http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
도로 융설체 개발을 위한 탄소나노튜브-시멘트 복합체 특성에 관한 실험적 연구
허진녕,박범진,김태형 한국도로학회 2013 한국도로학회논문집 Vol.15 No.2
PURPOSES : This study aims to review the possibility of developing a road snow-melting system that can prevent slip accidents by maintaining a constant temperature of the winter roads and enhance performance of structures, including improvement of compressive strength by mixing carbon nanotube (hereafter referred to as CNT) with cement paste, the basic material. METHODS: To achieve the above purpose, an experiment was conducted by mixing power-type CNT and wrap-type CNT up to cement paste formulation by weight of 0.0wt%~4.1wt% in accordance with “KS L ISO 679(of cement strength test method)”, and compressive strength was measured at 28 days of curing. In addition, the volume resistivity of the specimen was measured to test thermal and electrical characteristics, and the rate of temperature changes in specimen surface by power consumption was measured by passing electricity through the cross-sections of the specimen. Meanwhile, the criteria for checking the performance as a road snow-melting system was determined as volume resistivity of 100Ω·cm or less. RESULTS : A comparative analysis between specimen with 0wt% CNT content in plain status and specimen containing various types of CNTs was carried out. From its results, it was found that compressive strength increased approximately 19%, showing the highest rate when 0.2wt% of wrap-type CNT was contained, but volume resistivity of 100Ω·cm or less appeared only in specimens containing more than 0.2wt% CNT. In addition, it was observed that the surface temperature increased by 4.62℃ per minute on average in specimens containing 3.2wt% CNT. CONCLUSIONS : In this study, CNT was examined as an underlying material for a road snow-melting system, and the possibility of developing the road now-melting system was reviewed by conducting various experiments using CNT-Cement composites. From the experimental results, the specimens were found to have a superior performance when compared to the existing road snow-melting systems that place the heat transfer medium such as copper on the road. However, satisfactory strength performance were not obtained from the specimen containing CNT(2.0% or more) that functions as a heating element, which leads to the need for reviewing methods to increase the strength by using plasticizer or admixture.
딥러닝 모델을 활용한 포트홀 검출 및 성능 개선을 위한 전처리 방법론 연구
허진녕,이영인,김하영 한국지식정보기술학회 2023 한국지식정보기술학회 논문지 Vol.18 No.5
In recent years, the number of potholes has been increasing due to the high frequency of heavy rainfall. In addition, road surface damage is inevitable due to the aging of roads, and damaged roads (potholes and cracks) interfere with drivers' driving, causing various safety accidents. To efficiently solve this problem, various road damage detection studies have been conducted using artificial neural networks. However, previous studies have been limited by a lack of understanding of potholes. Furthermore, the need for research is growing as the number of risk factors that can cause potholes is rapidly increasing. To overcome the limitations of previous studies, this study proposes an image preprocessing technique that can effectively reflect the characteristics of potholes and an optimal structure for pothole detection based on EfficientDet. The proposed preprocessing technique combines two algorithms, CLAHE and Sobel Edge detection, to identify and learn potholes in road surface images by maximizing the boundaries of potholes through contour detection and contrast thresholding for the entire image, rather than solely relying on contrast. In addition, we designed the optimal number of BiFPN layers for the pothole dataset so that the module can clearly detect potholes. The methodology proposed in this study was applied to EfficientDet and YOLO v5 models to experimentally prove the feasibility of the methodology.