• 한국산학기술학회논문지
• /
• 제12권4호
• /
• pp.1812-1816
• /
• 2011

본 연구에서는 약액 주입 후 미 도포로 인한 복합적인 공정불량을 예방하기 위하여 100nm 이하의 나노 반도체 제조공정에서 필수적인 스피너(spinner) 장비를 위한 약액 흐름제어 시스템을 개발하였다. 본 연구개발을 통하여 실시간으로 상태요소들을 감시할 뿐만 아니라 상태요소의 비정상적 변화나 웨이퍼 가공불량이 발생할 경우 해당 유니트를 정지시킴과 동시에 원격지에 있는 엔지니어에게 경보를 전송함으로써 즉각적인 대처가 가능하여 모듈의 수율을 향상시킬 수 있을 것으로 기대된다. 또한 세부 동작 시퀀스를 제어하기 위한 H/W와 S/W 시스템을 생산라인에 실장하고 성능점검 및 인증을 수행한 결과 5가지의 유형별 비정상적 프로세스를 정확히 검출하였다.

• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.76-83
• /
• 2023

Recently, the development of computer vision with deep learning has made object detection using images applicable to diverse fields, such as medical care, manufacturing, and transportation. The manufacturing industry is saving time and money by applying computer vision technology to detect defects or issues that may occur during the manufacturing and inspection process. Annotations of collected images and their location information are required for computer vision technology. However, manually labeling large amounts of images is time-consuming, expensive, and can vary among workers, which may affect annotation quality and cause inaccurate performance. This paper proposes a process that can automatically collect annotations and location information for images using eXplainable AI, without manual annotation. If applied to the manufacturing industry, this process is thought to save the time and cost required for image annotation collection and collect relatively high-quality annotation information.

• 한국정보통신학회논문지
• /
• 제25권3호
• /
• pp.471-477
• /
• 2021

디스플레이 분야에 스마트 팩토리란 작업 자동화 뿐만 아니라 기존의 공정관리, 이동설비, 공정이상, 결함 분류 등에 AI/BIG DATA 기술을 이용한 보다 효율적인 디스플레이 제조를 의미한다. 과거 디스플레이 제조 과정에서 불량이 나오면 결함 분류, 공정 이상에 대한 대처가 시시각각 달랐기 때문에 이에 대한 많은 시간 소모가 발생했었다. 하지만 디스플레이 제조 분야는 고도화된 공정 장비를 이용해야 하고 불량 원인을 신속하게 파악해 수율을 올리는 것이 디스플레이 제조 산업의 경쟁력이다. 본 논문에는 스마트 팩토리 AI/BIG DATA 기술을 디스플레이 제조에 접목한 사례들에 대해 정리해 보고 기존 방법 대비 어떤 장점이 도출 되어질 수 있는지에 대해 처음으로 분석해 보고자 한다. 이를 통해 향후 AI/BIG DATA를 이용한 디스플레이 제조 분야에 보다 향상된 스마트 팩토리 개발을 위한 사전지식으로 활용하고자 한다.

• 제어로봇시스템학회논문지
• /
• 제14권5호
• /
• pp.415-419
• /
• 2008

Detecting and correcting defects on LCD glasses early in the manufacturing process becomes important for panel makers to reduce the manufacturing costs and to improve productivity. Many attempts have been made and were successfully applied to detect and identify simple defects such as scratches, dents, and foreign objects on glasses. However, it is still difficult to robustly detect low-contrast defect region, called Mura or blemish area on glasses. Typically, these defect areas are roughly defined as relatively large, several millimeters of diameter, and relatively dark and/or bright region of low Signal-to-Noise Ratio (SNR) against background of low-frequency signal. The aim of this article is to present a robust algorithm to segment these blemish defects. Early 90's, a highly robust estimator, known as the Model-Fitting (MF) estimator was developed by X. Zhuang et. al. and have been successfully used in many computer vision application. Compared to the conventional Least-Square (LS) estimator the MF estimator can successfully estimate model parameters from a dataset of contaminated Gaussian mixture. Such a noise model is defined as a regular white Gaussian noise model with probability $1-\varepsilon$ plus an outlier process with probability $varepsilon$. In the sense of robust estimation, the blemish defect in images can be considered as being a group of outliers in the process of estimating image background model parameters. The algorithm developed in this paper uses a modified MF estimator to robustly estimate the background model and as a by-product to segment the blemish defects, the outliers.

• International Journal of Precision Engineering and Manufacturing
• /
• 제7권3호
• /
• pp.18-23
• /
• 2006

The formation degree of sustain (ITO pattern) determines the quality of a PDP (Plasma Display Panel). Thus, in the present study, we attempt to detect 100% of the defects that are larger than $30{\mu}m$. Currently, the inspection method in the PDP manufacturing process is dependent upon the naked eye or a microscope in off-line mode. In this study, a prototype inspection system for PDP ITO patterned glass is developed. The developed system, which is based on a line-scan mechanism, obtains information on the defects and sorts the defects by type automatically. The developed inspection system adopts a multi-vision method using slit-beam formation for minimum inspection time and the detection algorithm is embodied in the detection ability. Characteristic defects such as pin holes, substances, and protrusions are extracted using the blob analysis method. Defects such as open, short, spots and others are distinguished by the line type inspection algorithm. It was experimentally verified that the developed inspection system can detect defects with reliability of up to 95% in about 60 seconds for the 42-inch PDP panel.

• 유통과학연구
• /
• 제17권4호
• /
• pp.51-57
• /
• 2019

Purpose - This study aims to improve the distribution structure of the OLED market and develop cost-effective optimization techniques. Specifically, it is a study on the optimization of ferric chloride to improve the etch of SUS MASK for OLED. Research design, data, and methodology - Applying the optimal conditions of the experiment, the final confirmation was evaluated for improvement by the Process Capability Index (Cpk). It is possible to derive social performance such as improvement of precision of SUS MASK manufacturing, economic performance such as defect rate, reduction of waste generation and treatment cost, technological achievement such as SUS MASK production technology, improvement of profit structure of technology development and process improvement do. Results - The improvement of the Cpk before the improvement was made was confirmed to be 0.57% with a defect estimate of 25.07% with a failure estimate of 0.57% after the improvement, and 8.84% with a failure estimate of 0.57% level after the improvement. Conclusions - If the conclusions obtained from the specimen experiment are applied to the manufacturing process of SUS MASK, it will be possible to expect excellent cost-effective competitiveness due to the improvement of precision and reduction of defect rate to enhance the OLED market penetration.

• 한국화재소방학회논문지
• /
• 제30권3호
• /
• pp.94-103
• /
• 2016

이 논문에서는 1년 전에 구입하여 8,500 km를 주행한 차량에서 발생한 화재사례를 분석하였다. 이 차량은 차량이 적색교통신호로 멈추었다가 파란불로 바뀌어 출발할 때 옆 차량이 경음기를 울려서 차량을 세워 확인해보니 엔진 쪽에 불이 붙어 있었다. 이 차량 화재는 배터리 + 단자에 삽입하여 나사로 조이는 고리의 전기적인 스파크로 인해 발생하였을 가능성이 높은 것으로 분석하였다. 그리고 그 고리의 전기적인 스파크는 제조결함으로 인해 발생한 것이므로 화재발생책임은 소유자나 운전자와 관련이 없이 제조자에게 있는 것으로 분석하였다. 이 차량화재의 화재발생책임과 관련하여 법원에서 제조자의 제조결함을 인정하였다.

• 한국산학기술학회논문지
• /
• 제10권7호
• /
• pp.1725-1728
• /
• 2009

본 연구개발에서는 정해진 환경에서 최대의 불량검출 능력을 발휘할 수 있도록 공정을 개선하기 위하여 전게이트 시각검사에 필수적인 FGV 패턴발생 장치와 공정제어 장치를 개발하였다. 본 연구개발을 통하여 접촉손실(Tact Loss)을 0에 근접 한 수준으로 유지할 뿐만 아니라 손실 및 에러 발생시 신속한 대처가 가능하여 모듈의 수율을 향상시킬 수 있을 것으로 기대된다. 또한 세부 동작 시퀀스를 제어하기 위한 H/W와 S/W 시스템을 생산라인에 실장하고 성능점검 및 인증을 수행한 결과 Tact에 의한 Pixel 불량의 경우는 98.1%, Line 불량의 경우는 99.1%의 검출율을 나타내었으며, Gate 및 Visual 레벨 테스트를 포함한 모듈공정 전체의 수율이 98.3%까지 증가하였다.

• 품질경영학회지
• /
• 제20권2호
• /
• pp.76-93
• /
• 1992

The purpose of this study, by surveying the status of firms, measurement-related investment and the defect rate, is to analyze the effect of measurement-related investment and to propose a scheme of efficient measurement-related investment which reduces the defect rate. For this project we obtain the data of the status of the measurement-related investment and the defect rate of 928 firms in Korean manufacturing industry by mailing survey. One of our results shows that the firms which have measurement standard laboratory, i.e, which invest in measurement-related area comparatively high, have the defect rate about 0.8% lower than those firms which don't have measurement standard laboratory. Also we find that the small-and-middle size firms have worse measurement-related facility than the large firms and the firms in the heavy-chemical industry have higher measurement-related investment effect than the firms in the light industry.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1999년도 춘계학술대회 논문집
• /
• pp.222-228
• /
• 1999

The two-microphone sound-intensity technique has been used for the detection of defects in radially loaded ball bearings. The difference in the sound-intensity levels measured for bearings with no defect and for those with intentionally introduced defects of different sizes in their elements under various operating conditions of loads and speeds is demonstrated. A change in the intensity frequency spectrum because of the defects is observed. The results show that the detectability of an outer-race defect is much better than that of on inner-race or ball defect. It is difficult to detect defects at lower speeds. Sound-pressure measurements were also performed fur comparison, and it is shown that the detectability of defects by sound-intensity measurements is better than that by sound-pressure measurements.