface element to the contact surface between segments and rings. And there is no management criteria for ovaling deformation of segment linings in Korea. So, this study the ovality criteria and meaning of segment lining. The results of study showed that the distribution patterns of stress and displacement under seismic waves were similar between continuous linings and segment linings. However, the maximum values of stress and displacement showed differences from segment linings. The stress distribution of the continuous lining modeled as a shell type has a stress distribution that has continuity in the 3D cylindrical shape, but the segment lining is concentrated outside the segment, and the largest stress occurs at the location where the contact surface between the segment and the ring is concentrated. This intermittent and localized stress distribution shows an increasing as the ovality of the lining increases at seismic waves. The ovality at which the increase in stress distribution begins to show irregularity and localization is about 150‰. Ovality of 150‰ is an unrealistic value that cannot represent actual lining deformation. Therefore, the ovality of the segment lining increase with depth, but it does not have a significant impact on the stability caused by seismic load.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.583-603
• /
• 2023

Recently, the advancement of mechanical tunnel boring machine (TBM) technology and the characteristics of subsea railway tunnels subjected to hydrostatic pressure have led to the widespread application of shield TBM methods in the design and construction of subsea railway tunnels. Subsea railway tunnels are exposed in a constant pore water pressure and are influenced by the amplification of seismic waves during earthquake. In particular, seismic loads acting on subsea railway tunnels under various ground conditions such as soft ground, soft soil-rock composite ground, and fractured zones can cause significant changes in tunnel displacement and stress, thereby affecting tunnel safety. Additionally, the dynamic response of the ground and tunnel varies based on seismic load parameters such as frequency characteristics, seismic waveform, and peak acceleration, adding complexity to the behavior of the ground-tunnel structure system. In this study, a finite difference method is employed to model the entire ground-tunnel structure system, considering hydrostatic pressure, for the investigation of dynamic behavior of subsea railway tunnel during earthquake. Since the key factors influencing the dynamic behavior during seismic events are ground conditions and seismic waves, six analysis cases are established based on virtual ground conditions: Case-1 with weathered soil, Case-2 with hard rock, Case-3 with a composite ground of soil and hard rock in the tunnel longitudinal direction, Case-4 with the tunnel passing through a narrow fault zone, Case-5 with a composite ground of soft soil and hard rock in the tunnel longitudinal direction, and Case-6 with the tunnel passing through a wide fractured zone. As a result, horizontal displacements due to earthquakes tend to increase with an increase in ground stiffness, however, the displacements tend to be restrained due to the confining effects of the ground and the rigid shield segments. On the contrary, peak compressive stress of segment significantly increases with weaker ground stiffness and the effects of displacement restrain contribute the increase of peak compressive stress of segment.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.