• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.92-99
• /
• 2004

The formation degree of sustain (ITO pattern) decides quality of PDP (Plasma Display Panel). For this reason, it makes efforts in searching defects more than 30 un as 100%. Now, the existing inspection is dependent upon naked eye or microscope in off-line PDP manufacturing process. In this study developed prototype inspection system of PDP 170 glass is based on line-scan mechanism. Developed system creates information that detects and sorts kinds of defect automatically. Designed inspection technology adopts multi-vision method by slip-beam formation for the minimum of inspection time and detection algorithm is embodied in detection ability of developed system. Designed algorithm had to make good use of kernel matrix that draws up an approach to geometry. A characteristic of defects, as pin hole, substance, protrusion, are extracted from blob analysis method. Defects, as open, short, spots and et al, are distinguished by line type inspection algorithm. In experiment, we could have ensured ability of inspection that can be detected with reliability of up to 95% in about 60 seconds.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.33 no.8
• /
• pp.807-812
• /
• 2009

Most structure engineers give the casting components over-estimated factor of safety without any reasonable foundation due to the worries about the unavoidable defects such as shrinkages and porosity in castings; the engineers have little knowledge on the relation between the defect and structural behavior. And the workers in casting field also do not know how to control the defects by manufacturing; they do not know to where the defects move or until how size they reduce the defects. In this study, shrinkage defect was scanned by industrial computerized tomography instrument (CT), and subsequently was modeled to a spheroid primitive for structural analysis. Using these simplified models of shrinkage, we observed the effects of the defect on the results of the structural analysis. A commercial structural analysis code was used to do the analysis works. Considering the conclusions, it is possible to manage the shrinkages effectively in casting process and to design the products with more reliable

• Journal of KIISE:Software and Applications
• /
• v.34 no.5
• /
• pp.447-454
• /
• 2007

TFT-LCD(Thin Film transistor liquid crystal display) has become actively used front panel display technology with increasing market. Intrinsically there is region of non uniformity with low contrast that to human eye is perceived as defect. As the gray level difference between the defect and the background is hardly distinguishable, conventional thresholding and edge detection techniques cannot be applied to detect the defect. Between the patterned and un-patterned LCD defects, this paper deals with un-patterned LCD defects by using independent component analysis, adaptive thresholding and skewness. Our method showed strong results even on noised LCD images and worked successfully on the manufacturing line.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.1
• /
• pp.58-68
• /
• 2006

The purpose of this study is to find empirical relationship between PL activities and firm performance. Five categories of PL activities and three performance measures were examined. Using a sample of 135 companies, we found that activities related to TQM practices and manufacturing defect had significant impacts on all three measures of performance. Activities related to design defect, warning defect and sales partially influenced performance measures. The result suggests that performance could be maximized by the mutual organic combination of the product safety efforts with the overall process from design to sales.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.10
• /
• pp.7-13
• /
• 2006

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.121-122
• /
• 2011

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.211-220
• /
• 2022

Recently, research on smart factories triggered by the 4th industrial revolution is being actively conducted. Accordingly, the manufacturing industry is conducting various studies to improve productivity and quality based on deep learning technology with robust performance. This paper is a study on the method of detecting tire surface defects in the visual inspection stage of the tire manufacturing process, and introduces a tire surface defect detection method using a depth image acquired through a 3D camera. The tire surface depth image dealt with in this study has the problem of low contrast caused by the shallow depth of the tire surface and the difference in the reference depth value due to the data acquisition environment. And due to the nature of the manufacturing industry, algorithms with performance that can be processed in real time along with detection performance is required. Therefore, in this paper, we studied a method to normalize the depth image through relatively simple methods so that the tire surface defect detection algorithm does not consist of a complex algorithm pipeline. and conducted a comparative experiment between the general normalization method and the normalization method suggested in this paper using YOLO V3, which could satisfy both detection performance and speed. As a result of the experiment, it is confirmed that the normalization method proposed in this paper improved performance by about 7% based on mAP 0.5, and the method proposed in this paper is effective.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.6
• /
• pp.579-587
• /
• 2015

Semiconductor manufacturing industry is a high density integration industry because it generates a vest number of data that takes about 300~400 processes that is supervised by numerous production parameters. It is asked of engineers to understand the correlation between different stages of the manufacturing process which is crucial in reducing production costs. With complex manufacturing processes, and defect processing time being the main cause. In the past, it was possible to grasp the corelation among manufacturing process stages through the engineer's domain knowledge. However, It is impossible to understand the corelation among manufacturing processes nowadays due to high density integration in current semiconductor manufacturing. in this paper we propose a canonical correlation analysis (CCA) using both wafer test voltage variables and fail bit counts variables. using the method we suggested, we can increase the semiconductor yield which is the result of the package test.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.1
• /
• pp.57-64
• /
• 2010

Metal Injection Molding (MIM) is attractive because it produces consistent, complex-geometry components for high-volume, high-strength, and high-performance applications. Also MIM using in optical communication field, display field, and semi-conductor field is a cost-effective alternative to metal machining or investment casting parts. It offers tremendous single-step parts consolidation potential and design flexibility. The objective of this paper is to study the suitability of design, flow analysis, debinding and sinterin processes, and capability analysis. The suitable injection conditions were 0.5~1.5 second filling time, 11.0~12.5 MPa injection pressure derived from flow analysis. The gravity of the product is measured after debinding an sintering. The maximum and minimum gravity levels are 7.5939 and 7.5097. the average and standard deviation are 7.5579 and 0.0122; when converted into density, the figure stands at 98.154%. According to an analysis of overall capacity, PPM total, which refers to defect per million opportunities(DPMO), stands at 166,066.3 Z.Bench-the sum of defect rates exceeding the actual lowest and highest limits-is 0.97, which translates into the good quality rate of around 88.4% and the sigma level of 2.47.