http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
FMEA 기법을 활용한 크레인 관련 중대 재해의 정량적 분석에 관한 연구
김홍현,이강 한국건축시공학회 2007 한국건축시공학회지 Vol.7 No.3
As buildings become higher, larger, and more complex, safety issues for construction workers working at such environments become more important. We analyzed 83 critical accident cases reported to the KOSHA(Korea Occupational Safety & Health Agency) for construction cranes by types of cranes and by patterns of accidents and causes. There are more number of accidents related to mobile cranes than that related to tower cranes, but the numbers of dead were similar in both cases. The most dominant cause of crane accidents was “fall of materials”. We also analyzed the cases of crane accidents using the FMEA(Failure Mode and Effect Analysis) in order to set up a priority for safety management and also to prioritize research and development items relating tower cranes. In the process, we tried to eliminate subjective indexes such as an expert group survey and use objective and quantitative indexes. As a result, it was found that critical crane accidents occurs most during the “lifting and translating” activity.
김홍현,정상조 한국군사과학기술학회 2019 한국군사과학기술학회지 Vol.22 No.5
This study selected a representative small arm firing range and analyzed the distribution of heavy metalpollutants such as Pb, Cu, Zn, etc. For this the concentrations of heavy metals in soils, roots and leaves of plants,and water of the small arm firing range were measured. The concentrations of heavy metals in the effluent werealso checked during precipitation. The concentration of lead in the samples collected from the top soil(0-5 cm) andsub soil(5-50 cm) near the target in the small arm firing range exceeded the concern level of the SoilEnvironment Conservation Act of Korea, but not in other soil samples. Plants that grow in soil heavilycontaminated with lead showed a high lead concentration, especially in roots. However, the concentration of leadin effluent from the small arm firing range was less than 0.02 ppm. The concentration of copper and zinc in thesmall arm firing range did not surpass the concern level of the Soil Environment Conservation Act of Korea. Through this study more accurate information on the distribution of heavy metal pollution in the soil of the smallarm firing range was obtained. Based on this research, we can conclude that some facility improvements canreduce the spreading of pollutants in the currently used small arm firing range and contribute to the design andoperation of advanced small arm firing ranges.
김홍현,조재호,Zhu Teng,강동중 제어·로봇·시스템학회 2019 International Journal of Control, Automation, and Vol.17 No.6
This paper proposes a three-level framework to detect texts in a single image. First, a salient feature map of text is extracted using a Fully Convolutional Network (FCN) that achieves good performance in semantic segmentation. Label combination using both boxes of word and characters level is proposed to improve the detection of uneven boundaries of text regions. Second, in the feature map of FCN, the text region has a higher probability value than the background region, and the coordinates in the character area are very close to each other. We segment the text area and the background area by using the characteristics of text feature map with Hierarchical Cluster Analysis (HCA). Finally, we applied a Convolutional Neural Networks (CNN) to classify the candidate text area into text and non-text. In this paper,we used CNN which can classify 4 classes in total by separating the background area and three text classes (one character, two characters, three characters or more). The text detection framework proposed in this paper have shown good performance with ICDAR2015, and high performance especially in Recall criterion, finding more texts than other algorithms.
Multi-task Convolutional Neural Network System for License Plate Recognition
김홍현,박제강,오주희,강동중 제어·로봇·시스템학회 2017 International Journal of Control, Automation, and Vol.15 No.6
License plate recognition is an active research field as demands sharply increase with the developmentof Intelligent Transportation System (ITS). However, since the license plate recognition(LPR) is sensitive to theconditions of the surrounding environment such as a complicated background in the image, viewing angle andillumination change, it is still difficult to correctly recognize letters and digits on LPR. This study applies DeepConvolutional Neural Network (DCNN) to the license plate recognition. The DCNN is a method of which theperformance has recently been proven to have an excellent generalization error rate in the field of image recognition. The proposed layer structure of the DCNN used in this study consists of a combination of a layer for judging theexistence of a license plate and a layer for recognizing digits and characters. This learning method is based on Multi-Task Learning (MTL). Through experiments using real images, this study shows that this layer structure classifiesdigits and characters more accurately than the DCNN using a conventional layer does. We also use artificial imagesgenerated directly for training model.
김홍현,이성순,하승욱,이강근 한국지질과학협의회 2018 Geosciences Journal Vol.22 No.6
A single-well push-drift-pull tracer test using two different tracers (SF6 and salt) was performed at the Environmental Impact Test (EIT) site to determine suitable locations for monitoring wells and arrange them prior to artificial CO2 injection and leak tests. Local-scale estimates of hydraulic properties (linear groundwater velocity and effective porosity) were obtained at the study site by the tracer test with two tracers. The mass recovery percentage of the volatile tracer (SF6) was lower than that of the non-volatile tracer (salt) and increased drift time may make degassing of SF6 intensified. The CO2 leakage monitoring results for both unsaturated and saturated zones suggest that the CO2 monitoring points should be located near points at which a high concentration gradient is expected. Based on the estimated hydraulic properties and tracer mass recovery rates, an optimal CO2 monitoring network including boreholes for monitoring the unsaturated zone was constructed at the study site.