http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
기하적인 형상 변형을 이용한 선박 브라켓 부재의 역변형 설계
천상욱(Sanguk Cheon),김형철(Hyeong-Cheol Kim) (사)한국CDE학회 2013 한국CDE학회 논문집 Vol.18 No.5
A method of designing a manufacturing shape of ship plate parts considering welding deformation is introduced. In this paper, the design shape of a bracket is deformed not by a thermoelastic method but by a pure geometric method. Deformation quantities are estimated based on data captured in the field and then a manufacturing design shape is obtained by deforming an original design shape by a geometric deformation method. The proposed method has been implemented and tested in the shipyard.
경량모델 기반 플랜트 구조물에 대한 동일 형상 판별 방법
천상욱(Sanguk Cheon),권기연(Ki-Youn Kwon) (사)한국CDE학회 2020 한국CDE학회 논문집 Vol.25 No.2
Lightweight models are widely used for visualizing and sharing large data in ships and plants. To minimize the file size and increase visibility, this model is mainly composed of triangular elements. Generally, ships and plants are composed of numerous thin metal plates, pipes and beams. These structures contain a large number of identical shapes. In this paper, we propose a method that can exactly determine identical shapes based on a lightweight model. The area and volume are compared for each part. Then, the boundary edges are extracted using triangular elements. The feature points are generated based on edge vertexes, bounding box, principle axis and secondary axis. Finally, the ICP (iterative closest point) is used to determine if thee feature points are in the same position.
Aveva Marine 배관 모델을 SmartMarine3D 배관 모델로 변환하는 방법
천상욱(Sanguk Cheon),이재준(Jae-Jun Lee),조민철(Min-Cheol Cho),이광(Kwang Lee) (사)한국CDE학회 2013 한국CDE학회 논문집 Vol.18 No.5
At shipyards, to enable design cooperation with engineering companies or to meet ship owner’s requirements, there is a need to translate ship models from one ship CAD system to another ship CAD system. In this paper, a method for translating pipe models from Aveva Marine to SmartMarine3D is introduced. Related data and architecture of translation system are addressed and specific details to be considered during translation are explained. The introduced method has been implemented and tested in a shipyard.
참조 모델과 설계 이력 데이터를 이용한 자동차 기구 요소의 지식 기반 설계 시스템 개발
천상욱 ( Sanguk Cheon ) 대한설비관리학회 2020 대한설비관리학회지 Vol.25 No.2
Reusing existing design data in product design can save resources by reducing the design data discussion process and redundant design work. The purpose of this paper is to improve the reuse rate of existing design data, reduce the quality problem of the model in the initial design stage, and to minimize the cost of frequent design changes. In order to support the effective inference process of knowledge-based design system, the types of product models were classified through characteristic analysis of design work. We apply the case-based and rule-based inferencing methods to support design knowledge reasoning so that the similarity of design data can be determined. The ontology model that defines the design history is designed using reference models, and the error of the redesigned CAD model of Class-3 is evaluated. The suggested design support method is implemented using XpertRule and is applied to automotive mechanical components.
선박 블록 단위의 대용량 JT 파일을 안드로이드 기기에서 가시화하는 방법
천상욱(Sanguk Cheon),서흥원(Heung-Won Suh) (사)한국CDE학회 2013 한국CDE학회 논문집 Vol.18 No.4
In shipbuilding, 2D manufacturing drawings are crucial for building a ship. Even various types of 3D models are being utilized for supporting ship manufacturing, which does not reduce the importance of 2D drawings. Recently things are changing in the shipbuilding industry. To reduce the number of 2D drawings or to reduce the quantity of information contained in 2D drawings, some attempts that can substitute for 2D drawings are being made. One of the attempts is to visualize lightweight 3D manufacturing models in a mobile device. In this paper, a method for displaying lightweight 3D models of a ship in an Android based device is introduced. To overcome the problem with parsing JT files in Android system, JT files are parsed in a Windows based server and as-simple-as-possible visualization data are transmitted to an Android based viewer. A comparison result with a commercial system is also given.
조선 PLM 환경에서 경량 CAD 모델에 대한 요구사항 분석 및 적용 사례
천상욱(Sanguk Cheon),이지훈(Ji-Hoon Lee),박광필(Kwang-Phil Park),서흥원(Heung-Won Suh) (사)한국CDE학회 2013 한국CDE학회 논문집 Vol.18 No.4
Introduction of PLM in domestic shipyards is being retarded as ship PLM has yet to firm up return of investment and process integration. To implement a ship PLM system, it is required to share ship CAD model data in various design and manufacturing environments. Lightweight CAD models provide a promising solution for sharing CAD models in the product life cycle, which can expedite implementation of ship PLM in domestic shipyards in the near future. Compared to proprietary CAD models, it is easy for lightweight CAD models to be interfaced with various application systems and be connected to manufacturing information. In this paper, the reason why lightweight CAD models are necessary to implement a ship PLM system is addressed and current implementation results are introduced.
조선 네스팅 문제의 부재 페어링을 위한 딥러닝 기반 부재 분류 방법
나건열(Gun-Yeol Na),천상욱(Sanguk Cheon),양정삼(Jeongsam Yang) (사)한국CDE학회 2021 한국CDE학회 논문집 Vol.26 No.4
With the rapid development of artificial intelligence technology, deep learning-based classification techniques have had enough reliability to be applied to industrial sites. However, while the study of the object classification on data acquired with 3D scanners or cameras has made remarkable progress, research activity based on geometric data sets is still in its infancy. In particular, in order to improve the classification performance of ship parts based on deep learning in the nesting problem to increase productivity in shipbuilding, the study of the construction of part datasets and data pre-processing is necessary. In this paper, we introduce a method to apply the artificial neural network technology of deep learning to the nesting algorithm for shipbuilding. Labeled with histogram-based shape contexts for constructing a dataset for classifying ship parts using Convolutional Neural Networks (CNNs). In addition, we introduce the preprocessing method of the geometric information of the ship parts for learning and the no-fit polygon (NFP) method for classified parts to pair up. To train the classification model for the 23,201 ship parts, a data set of 842 classes was constructed through the shape matching algorithm. The trained CNN model was able to classify those parts with an accuracy of 85.13%.