• Journal of Internet Computing and Services
• /
• v.19 no.6
• /
• pp.21-29
• /
• 2018

In the era of the 4-th industrial revolution, the concept of smart factory is emerging. There are efforts to predict the occurrences of facility errors which have negative effects on the utilization and productivity by using data analysis. Data composed of the situation of a facility error and the type of the error, called the facility error log, is required for the prediction. However, in many manufacturing companies, the types of facility error are not precisely defined and categorized. The worker who operates the facilities writes the type of facility error in the form with unstructured text based on his or her empirical judgement. That makes it impossible to analyze data. Therefore, this paper proposes a framework for constructing a phrase network to support the identification and classification of facility error types by using facility error logs written by operators. Specifically, phrase indicating the types are extracted from text data by using dictionary which classifies terms by their usage. Then, a phrase network is constructed by calculating the similarity between the extracted phrase. The performance of the proposed method was evaluated by using real-world facility error logs. It is expected that the proposed method will contribute to the accurate identification of error types and to the prediction of facility errors.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.272-278
• /
• 2018

Traffic volume has been greatly increasing due to urban development and the improvement of living standards, and many complaints are being raised due to the increasing road noise. As a countermeasure against these problems, highly soundproof walls are installed on the sides of roads. However, the ability to bear wind loads is a major design requirement for soundproof walls, which contributes to the exponential increases in construction costs and restricts the height of the walls. The aim of this study is to improve the performance of soundproof walls and to dramatically reduce wind loads while maintaining excellent price competitiveness. Based on Helmholz's resonator theory, a new concept is proposed for a ventilation-type soundproofing plate that can pass through a fluid like air and reduce noise. A full-scale metal soundproofing plate was produced to satisfy the quality standards of highways by conducting a sound-pressure transmission-loss test, wind tunnel test, and material quality test. To verify the reliability, the wall was manufactured and installed, and the sound insulation effect was examined by measuring the noise over time. In the future, ventilated soundproof walls on roads could create a pleasant living environment due to the high noise-insulation effect.

• Explosives and Blasting
• /
• v.36 no.4
• /
• pp.1-8
• /
• 2018

This numerical study was intended to evaluate the applicability of the half charge blasting to mining and tunnelling. The half charge blasting is a method that two separate rounds are sequentially blasted for the rock burdens in which long blast holes have already been drilled at one operation. The aim of the method is to decrease the construction cost and period in mining and tunnelling projects as well as to increase the blasting efficiency. Several numerical analyses were conducted by using the Euler-Lagrange solver on ANSYS AUTODYN to identify the effects of the suggested method on the blasting results in underground excavations. The overall performance of the suggested method was also compared to an ordinary blasting method. The analysis model was comprised of the Eulerian parts (explosive, air, and stemming materials) and the Lagrangian parts (rock material). As a result, it was found that, owing to the air decks formed in the bottom parts of the long blast holes, the first round of the suggested method presented a higher shock pressure and particle velocities in the vicinity of the blast holes compared to the ordinary blasting method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.430-439
• /
• 2019

In this study, a nonlinear impact analysis was performed to evaluate the safety and damage of an eco-pillar debris barrier with a hollow cross-section, which was proposed to improve constructability and economic efficiency. The construction of concrete eco-pillar debris barriers has increased recently. However, there are no design standards concerning debris barriers in Korea, and it is difficult to find a study on performance evaluations in extreme environments. Thus, an analysis of an eco-pillar debris barrier was done using the rock impact speed, which was estimated from the debris flow velocity. The diameters of rocks were determined by ETAG 27. The impact position, angles, and rock diameter were considered as variables. A concrete nonlinear material model was applied, and the estimation of damage was done by ABAQUS software. As a result, the damage ratio was found to be less than 1.0 at rock diameters of 0.3 m and 0.5 m, but it was 1.39 when the diameter was 0.7 m. This study could be used as basic data on impact force in the design of the cross section of an eco-pillar debris barrier.

• Journal of Korean Society of Forest Science
• /
• v.110 no.2
• /
• pp.155-164
• /
• 2021

Many studies have been conducted on developing automatic plant identification algorithms using machine learning to various plant features, such as leaves and flowers. Unlike other plant characteristics, barks show only little change regardless of the season and are maintained for a long period. Nevertheless, barks show a complex shape with a large variation depending on the environment, and there are insufficient materials that can be utilized to train algorithms. Here, in addition to the previously published bark image dataset, BarkNet v.1.0, images of barks were collected, and a dataset consisting of 53 tree species that can be easily observed in Korea was presented. A convolutional neural network (CNN) was trained and tested on the dataset, and the factors that interfere with the model's performance were identified. For CNN architecture, VGG-16 and 19 were utilized. As a result, VGG-16 achieved 90.41% and VGG-19 achieved 92.62% accuracy. When tested on new tree images that do not exist in the original dataset but belong to the same genus or family, it was confirmed that more than 80% of cases were successfully identified as the same genus or family. Meanwhile, it was found that the model tended to misclassify when there were distracting features in the image, including leaves, mosses, and knots. In these cases, we propose that random cropping and classification by majority votes are valid for improving possible errors in training and inferences.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.38 no.4
• /
• pp.39-48
• /
• 2020

This study examined the type, the structural shapes, and the representation of Sandae, which was the stage for traditional performing arts and constructed for the purpose of imperial processions, ritual ceremonies, banquets, etc. from the Goryeo Dynasty to the Late Joseon Dynasty, and the implications of Seokgasan, which was built in the same era. First, through the history and meaning of Sandae, it was confirmed that Sandae has a homogeneity with Seokgasan, which attempted to imitate the shape of "Mountain" in the outer space. The construction of Sandae was deeply related to the tradition of famous mountains. This is consistent with the fact that 'Famous mountains and lakes" in China was symbolically replicated on the Seokgasan in the front yard of the "Cheongyeongak" in the Goryeo Dynasty. Second, Sandae and Seokgasan differed in their structural shapes, materials, and production methods, but they were used as a stage background for national events by constructing in the shape of the mountain, and appeared in various types. It can be seen that the interest in gardens and art of those days has resulted in various formative expressions of nature through the shape and symbolic meaning of the Sandae that mimics the mountain. Third, it is presumed that the square pond with lotus flowers, which is believed to have been located in the center of the garden of Shin Jaehyo's old house, and the Sugak and Seokgasan adjacent to it were not only elements of the garden, but also functioned as a background for the training and performance stage of Shin Jaehyo's students.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.1
• /
• pp.1-6
• /
• 2021

Concrete structures gradually age due to deterioration of materials or excess loads and environmental factors, and their performance decreases, affecting the usability and safety of structures. Although external tension construction methods are widely used among the reinforcement methods of old bridges, it is insufficient to identify the effects and effects of reinforcement depending on the level of aging. Therefore, in this study, a four-point loading experiment was conducted on the subject with the non-reinforced and external tensioning method to confirm the reinforcement effect of the external tensioning method, assuming the aging of the structure as a reduction in the compressive strength and tensile reinforcement of concrete, to analyze the behavior of the reinforcement and confirm the reinforcement effect. As a result of the experiment, it was difficult to identify the amount of reinforcement in the extreme condition due to early elimination of the anchorage. Therefore, compliance with the regulations on anchor bolts is required when applying the external tension reinforcement method. Crack load and yield load increased depending on whether external tension was reinforced, but before the crack, the stiffness before and after reinforcement was similar, making it difficult to confirm the reinforcement effect.

• Resources Recycling
• /
• v.31 no.5
• /
• pp.42-51
• /
• 2022

Aggregate resources in Korea are expected to run out owing to an increase in development demand and construction investment. Recycled concrete aggregates (RCA), extracted from waste concrete, have a lower quality than natural aggregates. However, RCA can produce concrete similar in quality to the normal concrete by aggregate pretreatment, use of admixtures, and quality control. RCA are most suitable for use in precast concrete products such as sidewalk blocks and revetment blocks. Herein, the feasibility of producing revetment blocks using recycled aggregate concrete (RAC), similar in quality to normal concrete, was analyzed. The amount of RCA was varied, and moderate high early strength cement and steam curing were used to produce the concrete test blocks. In the block test, the load resistance characteristics of the blocks were evaluated to determine optimal RAC and glass fiber reinforced polymer (GFRP) rebar compositions. Thus, the variable that reduced the cement content was determined at the same level as that of natural aggregate concrete by the control of steam curing. In the concrete block test, although this depends on the reinforcement ratio, the RAC block exhibited the same or better performance than a normal concrete block. Therefore, the low quality of RCA in RAC is no longer a problem when concrete mixing and curing are controlled and appropriate reinforcement is used.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1643-1652
• /
• 2022

Deposited Marine Debris(DMD) can negatively affect marine ecosystems, fishery resources, and maritime safety and is mainly detected by sonar sensors, lifting frames, and divers. Considering the limitation of cost and time, recent efforts are being made by integrating underwater images and artificial intelligence (AI). We conducted a comparative study of You Only Look Once Version 5 (YOLOv5) and You Only Look Once Version 7 (YOLOv7) models to detect DMD from underwater images for more accurate and efficient management of DMD. For the detection of the DMD objects such as glass, metal, fish traps, tires, wood, and plastic, the two models showed a performance of over 0.85 in terms of Mean Average Precision (mAP@0.5). A more objective evaluation and an improvement of the models are expected with the construction of an extensive image database.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1633-1641
• /
• 2022

Urban population concentration and indiscriminate development are causing various environmental problems such as air pollution and heat island phenomena, and causing human resources to deteriorate the damage caused by natural disasters. Urban trees have been proposed as a solution to these urban problems, and actually play an important role, such as providing environmental improvement functions. Accordingly, quantitative measurement and analysis of individual trees in urban trees are required to understand the effect of trees on the urban environment. However, the complexity and diversity of urban trees have a problem of lowering the accuracy of single tree detection. Therefore, we conducted a study to effectively detect trees in Dongjak-gu using high-resolution aerial images that enable effective detection of tree objects and You Only Look Once Version 5 (YOLOv5), which showed excellent performance in object detection. Labeling guidelines for the construction of tree AI learning datasets were generated, and box annotation was performed on Dongjak-gu trees based on this. We tested various scale YOLOv5 models from the constructed dataset and adopted the optimal model to perform more efficient urban tree detection, resulting in significant results of mean Average Precision (mAP) 0.663.