본 논문에서는 구조물의 부분 변위값으로 전체 구조물의 변위 형상을 예측할 수 있는 인공지능 학습기법을 개발하였으며, 개발된 기술의 성능을 실험을 통해 평가하였다. 3차원 공간에서 변위 형상 및 노드 위치 좌표의 특성을 학습에 반영할 수 있는 Image-to-Image 변위 형상 학습과 위치 특징을 결합한 변위 상관 학습 방법을 제시하였다. 개발된 인공지능 학습방법의 성능을 평가하기 위해 목업 구 조 실험을 진행하였고, 3D 스캔으로 측정한 변위값과 인공지능으로 예측한 결과를 비교하였다. 비교 결과 인공지능 예측 결과는 3D 스캔 측정 결과에 비해 5.6~5.9%의 오차율을 보여 적정 성능을 보였다.

With the recent increase in the volume of liquid cargo transportation, there is a need for STS( Ship To Ship) globally. In the case of the STS mooring, the safety assessment should be conducted according to other criteria because mooring is different from the general mooring at the quay, but there is no separate standard in Korea. Thus in this study, STS mooring simulation and sensitivity analysis using OPTIMOOR program, the numerical analysis program, was conducted to identify the characteristics of the STS mooring. The target sea modeled the Yeosu port anchorage in Korea and the target ship was selected as the case of VLCC (Very Large Crude Oil Carrier)-VLCC. Through the numerical simulation and sensitivity analysis, the characteristics of STS mooring were identified. Also based on these results, we focused on establishing the standard for STS mooring safety assessment. Numerical simulation results show that the STS mooring safety can be changed according to a ship's cargo loading condition, pre-tension of mooring line, sea depth, encounter angle with the weather, and the weather condition. Additionally, the risk matrix is prepared to establish the safe external force range in the corresponding sea area. This result can be used to understand the mooring characteristics of STS and contribute to the revision of mooring safety assessment criteria.