• Tunnel and Underground Space
• /
• v.29 no.6
• /
• pp.508-522
• /
• 2019

Because of the slope failure, not only property damage but also human damage can occur, slope stability analysis should be conducted to predict and reinforce of the slope. This paper, defines the ground areas that can be characterized in terms of slope failure such as Rockmass jointset, Rockmass fault, Soil, Leakage water and Crush zone in sloped images. As a result, it was shown that the deep learning instance segmentation network can be used to recognize and automatically segment the precise shape of the ground region with different characteristics shown in the image. It showed the possibility of supporting the slope mapping work and automatically calculating the ground characteristics information of slopes necessary for decision making such as slope reinforcement.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.47 no.9
• /
• pp.642-648
• /
• 2019

In this study, Image-based computational analysis using the developed models was performed to predict the degradation of effective properties by ablation. The ablation tests of carbon/phenolic composites were performed using a 0.4 MW arc-heated wind tunnel. The carbon/phenolic composite samples were scanned using the micro-computed tomography (Micro-CT) to analyze the ablation characteristics according to a duration time of the ablation test. By calibrating the scanned images, computational models were developed that reflect the actual microstructure of the ablation composites. Also, nine computational models that reflect the actual pore shape were developed using the created cross-sectional images. Image-based computational analysis using the developed models was performed to predict the degradation of effective properties by ablation and the decrease of effective properties was confirmed with increase of porosity.

• Tunnel and Underground Space
• /
• v.29 no.3
• /
• pp.184-196
• /
• 2019

This study aims to extract a 3D image of micro-cracks generated by hydraulic fracturing tests, using the deep learning method and X-ray computed tomography images. The pixel-level cracks are difficult to be detected via conventional image processing methods, such as global thresholding, canny edge detection, and the region growing method. Thus, the convolutional neural network-based encoder-decoder network is adapted to extract and analyze the micro-crack quantitatively. The number of training data can be acquired by dividing, rotating, and flipping images and the optimum combination for the image augmentation method is verified. Application of the optimal image augmentation method shows enhanced performance for not only the validation dataset but also the test dataset. In addition, the influence of the original number of training data to the performance of the deep learning-based neural network is confirmed, and it leads to succeed the pixel-level crack detection.

• The Journal of Engineering Geology
• /
• v.10 no.3
• /
• pp.237-245
• /
• 2000

This study was for characterizing the engineering geological properties of Moryang Fault, and providing the basic data for tunnel design. Land-sat image analysis, geologic surveys, resistivity prospecting and 3-dimensional analysis for results of resistivity prospecting, core boring, mineralogical identification and chemical analysis for the bedrock, and K-Ar age dating for fault clay were carried out for the study of Moryang Fault which is located at Duckhyunri Sangbukmyun Uljinkun Ulsan metropolis. As a result of the study, it was shown that strike/dip was N20-3$0^{\circ}C$E/70-9$0^{\circ}C$NW, width of fault ranged from 20 to 60m(maximum 80m), and depth was more than 50m. K-Ar age dating results of fault clay were 5,700$\pm$1.129Ma and 1,900$\pm$0.380Ma. Hydraulic fracturing test results showed the principal stress direction similar to the strike of Moryang Fault.

• Journal of Aerospace System Engineering
• /
• v.12 no.4
• /
• pp.57-63
• /
• 2018

IR thermography is a non-invasive method and used for the visualization of the surface temperature of the model. However, this technique only derives 2D results and not quantitative data. The goal of this study is to apply the 3D mapping technique for IR thermography. The wind tunnel model is an ogive-cylinder with a wind speed of 20 m/s ~ 80 m/s and the angle of attack ranging from $0^{\circ}$ to $90^{\circ}$. The real location of the model was made to correspond with the position of the IR image using the makers. Based on this result, quantitative results were obtained. The 3D mapping method was verified by comparing the separation point and the theoretical value.

• Geotechnical Engineering
• /
• v.14 no.4
• /
• pp.91-102
• /
• 1998

Electrical resistivity method, one of the most widely used geophysical prospecting methods. has been usually applied to explorations for groundwater and underground resources. However, it has been extending its scope to civil & environmental engineering areas since it twas been developed so as to image underground structures effectively. A FEM algorithm for the dipole-dipole array was developed to correct topographic effects which have a serious influence on electrical methods. Applicability of the electrical resistivity imaging technique to civil & environmental engineering areas was verified through three case histories in this study First, thickness of soil layers was profiled to judge the possibility of developing borrow-pits tn an industrial complect site. Second, weak zones such as fractures and coal seams were detected to provide geological information for design and construction in a high mountain tunnel site. Third, horizontal/vertical distribution of the contaminated zone and depth of waste disposal were delineated in a completed industrial waste disposal site.

• Journal of the Society of Naval Architects of Korea
• /
• v.50 no.5
• /
• pp.324-333
• /
• 2013

Recently, rudder erosion due to cavitation has been frequently reported on a semi-spade rudder of a high-speed large ship. This problem raises economic and safety issues when operating ships. The semi-spade rudders have a gap between the horn/pintle and the movable wing part. Due to this gap, a discontinuous surface, cavitation phenomenon arises and results in unresolved problems such as rudder erosion. In this study, we made a rudder model for 2-D experiments using the NACA0020 and also manufactured gap flow blocking devices to insert to the gap of the model. In order to study the gap flow characteristics at various rudder deflection angles($5^{\circ}$, $10^{\circ}$, $35^{\circ}$) and the effect of the gap flow blocking devices, we carried out the velocity measurements using PIV(Particle Image Velocimetry) techniques and cavitation observation using high speed camera in Seoul National University cavitation tunnel. To observe the gap cavitation on a semi-spade rudder, we slowly lowered the inside pressure of the cavitation tunnel until cavitation occurred near the gap and then captured it using high-speed camera with the frame rate of 4300 fps(frame per second). During this procedure, cavitation numbers and the generated location were recorded, and these experimental data were compared with CFD results calculated by commercial code, Fluent. When we use gap flow blocking device to block the gap, it showed a different flow character compared with previous observation without the device. With the device blocking the gap, the flow velocity increases on the suction side, while it decreases on the pressure side. Therefore, we can conclude that the gap flow blocking device results in a high lift-force effect. And we can also observe that the cavitation inception is delayed.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.6
• /
• pp.1161-1175
• /
• 2018

An unexpected event could be easily followed by a large secondary accident due to the limitation in sight of drivers in road tunnels. Therefore, a series of automated incident detection systems have been under operation, which, however, appear in very low detection rates due to very low image qualities on CCTVs in tunnels. In order to overcome that limit, deep learning based tunnel incident detection system was developed, which already showed high detection rates in November of 2017. However, since the object detection process could deal with only still images, moving direction and speed of moving vehicles could not be identified. Furthermore it was hard to detect stopping and reverse the status of moving vehicles. Therefore, apart from the object detection, an object tracking method has been introduced and combined with the detection algorithm to track the moving vehicles. Also, stopping-reverse discrimination algorithm was proposed, thereby implementing into the combined incident detection processes. Each performance on detection of stopping, reverse driving and fire incident state were evaluated with showing 100% detection rate. But the detection for 'person' object appears relatively low success rate to 78.5%. Nevertheless, it is believed that the enlarged richness of image big-data could dramatically enhance the detection capacity of the automatic incident detection system.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.5
• /
• pp.200-209
• /
• 2018

This study proposed a method to select existing facilities as a landmark in order to reset accumulated errors of dead reckoning in a tunnel difficult to receive GNSS signals in automated driving. First, related standards and regulations were reviewed in order to survey 'variety' on shapes and installation locations as a feature of facilities. Second, 'recognition' on facilities was examined using image and Lidar sensors. Last, 'regularity' in terms of installation locations and intervals was surveyed through related references. The results of this study selected a fire fighting box / lamp (50m), an evacuation corridor lamp (300m), a lane control system (500m), a maximum / minimum speed limit sign and a jet fan as a candidate landmark to reset positioning errors. Based on those facilities, it was determined that error correction was possible. The results of this study are expected to be used in repositioning of automated driving vehicles in a tunnel.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.3
• /
• pp.419-432
• /
• 2019

Most of deep learning model training was proceeded by supervised learning, which is to train labeling data composed by inputs and corresponding outputs. Labeling data was directly generated manually, so labeling accuracy of data is relatively high. However, it requires heavy efforts in securing data because of cost and time. Additionally, the main goal of supervised learning is to improve detection performance for 'True Positive' data but not to reduce occurrence of 'False Positive' data. In this paper, the occurrence of unpredictable 'False Positive' appears by trained modes with labeling data and 'True Positive' data in monitoring of deep learning-based CCTV accident detection system, which is under operation at a tunnel monitoring center. Those types of 'False Positive' to 'fire' or 'person' objects were frequently taking place for lights of working vehicle, reflecting sunlight at tunnel entrance, long black feature which occurs to the part of lane or car, etc. To solve this problem, a deep learning model was developed by simultaneously training the 'False Positive' data generated in the field and the labeling data. As a result, in comparison with the model that was trained only by the existing labeling data, the re-inference performance with respect to the labeling data was improved. In addition, re-inference of the 'False Positive' data shows that the number of 'False Positive' for the persons were more reduced in case of training model including many 'False Positive' data. By training of the 'False Positive' data, the capability of field application of the deep learning model was improved automatically.