• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.133-138
• /
• 2005

Automotive pulleys play a key role in driving the cooling pump, oil pump, air-conditioner and so on by using an engine power. Researches on design processes and technologies of the pulleys can be found in many literatures. On the other hand, the areas related to manufacturing processes of the pulleys have been treated negligently. Vast data extracted from various information systems are transformed, integrated, and summarized to become a special database for helping users make a decision. The database, namely the data warehouse has been popularly used in the marketing and customer management of enterprises and recently applied to improve the design and manufacturing processes. In this study the manufacturing process of pulleys were analyzed through the intensive investigation of shop-floors and the interviews with workers and managers. The defects generated during a manufacturing process were categorized in a few types and the causes of defects examined for extracting the dominant parameters in the setup process for producing pulleys. As the first step to construct the data warehouse for the manufacturing processes of pulleys, authors proposed its architecture focused on the reduction of defect rate during the setup process.

• 한국기계가공학회지
• /
• 제19권5호
• /
• pp.82-90
• /
• 2020

Due to the complicated shape of the spider, the production method was changed from cold to warm forging. Finite element analysis was performed to predict the forging load and shape using the enclosed hydraulic die set. As the forging load increases due to the spider die volume, die stress analyses were performed to optimize the die design in order to reduce the die stress in various conditions. Large deformation while producing the complicated forging parts induces high forging load, which is one of the main parameters of the forging surface defects. The forging process was analyzed to find out the root cause of the surface defects generated during the spider production for various parameters, thereby revealing that the radius of die in the defect zone influenced the air trap depth, being the root cause of the surface defect. It was verified that die life was increased and the surface defect was eliminated by changing the die design during the mass production test.

• 한국산학기술학회논문지
• /
• 제17권8호
• /
• pp.379-388
• /
• 2016

현대 무기체계 제조를 위해 적용되는 수많은 생산 기술과 다양한 공정 환경으로 인해 다양한 결함이 무기체계 제조공정에 유입되고 있다. 이렇게 제조공정에 유입되는 결함 중 육안 검사, 기능 시험 등 기존 품질 관리 절차를 통해 검출할 수 있는 "명백결함(Patent Defect)"과 무기체계 복잡성과 제조공정의 복잡도로 기존 품질 관리 방식으로 검출이 제한되는 "잠재결함(Latent Defect)" 2가지 종류가 있다. 이러한 초기 결함 문제를 최소화하기 위해 무기체계 생산공정 중 유입된 결함요소를 환경부하(온도, 진동)를 활용하여 결함검출/제거/개선하기 위해 환경 부하 선별(ESS : Environmental Stress Screening) 시험을 수행해야 한다. 본 논문은 국내 무기체계 제조업체에서 정량적 환경 부하 선별 시험 설계의 어려움을 최소화하기 위해 MIL-HDBK-344(Environmental Stress Screening of Electronic Equipment)의 수학적 모델을 기반으로 정량적 환경 부하 선별시험 효과도 분석 및 프로파일 자동화 도구를 구현하였으며, 6가지(온도부하변수 3가지(온도범위/온도변화율/허용 잔류결함밀도), 진동부하변수 2가지(부하크기/허용 잔류결함밀도), 시험설계변수 1가지(허용 시험시간)) 시나리오를 통해 구현된 도구 유효성을 확인했다.

• 산업경영시스템학회지
• /
• 제46권4호
• /
• pp.312-320
• /
• 2023

Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

• 한국자동차공학회논문집
• /
• 제22권2호
• /
• pp.148-155
• /
• 2014

Most truck fires breaking out on the expressway are directly damaged by fire destruction of truck and freight and many of them cause indirect damage such as serious traffic holdups. This study analyzed the fire causes and their liability of the 25-ton truck fire breaking out during expressway driving. This truck fire was caused by manufacturing defect of return spring of a braking system. The fire liability rested with a maker(manufacturer) rather than a truck owner or a driver and the maker also bore fire liability based on the Product Liability Law.

• 한국생산제조학회지
• /
• 제20권2호
• /
• pp.139-144
• /
• 2011

This paper presents a boundary element application to determine the optimal impressed current densities at defect position on the pipe line. In this protection paint, enough current must be impressed to lower the potential distribution on the metal surface to the critical values. The optimal impressed current densities are determined in order to minimize the power supply for protection. This inverse problem was formulated by employing the boundary element method. Since the system of linear equations obtained was ill-conditioned, including singular value decomposition, conjugate gradient method were applied and the accuracies of these estimation. Several numerical examples are presented to demonstrate the practical applicability of the proposed method.

• 대한안전경영과학회지
• /
• 제8권1호
• /
• pp.27-42
• /
• 2006

Considering in view of China's low price and Japan's high technology, the most important point is the quality of product. To increase the comparative power internationally all workingmen have to fulfill the responsibility to maximize the quality, and this is possible practiced under 'Zero Defect' spirit. To reduce the defect ratio to 'Zero' the workingmen have to recognize own fault, all the manufacturing process should be conducted under 'Fool Proof System', If done under this circumstances, then labor force can work comfortably and safely without nervousness and tiresome. The productivity and quality can increase ultimately and even foreign labor, imbecile child, old-aged labor can participate in work, which can reduce shortage of labor source. Therefore, in this study all defects in manufacturing process, it would be recognized the errors and mistakes caused by human.

• Design & Manufacturing
• /
• 제14권4호
• /
• pp.52-57
• /
• 2020

In this study attempted to prevent defects due to blow holes among defects of sand casting products. It was intended to reduce the defect rate by reducing the blow hole of the inner surface. Currently, expectations and requirements for the quality level of non-ferrous aluminum casting in the casting industry are increasing. In addition, the shape is complex and the shrinkage precision is required. Among them, the test prototype is expensive to manufacture the mold, and the production time is also long, and the product is manufactured by sand casting. At this time, the highest defect rates are defects caused by shrinkage defects, surface defects, and blow holes.. At this study, the manufacturing time was shortened by using the shape of the fluid movement path in advance. Also, it is possible to reduce defects due to blow holes.

• 제어로봇시스템학회논문지
• /
• 제19권3호
• /
• pp.256-261
• /
• 2013

In the steel manufacturing area, researches for defect inspection receive a big attention for quality control. This paper proposes an algorithm to detect a scratch defect on steel billets. This algorithm takes ROIs (Regions of Interest), and extracts 11 features which represent properties of defect on a ROI. SVM (Support Vector Machine) is used to classify defect and normal ROIs. The algorithm classifies a frame image of a Billet as a defect image if there is one or more defect ROIs. In the experiments, the proposed algorithm had reliable classifying accuracy.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2000년도 춘계학술대회논문집 - 한국공작기계학회
• /
• pp.115-120
• /
• 2000

This study is on the application the image processing algorithm for inspection of the aluminium mill strip surface defect. The image of surface defect data was obtained using the CCD camera with the digital signal board. The edge was found from the difference of pixel intensity between the normal image and defect image. Two step were taken to find the edge in the image processing algorithm. First, noise was removed by using the median filter in the image. Second, the edge was sharpened in detail by using the sharpening convolution filter in the image. Canny algorithm was used to defect the exact edge. The defect section was separated from the original image is to find the coordination point p1 and p2 which include the defect image