• 한국인공지능학회지
• /
• 제11권3호
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• 한국인공지능학회지
• /
• 제11권4호
• /
• pp.1-8
• /
• 2023

In this paper, we propose a black ice detection platform framework using Convolutional Neural Networks (CNNs). To overcome black ice problem, we introduce a real-time based early warning platform using CNN-based architecture, and furthermore, in order to enhance the accuracy of black ice detection, we apply a multi-scale dilation convolution feature fusion (MsDC-FF) technique. Then, we establish a specialized experimental platform by using a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Experimental results of a real-time black ice detection platform show the better performance of our proposed network model compared to conventional image segmentation models. Our proposed platform have achieved real-time segmentation of road black ice areas by deploying a road black ice area segmentation network on the edge device Jetson Nano devices. This approach in parallel using multi-scale dilated convolutions with different dilation rates had faster segmentation speeds due to its smaller model parameters. The proposed MsCD-FF Net(2) model had the fastest segmentation speed at 5.53 frame per second (FPS). Thereby encouraging safe driving for motorists and providing decision support for road surface management in the road traffic monitoring department.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2002년도 춘계 학술발표회 논문집
• /
• pp.203-210
• /
• 2002

The past bridge design specifications of Korea didn't include 1imitation on the amount of lap splices in the plastic hinge zone of piers, and so do current specifications. But these specifications include just limitation on the minimal length of lap splices. Thus, a large majority of non-seismically designed bridge piers may have lap splices in plastic hinge zone. In this study, model pier was selected among existent bridge piers whose failure mode is complex shear-flexure mode. Full scaled RC pier models whose aspect ratio is about 2.67 were constructed and quasi static test according to the drift level history was implemented. From the test results, effect of the lap splices on the seismic performance of bridges piers was analyzed, and the seismic capacity of the model bridges was evaluated by capacity spectrum method.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 추계학술대회 논문집
• /
• pp.720-725
• /
• 1997

This paper is to study the wind effect of the large scale gantry crane. It is used to control the sway of gantry crane in the loadingiunloading job of containers. I'hls is very important in the automated container terminal because the sway of handling equipments in pard is caused by thc l~nexpected disturbance such as wind and dynamic inertia by deriving force. This study shows the process of the modelling simulation of the wind effect of the sway motion of the gantry crane. Pro-Engineer, ANSYS and DAD'; ~ rr . used for 3D solid modelling and dynamic simulation. Though this study did not use the real parameters. the ; cwl ~ shows the trend of the wind effect is very large in the large scale crane and should be considered in design of the large scale gantry crane. In future, if the study is done by using the real parameters, the result is much more ~ise!'ul for dynamic control and design of gantry crane.

• 한국철도학회논문집
• /
• 제9권3호
• /
• pp.305-312
• /
• 2006

Gravel ballasted tracks are used as a basic structure for the domestic railway tracks. However, such kind of tracks has few disadvantages with service life of the structure, such as rapid deterioration of the tracks. Due to this reason, there is a need to develop low maintenance track to improve the service life of the conventional line tracks. CMP paved tacks are one of the kind of concrete tracks those were manufactured by using the prepacked concrete techniques. The purpose to develop paved tracks is to reduce the maintenance cost. The most important controlling factors to design the paved tracks are surrounding environmental condition and repeated train loading. In this study, in order to investigate the deformation characteristics such as displacement, earth pressure, strain ratio, and crack along the repeated loading cycle, cyclic loading test through real scale model was carried out.

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제54권8호
• /
• pp.371-377
• /
• 2005

This paper Presents the Potential gradient characteristics of structure grounding electrode when a test current flows through grounding electrode. In order to analyze the potential gradient of ground surface on structure grounding electrode, the reduced scale model has been used. The potential gradient has been measured and analyzed for types of structure using the hemispherical grounding simulation system in real time. The structures were designed through reducing real buildings and fabricated with four types on a scale of one-one hundred sixty. The supporter was made to put up with weight of structure and could move into vertical, horizontal, rotary direction. When a test current flowed through structure grounding electrodes, ground potential rise was the lowest value at electric cage type(type B). According to resistivity and absorption percentage In concrete attached to structure, the potential distribution of ground surface appeared differently.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.670-673
• /
• 2002

This paper proposes a digital algorithm for gray-scale/color image segmentation of real-time video signals and a cell-network-based implementation architecture in state-of-the-art CMOS technology. Through extrapolation of design and simulation results we predict that about 300$\times$300 pixels can be integrated on a chip at 100nm CMOS technology, realizing very high-speed segmentation at about 1600sec per color image. Consequently real-time color-video segmentation will become possible in near future.

• Journal of Mechanical Science and Technology
• /
• 제15권6호
• /
• pp.776-787
• /
• 2001

The turbofan engine performance analysis for a medium scale commercial aircraft was carried out and the LQR control scheme for performance optimization was studied. By using scaled component maps from well-known CF6 engine characteristics, the steady-state performance analysis result was compared with BR715-56 engine performance data. The transient performance analysis was performed with four fuel schedules. The linear simulation was done at the maximum take-off condition. The real time linear simulation was performed by interpolation of the system matrices, which used the least square method as the function of LPC rotational speed. By using linear system matrices of design point, the LQR controller which used control variables for the fuel flow and the LPC bleed air was designed.

• 한국ITS학회 논문지
• /
• 제23권1호
• /
• pp.167-181
• /
• 2024

자율주행 기술 개발에 있어서 드라이빙 시뮬레이터의 활용은 사고 환경에 대한 다양한 테스트를 단시간에 효과적으로 수행 가능하게 하여 개발 비용 및 노력을 획기적으로 줄일 수 있다. 그러나 드라이빙 시뮬레이터는 실제 환경과 차이가 존재한다는 심각한 단점이 존재하므로 드라이빙 시뮬레이터를 이용하여 개발된 자율주행 알고리즘이 실제 차량 시스템에 직접 적용시킬 때 큰 차이가 발생하는 문제가 있다. 이러한 문제는 Sim2Real 문제로 정의되며, 시나리오, 센서 모델링, 차량 동역학 등으로 구분할 수 있다. 본 논문에서는 Sim2Real 문제 중에서 IMU센서에 대해서 Sim2Real 문제 해결 방안에 대한 연구를 수행한다. 실제 환경과 에뮬레이터된 가상 IMU 센서의 차이를 줄이기 위해서 IMU 센서의 정밀 오차 모델링을 통한 센서 에뮬레이터 기술에 대해 소개한다. Bias, Scale Factor, Misalignmnet, Random Walk에 따른 오차를 가상 IMU 센서 등급별로 모델링하고 이를 실제 IMU 센서의 등급에 따른 오차 지표와 비교함으로써 IMU 센서의 Sim2Real 문제를 완화한다.

• 한국화재소방학회논문지
• /
• 제23권5호
• /
• pp.57-65
• /
• 2009

본 연구에서는 화재 시 많은 인명피해가 예상되는 공동 주택을 대상으로 단위공간별 화재 성상을 예측하기 위한 실물화재실험을 실시하였다. 실험 모델 주택을 구성하고 있는 내부 가연물을 선정한 후 각 단위 품목에 대한 화재특성 실험을 실시하였으며, 주방, 거실, 침실, 공부방 등 4종류의 단위 공간으로 구분하여 각각 실물화재실험을 실시하였다. 실험결과 침실의 경우 점화 후 약 5분이 경과되었을 때 플래쉬오버 상태에 이르게 되어 매우 급격한 성장을 보였으며, 최대 열방출율 약 7,433.3kW, 최대 CO 578.6ppm, 최대 $CO_2$ 1.25%, 내부 최대온도 $1,350^{\circ}C$로 측정되었다. 특히, 화재 발생 초기에 가연 공간에서 화재의 진화가 이루어지지 않으면 약 3분 내에 인체에 급격한 피해를 줄 수 있는 한계온도 이상으로 화재가 성장하기 때문에 신속한 초기 대응이 필요함을 확인하였으며, 장롱, 침구류 등 비교적 화재가 급속히 전이 될 수 있는 가연물량이 다수 배치되어 있는 침실에서 용도별 가연 공간 중 가장 위험도가 높은 것으로 측정되었다. 단위 가연물에서 발생되는 유독가스가 임계수준 이상으로 발생되어 이로 인해 인체에 심각한 피해를 줄 수 있을 것으로 판단된다. 이러한 실물화재실험에서 얻어낸 결과는 향후 화재확대 예측 시뮬레이션 결과와 비교함으로써 각 용도별 공간에서의 화재 확산 예측에 적용될 수 있을 것이다.