• 한국생산제조학회지
• /
• 제18권6호
• /
• pp.604-613
• /
• 2009

Recently, researches to develop phased array ultrasonic examination techniques are proceeded to diagnose dental caries and the status of surgical operation of dental implant. Sound field analysis of phased array ultrasonic transducers were carried out in order to characterizing the ultrasonic phased array beams. The sound field of ultrasonic radiation was calculated for the sample called "gypsum-improved stone" with the similar characteristics of dental materials. Industrial phased array ultrasonic devices were utilized for the insptriion of the artificial flaws machined in the gypsum-improved stone. Dental implants were made at the pig jaw bone and defect images were confirmed for the dental implants.

• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.99-103
• /
• 2021

Warpage defect detecting of scaffold is very important in biosensor production. Because warpaged scaffold cause problem in cell culture. Currently, there is no detection equipment to warpaged scaffold. In this paper, we produced detection model for shape warpage detection using deep learning based CNN. We confirmed the shape of the scaffold that is widely used in cell culture. We produced scaffold specimens, which are widely used in biosensor fabrications. Then, the scaffold specimens were photographed to collect image data necessary for model manufacturing. We produced the detecting model of scaffold warpage defect using Densenet among CNN models. We evaluated the accuracy of the defect detection model with mAP, which evaluates the detection accuracy of deep learning. As a result of model evaluating, it was confirmed that the defect detection accuracy of the scaffold was more than 95%.

• 산업경영시스템학회지
• /
• 제46권2호
• /
• pp.1-12
• /
• 2023

To make semiconductor chips, a number of complex semiconductor manufacturing processes are required. Semiconductor chips that have undergone complex processes are subjected to EDS(Electrical Die Sorting) tests to check product quality, and a wafer bin map reflecting the information about the normal and defective chips is created. Defective chips found in the wafer bin map form various patterns, which are called defective patterns, and the defective patterns are a very important clue in determining the cause of defects in the process and design of semiconductors. Therefore, it is desired to automatically and quickly detect defective patterns in the field, and various methods have been proposed to detect defective patterns. Existing methods have considered simple, complex, and new defect patterns, but they had the disadvantage of being unable to provide field engineers the evidence of classification results through deep learning. It is necessary to supplement this and provide detailed information on the size, location, and patterns of the defects. In this paper, we propose an anomaly detection framework that can be explained through FCDD(Fully Convolutional Data Description) trained only with normal data to provide field engineers with details such as detection results of abnormal defect patterns, defect size, and location of defect patterns on wafer bin map. The results are analyzed using open dataset, providing prominent results of the proposed anomaly detection framework.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2199-2213
• /
• 2024

To enhance the quality of defect detection for Printed Circuit Board Assembly (PCBA) during electronic product manufacturing, this study primarily focuses on optimizing the YOLOv7-based method for PCBA defect detection. In this method, the Mish, a smoother function, replaces the Leaky ReLU activation function of YOLOv7, effectively expanding the network's information processing capabilities. Concurrently, a Squeeze-and-Excitation attention mechanism (SEAM) has been integrated into the head of the model, significantly augmenting the precision of small target defect detection. Additionally, considering angular loss, compared to the CIoU loss function in YOLOv7, the SIoU loss function in the paper enhances robustness and training speed and optimizes inference accuracy. In terms of data preprocessing, this study has devised a brightness adjustment data enhancement technique based on split-filtering to enrich the dataset while minimizing the impact of noise and lighting on images. The experimental results under identical training conditions demonstrate that our model exhibits a 9.9% increase in mAP value and an FPS increase to 164 compared to the YOLOv7. These indicate that the method proposed has a superior performance in PCBA defect detection and has a specific application value.

• 품질경영학회지
• /
• 제37권3호
• /
• pp.83-93
• /
• 2009

This study proposes a stepwise approach to product safety management(PSM), of which roadmap consists of five phases. ISO 9001 QM model is assumed as the first-phase model and each higher-phase model is built by adding a corresponding module to the lower one. In the phase order, those modules are CCMS, a failure to warn, manufacturing defect and design defect. The progress in PSM of a domestic food company is discussed.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1998년도 추계학술대회 논문집
• /
• pp.66-71
• /
• 1998

• 산업공학
• /
• 제18권1호
• /
• pp.73-81
• /
• 2005

Injection molding has been widely used in producing plastic parts in large quantities. However, its productivity mainly depends on the expertise and experience of skilled workers because of the difficulty and complexity to determine a robust injection molding condition which is not influenced by the minor operational variation of an injection molding machine and produces good parts continuously. This study analyzes the defect types of the parts and proposes a support system to assist users in determining the robust process condition. The support system calculates the start condition from the information of an injection mold, the injection molding machine, the resin used, and the part. Through the iterative step which updates the condition using the defect information of the part tested, users can obtain the initial condition which produces the part without any problem for the first time. The support system also assists users in obtaining the robust condition from the initial condition using the technique of experimental design. To prove the validity of the support system, this study implements it in the control panel of the injection molding machine.

• International Journal of Precision Engineering and Manufacturing
• /
• 제6권3호
• /
• pp.19-23
• /
• 2005

To minimize the weld defect in manufacturing of the welded tube by using $CO_2$ laser, the monitoring of the welding quality and the seam tracking along the butt-joint lengthwise to the tube axis are studied. The longitudinal butt-joint is shaped from $60kgf/mm^2$ grade steel sheet by 2 roll bending method, and welded by the $CO_2$ laser welding system equipped with the seam tracker and plasma sensor. The laser welded tube has the thickness of 1.5mm, diameter of 105.4mm and length of 2000mm. The precise positioning of the laser beam on the butt-joint to be assembled is obtained within $200{\mu}m$ by the laser vision sensor. The artificial defects in the butt-joint are well observed by the signal of plasma intensity measured from the plasma sensor of UV wavelength range within 400nm. The developed $CO_2$ laser tube welding system has the function of the precision seam tracking and the real-time monitoring of the welding quality. In conclusion, the laser welded tube can be used for manufacturing of automobile chassis and components after hydro-forming.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2008년도 춘계 학술발표회 제20권1호
• /
• pp.469-472
• /
• 2008

본 연구에서는 경제성, 환경부하저감성 및 순환잔골재의 품질개선효과가 우수한 순환잔골재 건식생산기술로서 고속회전충격식 비중분리장치 및 원심력 미분말 집진장치 등으로 구성된 건식생산시스템을 개발하고 순환잔골재의 품질을 평가하여 성능을 검증하고자 한다. 그 결과 고속회전충격에 의한 순환잔골재의 파쇄작용, 원심력 및 질량차에 의한 미분말과 미세분진의 분리 및 집진작용, 질량차에 의한 미세립분의 분리 회수에 의해 표준입도, 절건밀도 등 순환잔골재의 품질개선에 효과가 있는 것으로 확인되었다.

• 한국기계가공학회지
• /
• 제12권6호
• /
• pp.69-76
• /
• 2013

This paper presents the development of the FCF method for the manufacturing of final products using numbers related to the minimum amount of work. The utilized product is a drum clutch, which is part of the transmission of an automobile. A double acting press is secured first and a prediction of the forming load on the practical material is made through an experiment with a plasticine model. Also, a finite element simulation using product shape and properties is performed, as well as a press experiment. A double acting press is manufactured that is suitable for a double acting experiment with a conventional hydraulic press(200 tons). A peripheral device for the press is additionally designed for experimental purposes. And, the press has as its essential points the drive speed, stroke control, etc., all of which influence the forming and is modified. Especially, a laser system is used for velocity measurement of two punches. The forming load of a practical material is predicted in order to derive a forming load formula for cold conditions on the basis of approximate similarity theory. Finite element analysis of the relative velocity ratio(RVR), etc., for most suitable flow defect(unfilling, etc.) prevention is achieved as well. The results are verified through a press experiment.