• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 추계 학술발표회 3차
• /
• pp.72-77
• /
• 2010

The Incheon Bridge, which was opened to the traffic in October 2009, is an 18.4 km long sea-crossing bridge connecting the Incheon International Airport with the expressway networks around the Seoul metropolitan area by way of Songdo District of Incheon City. This bridge is an integration of several special featured bridges and the major part of the bridge consists of cable-stayed spans. This marine cable-stayed bridge has a main span of 800 m wide to cross the vessel navigation channel in and out of the Incheon Port. In waterways where ship collision is anticipated, bridges shall be designed to resist ship impact forces, and/or, adequately protected by ship impact protection (SIP) systems. For the Incheon Bridge, large diameter circular dolphins as SIP were made at 44 locations of the both side of the main span around the piers of the cable-stayed bridge span. This world's largest dolphin-type SIP system protects the bridge against the collision with 100,000 DWT tanker navigating the channel with speed of 10 knots. Diameter of the dolphin is up to 25 m. Vessel collision risk was assessed by probability based analysis with AASHTO Method-II. The annual frequency of bridge collapse through the risk analysis for 71,370 cases of the impact scenario was less than $0.5{\times}10^{-4}$ and satisfies design requirements. The dolphin is the circular sheet pile structure filled with crushed rock and closed at the top with a robust concrete cap. The structural design was performed with numerical analyses of which constitutional model was verified by the physical model experiment using the geo-centrifugal testing equipment. 3D non-linear finite element models were used to analyze the structural response and energy-dissipating capability of dolphins which were deeply embedded in the seabed. The dolphin structure secures external stability and internal stability for ordinary loads such as wave and current pressure. Considering failure mechanism, stability assessment was performed for the strength limit state and service limit state of the dolphins. The friction angle of the crushed stone as a filling material was reduced to $38^{\circ}$ considering the possibility of contracting behavior as the impact.

• 한국정보통신학회논문지
• /
• 제24권10호
• /
• pp.1331-1340
• /
• 2020

해상 객체 검출은 선장이 육안으로 해상 주변의 충돌 위험성이 있는 부유물을 컴퓨터를 통해 자동으로 검출하여 사람이 확인하는 방법과 유사한 정확도로 인지하는 방법을 말한다. 기존 선박에서는 레이더의 전파를 통해 해상 부유물의 유무와 거리를 판단하였지만 형체를 알아내어 장애물이 무엇인지는 판단할 수 없는 약점이 있다. 반면, 카메라는 인공지능 기술이 발달하면서 물체를 검출하거나 인식하는데 성능이 우수하여 항로에 있는 장애물을 정확하게 판단할 수 있다. 하지만, 디지털 영상을 분석하기 위해서는 컴퓨터가 대용량의 화소를 연산해야 하는데 CPU는 순차적 처리 방식에 특화된 구조이기에 처리속도가 매우 느려 원활한 서비스 지원은 물론 안전성도 보장할 수 없게 된다. 따라서 본 논문에서는 해상 객체 인식 소프트웨어를 개발하였고 연산량이 많은 부분을 가속화하기 위해 FPGA로 구현하였다. 또한, 임베디드 보드와 FPGA 인터페이스를 통해 시스템 구현 완성도를 높였으며 소프트웨어 기반의 기존 구현 방법보다 약 30배의 빠른 성능을 얻었고 전체 시스템의 속도는 약 3배 이상이 개선되었음을 확인할 수 있었다.