http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
드론과 Mobile Mapping System을 활용한 인공지능 기반 도로 균열 검출
현세권(HYUN, Sekwon),도명식(DO, Myung Sik) 대한교통학회 2021 대한교통학회지 Vol.39 No.4
최근 5년간 중앙정부의 전체 예산은 매년 4.9%의 비율로 증가하고 있으나, 도로부문의 유지관리 예산은 매년 줄고 있다. 또한 도로법의 개정 및 지속가능한 기반시설 관리 기본법의 신설에 따라 모든 지자체에서 유지관리와 성능개선을 위해 5년 단위의 기본계획을 수립해야 한다. 하지만 상대적으로 예산이 적은 지자체에서 도로관리를 위한 고가의 장비를 도입하기는 현실적으로 어려운 실정이다. 이에 본 연구는 인공지능을 활용하여 상대적으로 가격이 저렴한 Mobile Mapping System(MMS)와 드론을 활용한 도로균열 검출 방법을 제시하는 것을 연구의 목적으로 한다. MMS와 드론을 활용하여 얻은 해상도 높은 도로 노면 사진데이터를 취득하고 데이터의 특성에 따라 인공지능을 학습시키기 위하여 전처리를 수행하였다. 딥러닝 학습을 위해 도로 파손 유형에 따라 균열이 있는 곳과 없는 곳, 또는 도로가 아닌 곳으로 라벨링을 진행하였고 Basic CNN모델과 Mobilenetv2신경망을 수정하여 학습을 진행하였다. Mobilenetv2의 알고리즘의 분류정확도는 MMS데이터 95%, 드론데이터 78%를 얻었다. 이는 MMS와 드론을 활용하여 정도 높은 균열 분류가 가능하다는 결론을 도출할 수 있었다. 향후 본 연구에서 개발된 알고리즘을 기반으로 지자체와 시설물 관리 기관에서 도로균열을 체계적으로 관리될 것이다. 또한 사용자 중심의 소프트웨어를 활용하여 도로를 이용하는 시민들에게도 도움이 될 것으로 기대된다. In recent years, the total budget of the central government has been increasing at a rate of 4.9% per year, but the maintenance budget of the road sector has been decreasing annually. In addition, with the revision of the Road Act and the establishment of the Framework Act on Sustainable Infrastructure Management, all local governments shall establish a five-year master plan to improve maintenance and performance. However, it is difficult for local governments with relatively small budgets to introduce expensive equipment for road management. In response, the purpose of this study is to present a road crack detection method using mobile mapping system (MMS) and drones that are relatively inexpensive with the use of artificial intelligence. High-precision road surface photographic data could be acquired using MMS and drones. Pre-processing was carried out to train the artificial intelligence depending on the characteristics of the data. Labeling was conducted according to the type of road cracks and was labeled based on where cracks were present, where none were present, or where roads were not. The training was done by modifying the basic convolution network model and the mobilenetv2 neural network. As a result of the training, the data classification accuracy using the mobilenetv2 algorithm was able to achieve 95% on MMS data and 78% on drone data. It can be hypothesized that a more high-performance crack classification accuracy might be achieved by utilizing MMS and drone equipment. In the future, road cracks will be systematically managed by local governments and facility management agencies based on algorithms developed in this study. It is also expected to benefit citizens who use user-centered software to use roads.
ZnO 나노막대가 형성된 STO기판에 증착한 Y-Ba-Cu-O 박막의 미세구조 분석
오세권,장건익,강병원,김경원,이초연,현옥배,Oh, S.K.,Jang, G.E.,Tran, H.D.,Kang, B.W.,Kim, K.W.,Lee, C.Y.,Hyun, O.B. 한국초전도학회 2009 Progress in superconductivity Vol.11 No.1
For many large-scale applications of high-temperature superconducting materials, large critical current density ($J_c$) in high applied magnetic fields are required. A number of methods have been reported to introduce artificial pinning centers in $YBa_2Cu_3O_{7-{\delta}}$ films for enhancement of their $J_c$. We studied the microstructures and characteristic of $YBa_2Cu_3O_{7-{\delta}}$ films fabricated on $SrTiO_3$ (100) substrates with ZnO nanorods as pinning centers. Au catalyst nanoparticles were synthesized on STO substrates with self assembled monolayer to control the number of ZnO nanorods. The density of Au nanoparticles is approximately $240{\sim}260{\mu}m^{-2}$ with diameters of $41{\sim}49nm$. ZnO nanorods were grown on STO by hot-walled PLD with Au nanoparticles. Typical size of ZnO nanorod was around 179 nm in diameter and $2{\sim}6{\mu}m$ in length respectively. YBCO films deposited directly on STO substrates show the c-axis orientation, while YBCO films with ZnO nanorods exhibit any mixed phases without any typical crystal orientation.
Growth behavior of YBCO films on STO substrates with ZnO nanorods
오세권,이초연,장건익,김경원,현옥배 한국초전도.저온공학회 2009 한국초전도저온공학회논문지 Vol.11 No.4
The influence of nanorods grown on substrate prior to YBCO deposition has been investigated. We studied the microstructures and characteristic of YBa2Cu3O7-δ films fabricated on SrTiO3 (100) substrates with ZnO nanorods as one of the possible pinning centers. The growth density of ZnO nanorods was modulated through Au nanoparticles synthesized on top of the STO(100) substrates with self assembled monolayer. The density of Au nanoparticles is approximately 240~260 μm-2 with diameters of 41~49 nm. ZnO nanorods were grown on Au nanoparticles by hot-walled PLD with Au nanoparticles. Typical size of ZnO nanorod was around 179 nm in diameter and 2~6 μm in length respectively. The ZnO nanorods have apparently randomly aligned and exhibit single-crystal nature along (0002) growth direction. Our preliminary results indicate that YBCO film deposited directly on STO substrate shows the c-axis orientation while YBCO films with ZnO nanorods exhibit any mixed phases without any typical crystal orientation.