• 산업공학
• /
• 제21권2호
• /
• pp.151-160
• /
• 2008

Defect size distribution is a probability density function for the defects that occur on wafers or glasses during semiconductor/LCD fabrication. It is one of the most important information to estimate manufacturing yield using well-known statistical estimation methods. The defects are detected by automatic optical inspection (AOI) facilities. However, the data that is provided from AOI is not accurate due to resolution of AOI and its defect detection mechanism. It causes distortion of defect size distribution and results in wrong estimation of the manufacturing yield. In this paper, I suggest a size conversion method and a maximum likelihood estimator to overcome the vague defect size information of AOI. The methods are verified by the Monte Carlo simulation that is constructed as similar as real situation.

• 산업경영시스템학회지
• /
• 제27권2호
• /
• pp.10-16
• /
• 2004

Data mining technique is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules. This paper uses a data mining technique for the prediction of defect types in manufacturing Process. The Purpose of this Paper is to model the recognition of defect type Patterns and Prediction of each defect type before it occurs in manufacturing process. The proposed model consists of data handling, defect type analysis, and defect type prediction stages. The performance measurement shows that it is higher in prediction accuracy than logistic regression model.

• 반도체디스플레이기술학회지
• /
• 제21권4호
• /
• pp.168-173
• /
• 2022

As the function of a product is advanced and the process is refined, the yield in the fine manufacturing process becomes an important variable that determines the cost and quality of the product. Since a fine manufacturing process generally produces a product through many steps, it is difficult to find which process or equipment has a defect, and thus it is practically difficult to ensure a high yield. This paper presents the system architecture of how to build a smart manufacturing system to analyze the big data of the manufacturing plant, and the equipment factor analysis methodology to increase the yield of products in the smart manufacturing system. In order to improve the yield of the product, it is necessary to analyze the defect factor that causes the low yield among the numerous factors of the equipment, and find and manage the equipment factor that affects the defect factor. This study analyzed the key factors of abnormal equipment that affect the yield of products in the manufacturing process using the data mining technique. Eventually, a methodology for finding key factors of abnormal equipment that directly affect the yield of products in smart manufacturing systems is presented. The methodology presented in this study was applied to the actual manufacturing plant to confirm the effect of key factors of important facilities on yield.

• 한국빅데이터학회지
• /
• 제3권1호
• /
• pp.95-103
• /
• 2018

ICT 기술의 발전에 따라 제조 산업은 공정 상에서 생성되는 제조 데이터를 분석하여 효율을 높이고자 많은 노력을 하고 있다. 본 논문에서는 스마트 공장의 일환으로 의사결정나무 알고리즘(CHAID)을 이용한 데이터 마이닝 기반 제조공정을 제안한다. 약 5개월간 수집된 실제 제조 공정의 432개 센서 데이터를 활용하여 불량률이 낮은 안정적인 공정 기간과 불량률이 높은 불안정한 공정 기간 간에 유의미한 차이를 보이는 변수를 찾아냈다. 선정된 최종 변수가 불량률 개선에 실제로 효과가 있는지를 측정하기 위해 해당 변수의 안정 값 범위를 설정하여 14일 간 공정에서 해당 센서가 안정 값의 범위를 벗어나지 않도록 공정 설정 값을 조절했고, 불량률 개선의 효과를 측정하였다. 이를 통해 제조 산업에서 생성되는 공정 센서 데이터를 활용 및 분석하여 불량률을 개선할 수 있는 실증적인 가이드라인을 제시할 수 있을 것으로 기대한다.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.81-86
• /
• 2023

Recently, there has been an increased demand for light-emitting diode (LED) due to the growing emphasis on environmental protection. However, the use of GaN-based sapphire in LED manufacturing leads to the generation of defects, such as dislocations caused by lattice mismatch, which ultimately reduces the luminous efficiency of LEDs. Moreover, most inspections for LED semiconductors focus on evaluating the luminous efficiency after packaging. To address these challenges, this paper aims to detect defects at the wafer stage, which could potentially improve the manufacturing process and reduce costs. To achieve this, image processing and deep learning-based defect detection techniques for Sapphire Epi-Wafer used in Green LED manufacturing were developed and compared. Through performance evaluation of each algorithm, it was found that the deep learning approach outperformed the image processing approach in terms of detection accuracy and efficiency.

• 한국레이저가공학회지
• /
• 제15권1호
• /
• pp.6-9
• /
• 2012

In TFT-LCD manufacturing process, various defects are generated by manufacturing machine trouble or particle. These defects can be repaired through the TFT-Laser repair process that only can't be automated in TFT-LCD manufacturing Process. In this Paper, we propose auto defect algorithm for TFT-LCD laser repair machine using image processing algorithm in order to automate process. Proposed algorithm can detect very small defects (< 2um) in 98% success ratio, and generated laser repair path guarantee highly precise position accuracy. Through proposed system, much of the work still done the old-fashioned way, by hand, can be automated and manufacturing company can be strengthed the competitiveness of cost.

• Journal of the Korean Data and Information Science Society
• /
• 제19권2호
• /
• pp.609-620
• /
• 2008

There may be several parallel equipments having the same function in a multi-stage manufacturing process, which affect the product quality differently and have significant differences in defect rate. The product quality may depend on what equipments it has been processed as well as what process variable values it has. Applying one model ignoring the presence of different equipments may distort the prediction of defect rate and the identification of important quality variables affecting the defect rate. We propose a procedure for data segmentation when constructing models for predicting the defect rate or for identifying major process variables influencing product quality. The proposed procedure is based on the principal component analysis and the analysis of variance, which demonstrates a better performance in predicting defect rate through a case study with a PDP manufacturing process.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.108-111
• /
• 2022

제품의 결함 탐지를 위한 머신 비전 시스템에 딥러닝을 적용하기 위해서는 다양한 결함 사례에 대한 방대한 학습 데이터가 필요하다. 하지만 실제 제조 산업에서는 결함의 종류에 따른 데이터 불균형이 생기기 때문에 결함 사례를 일반화할 수 있을 만큼의 제품 이미지를 수집하기 위해서는 많은 시간이 소요된다. 본 논문에서는 적은 데이터로도 학습이 가능한 샴 신경망을 제품 결함 탐지에 적용하고, 제품 결함 이미지 데이터의 속성을 고려하여 이미지 쌍 구성법과 대조 손실 함수를 수정하였다. AUC-ROC로 샴 신경망의 임베딩 성능을 간접적으로 확인한 결과, 같은 제품끼리만 쌍을 구성하고 결함이 있는 제품 간에는 쌍을 구성하였을 때, 그리고 지수 대조 손실로 학습하였을 때 좋은 임베딩 성능을 보였다.

• International Journal of Contents
• /
• 제13권2호
• /
• pp.57-65
• /
• 2017

Recently, due to the significance of Industry 4.0, the manufacturing industry is developing globally. Conventionally, the manufacturing industry generates a large volume of data that is often related to process, line and products. In this paper, we analyzed causes of defective products in the manufacturing process using the decision tree technique, that is a well-known technique used in data mining. We used data collected from the domestic manufacturing industry that includes Manufacturing Execution System (MES), Point of Production (POP), equipment data accumulated directly in equipment, in-process/external air-conditioning sensors and static electricity. We propose to implement a model using C4.5 decision tree algorithm. Specifically, the proposed decision tree model is modeled based on components of a specific part. We propose to identify the state of products, where the defect occurred and compare it with the generated decision tree model to determine the cause of the defect.

• 산업경영시스템학회지
• /
• 제34권3호
• /
• pp.115-122
• /
• 2011

The critical role played by manufacturing performance measurement systems in achieving competitive success is increasingly recognized. Developing an integrated performance measurement model is significant for strategic management. This study consist of several principal steps. Performance criteria from the literature and an questionnaire were utilized prior to building the performance model. The AHP(Analytic Hierarchy Process) is utilized to evaluate the weight of each criterion when generating the performance measurement model for Korea automobile parts manufacturing company. AHP analysis showed clear difference in the priority between 5 criteria and 24 sub-criteria in terms of manufacturing performance of Korean automobile parts manufacturing company. The result of priority evaluation in the 5 criteria of 2nd level was ranked quality, cost, delivery, employee, flexibility. And the critical sub-criteria in the 24 sub-criteria of 3rd level was ranked claim rate, process defect rate, outsourcing parts defect rate, ability to quality management innovation, claim cost, etc.