• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2001년도 추계종합학술대회
• /
• pp.587-591
• /
• 2001

본 연구에서는 영상 처리를 이용하여 외형적인 칼라 팔레트내의 불량품을 식별하는 실험을 수행하고자 한다. 기본적인 팔레트 자동선별시스템에 대해 기술하며, 각 샘플링된 팔레트에 대해 영상처리기법을 이용한 불순물 검출 알고리듬을 제안하고자 한다. 또한 이를 상용화할 수 있도록 윈도우환경의 비전처리 프로그램을 제시하였다. 끝으로 본 연구에 대한 평가와 앞으로의 연구과제에 대해 기술하고자 한다.

• 한국안전학회지
• /
• 제17권4호
• /
• pp.110-118
• /
• 2002

During the last ten years, the need has been increase for reducing maintenance cost for aged equipments are ensuring safety, efficiency and profitability of petrochemical and refinery plants. American Petroleum institute(API) developed a code, API 581 for proposing standard procedures of risk based inspection. Even though the API 581 code covers general RBI procedures, there must be some limitations. In this study, a semi-quantitative assessment algorithm for RBI based on the API 581 code was reconstructed for developing an RBI software. The user-friendly realRBI software is developed with a module for evaluation semi-quantitative risk category using the potential consequence factor and the likelihood factor. Also, inspection planning module for inspection time and inspection method for equipments are included.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.1549-1552
• /
• 1997

In this paper, a optimal algorithm that can produce the FOV is proposed in terms of using the Kohonen's Self-Organizing Map(KSOM). A FOV, that stands for "Field Of View", means maximum area where a camera could be wholly seen and influences the total time of inspection of vision system. Therefore, we draw algorithm with a KSOM which aims to map an input space of N-dimensions into a one-or two-dimensional lattice of output layer neurons in order to optimize the number and location of FOV, instead of former sequentila method. Then, we show demonstratin through computer simulation using the real PCB data. PCB data.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 춘계학술대회
• /
• pp.598-603
• /
• 2003

During the last ten years, the need has been increased for reducing maintenance cost for aged equipments and ensuring safety, efficiency and profitability of petrochemical and refinery plants. RBI (Risk Based Inspection) methodology is one of the most promising technologies satisfying the need in the field of integrity management. In this study, a user-friendly software, realRBI for RBI based on the API 581 code was developed and a quantitative analysis was performed for over 500 equipments in a domestic plant whose operating time reaches about 13 years. Current risks for each equipment parts were evaluated and risk based prioritization were determined as a conclusion.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 추계학술대회
• /
• pp.164-169
• /
• 2003

The purpose of this study is to develop a practical image inspect ion system that could recognize it correctly, endowing flexibility to the productive field, although the same object for work will be changed in the size and rotated. In this experiment, it selected a fighter, rotating the direction from 30$^{\circ}$ to 45 simultaneously while changing the size from 1/4 to 1/16, as an object inspection without using another hardware for exclusive image processing. The invariant moments, Hu has suggested, was used as feature vector moment descriptor. As a result of the experiment, the image inspect ion system developed from this research was operated in real-time regardless of the chance of size and rotation for the object inspection, and it maintained the correspondent rates steadily above from 94％ to 96％. Accordingly, it is considered as the flexibility can be considerably endowed to the factory automat ion when the image inspect ion system developed from this research is applied to the product ive field.

• 품질경영학회지
• /
• 제23권3호
• /
• pp.33-44
• /
• 1995

This paper presents an automated visual inspection system for the electronic parts manufacturing process. In this system, a statistical process control (SPC) method is integrated into the automated inspection method on a real time base. It shows how the collected data can be analyzed with the SPC to provide process information. Also presented are studies of subpixel image processing technology to improve the accuracy of parts measurements, and the cumulative-sum (CUSUM) control chart for fraction defectives. An application of the developed system to connector manufacturing process as a part of computer integrated manufacturing (CIM) is presented.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2004년도 춘계 학술발표대회 개요집
• /
• pp.302-304
• /
• 2004

Nuclear fuel elements containing dry recycling nuclear fuel pellets for the irradiation test in a reactor were remotely fabricated from spent PWR fuel materials in a hot cell. End closure welding as well as seal tube welding for thermal sensor of the elements was performed by Nd:YAG laser. The soundness of the end closure welds and seal tube welds for the elements were evaluated by a precise X-ray inspection system composed of a micro-focus X-ray generator with an image intensifier and a real time camera system. Then, helium leak test was performed for the elements. The soundness of the welds of the fuel elements was confirmed by the X-ray inspection and helium leak test. The irradiation test for the fuel elements were successfully completed at the HANARO research reactor.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2006년도 춘계학술대회 논문집
• /
• pp.61-62
• /
• 2006

A new neural network classifier is proposed for the automatic real-time surface inspection of high-speed cold steel strips having 11 different types of defects. 46 geometrical and gray-level features are extracted for the defect classification. 3241 samples of Posco's Kwangyang steel factory are used for training and testing the neural network classifier. The developed classifier produces plausible 15% error rate which is much better than 20-30% error rate of human vision inspection adopted in most of domestic steel factories.

• 한국정밀공학회지
• /
• 제24권4호
• /
• pp.76-83
• /
• 2007

A new neural network classifier is proposed for the automatic real-time surface inspection of high-speed cold steel strips having 11 different types of defects. 46 geometrical and gray-level features are extracted for the defect classification. 3241 samples of Posco's Kwangyang steel factory are used for training and testing the neural network classifier. The developed classifier produces plausible 15% error rate which is much better than 20-30% error rate of human vision inspection adopted in most of domestic steel factories.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 B
• /
• pp.406-408
• /
• 1997

This paper presents the new method of a nondestructive spot welding state inspection system using neural networks. The learning process of neural networks makes the inspection system to adapt the variable welding parameters. The inspecting process is working with on-line real-time after off-line learning process. This neural network based inspection system shows reliable results through the field test for variations of applied voltages, currents, and contact area of the welding electrode.