교통안전시설물의 관리는 도로교통의 안전과 직결되는 문제이다. 운전자는 신호등, 표지판, 노면표시 등을 통해 운전에 필요한 정보 를 얻는다. 노후된 표지판과 노면표시는 운전자에게 잘못된 정보를 제공할 수 있으므로 주기적인 시설물의 관리가 필요하다. 본 연구 는 딥 러닝 기술을 활용해 운전자 시각의 영상 자료에서 교통안전표지를 자동으로 탐지하고자 하며, 교통안전표지의 공통된 색상 특 징을 기반으로 클래스를 그룹으로 묶어 데이터셋을 구축하는 방법을 제안한다. 객체탐지의 성능지표로 널리 활용되는 mAP를 사용해 클래스 묶음 여부에 따른 탐지 성능을 비교한 결과, 색상 기반 클래스 묶음을 적용한 모델의 탐지 성능이 비교군에 비해 약 36% 상승 함을 확인하였다.

도로포장의 대표적 파손 종류인 균열은 일반적으로 폭이 좁고 기하학적으로 정의하기 어렵기 때문에 균열을 검출하고 유형을 분류 한 후 정량화하기까지 많은 시간이 소요된다. 본 연구의 목적은 균열 검출 이후 단계에서 요구되는 분류 및 정량화 과정을 자동화하 기 위함이다. 이를 위해, 본 연구에서는 균열이 매핑된 포장관리체계용 노면영상을 대상으로 하는 25cm 정사각형의 격자 배치 방법과 차륜 통과 영역 구분을 제시하였다. 각 격자 내 균열 객체의 길이와 진전방향, 인접한 정도 등 시각적 정보에 의한 균열 격자 속성을 정의하고 프로그래밍하여 균열 유형분류와 집계를 자동화하였다. 무작위로 수집된 고속도로 노면영상 자료를 통해 포장형식 별 주요 균열 유형을 분석하였고 차륜 통과 영역에서의 균열률 증가를 수치적으로 확인하였다.

포장상태 평가를 위한 노면영상 촬영은 라인스캔 방식이 주를 이루고 있다. 라인스캔 특성 상, 조사환경이나 장비특성이 달라질 경 우 밝기가 상이한 노면영상을 취득할 수 있고 이는 U-net과 같은 픽셀 단위 segmentation 딥러닝 모델의 균열 자동검출 성능에 영향을 미친다. 본 연구에서는 인공지능 검출 모델의 변경 없이 영상의 밝기 최적화와 morphology 연산기법을 노면영상 전·후처리 방법으로 제시하고 그 효과를 분석하였다. 영상 처리를 통해 과다 검출경향을 보인 이상치들이 제거되었으며 정답으로 간주할 수 있는 전문요 원 분석결과인 GT 균열률과의 상관성 또한 향상됨을 확인하였다.

PURPOSES : The purpose of this study is to derive dropout rates according to various international roughness index (IRI) specifications using ProVAL, develop a comparative methodology, and indirectly assess the level of road management in each country. METHODS : Based on a literature review, the IRI specifications for each country were collected, and the ProVAL analysis tool was used to compare and analyze dropout rates according to each specification. Thus, the dropout rate rankings for each country were calculated. Additionally, by analyzing the correlation between dropout rates according to each threshold, a model was created to convert the threshold between the most commonly used baseline distances of 100 m and 161 m. RESULTS : Dropout rates were derived according to the standards of each country and rankings were assigned. Comparing 51 standards, the IRI level of New Mexico appeared to be the highest, whereas the domestic specifications ranked 36th. A model was created to convert the threshold between the standard distances of 100 m and 161 m. CONCLUSIONS : This study objectively assessed the roughness standards in various countries using the dropout rate and IRI ranking specifications. The highest specification was found for the asphalt of New Mexico in the USA, with the domestic specification ranking 36th. A model that converts the thresholds between the most commonly used baseline distances of 100 m and 161 m was developed, with slight differences across sections. For a precise conversion, individual models may be required for each section.

PURPOSES : This study suggests an estimated texture depth (ETD) equation for concrete pavements, applicable to highway pavement texture, and the measurement method of mean profile depth (MPD) in a longitudinal texture. METHODS : First, we proposed the most suitable ETD equation through the correlation between ETD data and the measured mean texture depth (MTD) data. Second, we suggested a novel MPD measurement method, by checking the error of the ETD data and measured MTD data by the measurement method. RESULTS : The ETD equation presented by Fisco and Plati was considered the most appropriate for the transverse texture. In addition, the correlation between ETD and the measured MTD was good in the longitudinal measurement method. The ETD equation of Fisco and Plati is suitable for longitudinal texture, and the MPD measurement method obtained good results when applied to transverse measurements. To verify the novel measurement method, we confirmed the correlation between the SR and MPD data using a novel method. The correlation for the novel measurement method is 0.7. CONCLUSIONS : Accordingly, the ETD equation presented in the existing literature has a good correlation between ETD data and the measured MTD data, but it did not reflect longitudinal texture data. Therefore, we assumed the ETD equation produced in this study, and suggested the transverse measurement method in the longitudinal texture.

PURPOSES : Accidents involving autonomous vehicle continue to occur. However, research on autonomous vehicle monitoring has been insufficient. The purpose of this study is to develop monitoring indicators from the perspective of vehicles and road infrastructure for the safe driving of autonomous vehicles. In addition, the purpose is to monitor autonomous vehicles and road environments using the monitoring indicators developed, as well as to analyze the characteristics of road sections where autonomous vehicles exhibit abnormalities. METHODS : Data from Pangyo Zero Shuttle, an autonomous vehicle, were used in this study. Infrastructure data installed in Pangyo Zero City were used. The data were collected from June 2019 to July 2019, during the normal driving period of the zero shuttle. The five monitoring indicators were developed by combining the vehicle operation information table collected from the V2X device of the zero shuttle and the road environment monitoring detail table collected from the infrastructure data with the road section table. In addition, an analysis of road characteristics with frequent errors is performed for each monitoring indicator. RESULTS : The three monitoring indicators from the perspective of the vehicle allowed monitoring of the sensor error, sensor communication error, and yaw rate error of the autonomous vehicle's timing and road section. In addition, the two monitoring indicators from the infrastructure perspective enabled the monitoring of events and road surface conditions on roads where autonomous vehicles drive. As a result of analyzing the road characteristics that frequently caused errors by monitoring indicators, sensor errors frequently occurred in the section waiting to enter the left-turn lane. Sensor communication errors are left-turn standby and have occurred frequently on road sections where U-turns are allowed. Finally, yaw rate error occurred frequently in sections of roads where there were no induction lines or where changes to lanes occurred frequently. CONCLUSIONS : The five monitoring indicators developed in this study allowed the monitoring of autonomous vehicles and roads. The results of this study are expected to help the safe driving of autonomous vehicles and contribute to the detection of autonomous driving abnormalities and the provision of real-time road condition information through further analysis.

PURPOSES : The purpose of this study was to identify the availability of Grip-Tester, which can be used as continuous friction testers, for estimating the skid resistance of pavements by examining its basic performance. METHODS : Based on a literature review, various factors influencing skid resistance on road surfaces were described, and the subject to be evaluated were proposed. Friction tests were conducted at various operating speeds to assess the water supply performance, repeatability, and reproducibility of the measurement results. Both the British pendulum number (BPN) and mean texture depth (MTD) were examined to confirm the relationship between the Grip Number(GN) and surface texture. RESULTS : The results of the watering test indicate that more than 91% of valid measurements can be obtained at the maximum operating speed of 90 km/h to maintain a water film thickness of 0.25 mm. The repeatability and reproducibility of the measured GN were derived from the cross-correlation analyses to be 90.9% and 87.4%, respectively. It was found that the variations in GN values according to operating speeds follow an exponential model similar to the commonly known Penn State model, which can be considered to be due to the effect of texture on skid resistance. CONCLUSIONS : The grip tester is suitable for continuously surveying the skid resistance because GN datasets are reliable at variable operating speeds and correlate with the surface texture. This method may provide objective data for making decisions regarding the maintenance of skid resistance through periodic full-scale investigations with the tester in the future.

PURPOSES : This study uses deep learning image classification models and vehicle-mounted cameras to detect types of pavement distress — such as potholes, spalling, punch-outs, and patching damage — which require urgent maintenance. METHODS : For the automatic detection of pavement distress, the optimal mount location on a vehicle for a regular action camera was first determined. Using the orthogonal projection of obliquely captured surface images, morphological operations, and multi-blob image processing, candidate distressed pavement images were extracted from road surface images of a 16,036 km in-lane distance. Next, the distressed pavement images classified by experts were trained and tested for evaluation by three deep learning convolutional neural network (CNN) models: GoogLeNet, AlexNet, and VGGNet. The CNN models were image classification tools used to identify and extract the combined features of the target images via deep layers. Here, a data augmentation technique was applied to produce big distress data for training. Third, the dimensions of the detected distressed pavement patches were computed to estimate the quantity of repair materials needed. RESULTS : It was found that installing cameras 1.8 m above the ground on the exterior rear of the vehicle could provide clear pavement surface images with a resolution of 1 cm per pixel. The sensitivity analysis results of the trained GoogLeNet, AlexNet, and VGGNet models were 93 %, 86 %, and 72 %, respectively, compared to 62.7 % for the dimensional computation. Following readjustment of the image categories in the GoogLeNet model, distress detection sensitivity increased to 94.6 %. CONCLUSIONS : These findings support urgent maintenance by sending the detected distressed pavement images with the dimensions of the distressed patches and GPS coordinates to local maintenance offices in real-time.

국내 고층 아파트의 구조시스템은 크게 다수의 벽체가 분산적으로 배치되어 있는 내력벽 시스템과 중앙 코어벽 시스템으 로 구분할 수 있다. 각각 시스템에 따른 횡방향 거동을 분석하기 위해 본 연구는 국내 고층 아파트 중 대표적인 평면을 갖는 대상 건물을 선정하고, 비선형 정적해석을 수행하여 붕괴메커니즘을 살펴보았다. 비선형 정적해석을 통해 도출된 힘-변위 관계로부터 지진응답에 있어서 중요한 요소인 초과강도계수 및 연성도계수를 산정하여 반응수정계수를 평가하였다. 중앙 코어벽 시스템은 연성도는 작지만, 풍하중에 의해 지배되어 초과강도가 크게 산정돼 초과강도계수에 의해 반응수정계수가 산정되었고, 내력벽 시스템은 벽량이 많아 연성도가 크기 때문에 상당힌 큰 반응수정계수가 산정된다.

본 연구에서는 해상에서 빈번하게 발생하는 추진기 로프 감김 사고를 예방하기 위해 개발된 로프절단장치의 안전성 및 효용성 에 대한 연구를 시도하였다. 먼저 이론식과 유한요소 해석을 통하여 실선 실험에 사용될 세 종류의 로프절단장치의 볼트의 강도 및 장치가 축계에 미치는 비틀림응력을 계산하였다. 그 결과 로프절단장치에 사용된 볼트는 안전수명설계 및 손상허용설계의 관점에서 적절하게 설계된 것으로 확인되었으며, locking-up 발생 시 축계에 미치는 영향도 미미하여 안전성 또한 만족할 수 있는 수준인 것으로 나타났다. 안전성 검증을 마친 세 종류의 절단장치가 설치된 선박을 활용하여 실제로 해상에서 로프 및 어망을 절단하는 실험을 진행하였으며, 그 결과 대체적으로 실험에 사용된 20~50 mm 굵기의 로프를 잘 절단하였으나, 소형 축계에 장착된 절단장치의 경우 굵은 로프를 절단할 때는 효용성이 저하함을 알 수 있었다.

긴급하거나 광역으로 발생한 해상유류오염사고에는 방제정만으로 대응하기에는 한계가 있어서, 해양경찰청 경비함정도 방제 작업에 동원된다. 본 연구에서는 소형 경비함정에 적합한 유흡착장비를 개발하였다. 장비는 고정지지대, 폴대, 슬라이드고정부 3개 부속품으로 구성되어 용접 또는 추가 구조물 설치 없이 소형 경비함정 현측 추락방지봉에 간단하게 토글핀으로 결속하는 방식으로 장착 및 분리가 가능하다. 각 부속품의 무게는 고정지지대 약 9.2 kg, 폴대(2개) 약 6.5 kg, 슬라이드 고정부(4개) 약 3.5 kg이며, 좌·우 180°로 원활하게 움직이는 길이 3 m의 폴대는 갑판 방향으로 접어서 유흡착재 교체작업을 할 수 있다. 본 장비의 개발로 소형 경비함정에서 유흡착재의 투입 및 수거가 용이한 방법으로 개선되어 보다 효율적인 방제작업이 가능할 것으로 판단된다.

‘Seismic Performance Evaluation Method for Existing Buildings (2013)’ developed in accordance with the overseas guidelines ASCE 41 - 06 is the most widely used procedure among domestic seismic performance evaluation guidelines in Korea. However, unlike ASCE 41 - 06, it stipulates that the final performance should be derived as the gravity load distribution ratio of the lateral force resistance system in the guideline. Therefore, in the case of a dual steel structure system with slender braces, where the internal moment frame is mostly responsible for the gravity load, the evaluation of slender braces based on gravity load distribution ratio is difficult to be achieved. In this research, we propose an objective evaluation process for such system by evaluating seismic performance for large-scale factory facilities as an example.

Fe-Si-Cr ferroalloy is predominantly produced by carbothermic reduction. In this study, silicothermic and carbothermic mixed reduction of chromite ore to produce Fe-Si-Cr alloy is suggested. As reductants, silicon and silicon carbide are evaluated by thermochemical calculations, which prove that silicon carbide can be applied as a raw material. Considering the critical temperature of the change from the carbide to the metallic form of chromium, thereduction experiments were carried out. In these high temperature reactions, silicon and silicon carbide act as effective reductants to produce Fe-Si-Cr ferroalloy. However, at temperatures lower than the critical temperature, silicon carbide shows a slow reaction rate for reducing chromite ore. For the proper implementation of a commercial process that uses silicon carbide reductants, the operation temperature should be kept above the critical temperature. Using equilibrium calculations for chromite ore reduction with silicon and silicon carbide, the compositions of reacted metal and slag were successfully predicted. Therefore, the mass balance of the silicothermic and carbothermic mixed reduction of chromite ore can be proposed based on the calculations and the experimental results.