• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.56-64
• /
• 2019

Various defects that occur in the maintenance stage are connected to all kinds of wasted resources and economic losses as additional investments are made. Residents are harmed temporally, materially, and psychologically, and businesses suffer not only monetary losses but also reduced credit ratings. The aim of this study was to increase the efficiency of quality management and minimize defect disputes by estimating the importance of the defect type considering the defect frequency and severity in apartment buildings. For this, 7,548 defect items for 48 apartment buildings were examined. The analysis confirmed that defects are concentrated on RC, finishing and MEP work. In addition, defects with high importance are identified as broken, incorrect installation, missing tasks, and water problems. In addition, the exterior wall/roof, the Internal wall, ceiling, and floor, which are constructed in the field, are more important than the furniture and MEP equipment installed in the field.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.2
• /
• pp.179-186
• /
• 1997

In this paper we suggest a development of surface defect inspection algorithms for cold mill strip. The defects which exist in a surface of cold mill strip have a scattering or singular distribution. This paper consists of preprocessing, feature extraction and defect classification. By preprocessing, the binarized defect image is achieved. In this procedure, Top-hit transform, adaptive thresholding, thinning and noise rejection are used. Especially, Top-hit transform using local min/max operation diminishes the effect of bad lighting. In feature extraction, geometric, moment and co-occurrence matrix features are calculated. For the defect classification, multilayer neural network is used. The proposed algorithm showed 15% error rate.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.12
• /
• pp.168-173
• /
• 1999

It is investigated that internal defect of planetary gear which consists of two gears with different number of teeth on both side. The internal defect, central burst, begin to form at the place of adiabatic shear band which usually has maximum ductile fracture value during the forming operation, forward and backward extrusion. It makes the plastic forming of planetary gear difficult. The prediction of defect to minimize the cost to produce the planetary gear. The finite element simulation code DEFORM is applied to analyze the defects. In the analysis, the toothed gears are assumed as axisymmetric cylinders whose diameters are equal to those of pitch circles of the each gears. Experiments were carried out with the SCM415 alloy steel as billet material and AIDA 630-ton knuckle-joint press. The calculated results and experimental inspections are compared to design a die and blank without defects and the results are useful to predict the internal defect.

• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.1
• /
• pp.57-62
• /
• 2002

The semiconductor industry has continuously been looking for the ways to improve yield and to reduce manufacturing cost. The layout modification approach, one of yield enhancement techniques, is applicable to all design styles, but it does not require any additional resources in terms of silicon area. The layout modification method for yield enhancement consists of making local variations in the layout of some layers in such a way that the critical area, and consequently the sensitivity of the layer to point defects, is reduced. Chen and Koren (1995) proposed a greedy algorithm that removes defect sensitive area using via moving, but it is easy to fall into a local minimum. In this paper, we present a via moving algorithm using simulated annealing and enhance yield by diminishing defect sensitive area. As a result, we could decrease the defect sensitive area effectively compared to the greedy algorithm presented by Chen and Koren. We expect that the proposed algorithm can make significant contributions on company profit through yield enhancement.

• Current Photovoltaic Research
• /
• v.8 no.1
• /
• pp.17-26
• /
• 2020

It is clear that monocrystalline Silicon (Si) ingots are the key raw material for semiconductors devices. In the present industries markets, most of monocrystalline Silicon (Si) ingots are made by Czochralski Process due to their advantages with low production cost and the big crystal diameters in comparison with other manufacturing process such as Float-Zone technique. However, the disadvantage of Czochralski Process is the presence of impurities such as oxygen or carbon from the quartz and graphite crucible which later will resulted in defects and then lowering the efficiency of Si wafer. The heat transfer plays an important role in the formation of Si ingots. However, the heat transfer generates convection in Si molten state which induces the defects in Si crystal. In this study, a crystal growth simulation software was used to optimize the Si crystal growth process. The furnace and system design were modified. The results showed the melt-crystal interface shape can affect the Si crystal growth rate and defect points. In this study, the defect points and desired interface shape were controlled by specific crystal growth rate condition.

• Journal of the Korean Society of Safety
• /
• v.30 no.5
• /
• pp.52-58
• /
• 2015

Although lots of safety inspection and precision safety diagnosis have been conducted on concrete retaining wall, there is no comprehensive analysis on the basis of the accumulated data associated with the statistic. Especially, the concentrated management is necessary on the evaluation items that cause critical damages for the efficient performance. In this regard, this study conducted a correlation analysis between the 18 condition evaluation items and defect index for the concrete retaining wall as well as how each item affects the final defect index as much as in the manual. As a result, correlation coefficient between sliding and overturning was 0.601, which means that they have a strong correlation, and the most influential item on defect index is the condition of drainage that scored the 0.750 correlation coefficient. In addition, as a result of regression analysis, the condition of drainage with the 0.683 correlation coefficient has a strong correlation with the defect index. If the condition evaluation items are integrated or readjusted based on the results of the statistical analysis in this study, the more efficient and accurate maintenance will be possible.

• Journal of Advanced Marine Engineering and Technology
• /
• v.30 no.5
• /
• pp.636-644
• /
• 2006

Recently, there were some successful examples that the laser welding was introduced into production line. However, the spread of laser welding is not sufficient in many industries. There are several reasons why it is difficult to penetrate the laser welding into production lines. Because it is different from reflection, absorption and permeation of laser beam according to material and surface condition. Moreover, there are significant problems in processing such as absorption and scattering of beam by the induced plasma or plume. Therefore, understanding of mechanism on formation of weld defect in laser welding of the laminated core for motor is very important. In this paper, it was analyzed in terms of materials which was source of defect in laser welding and conventional arc welding. As a results of analysis, insulation coating film of the laminated core was judged to main factor of weld defect. it could be well aware as tracing carbon volume, and it was deduced that weld defect by insulation coating film was caused by difference of mechanism between the two heat sources.

• Journal of the Korean Society of Safety
• /
• v.20 no.1 s.69
• /
• pp.55-61
• /
• 2005

The purpose of this study is to investigate the effect of circumferential location of local wall thinning defect on the collapse behavior of an elbow. Thus, the present study conducts three-dimensional finite element analysis on the 90-degree elbow containing a local wall thinning at intrados, crown and extrados of bend region and evaluates the collapse moment of wall thinned elbow under various thinning shapes and loading conditions. Combined internal pressure and bending moment are considered as an applied load. The internal pressure of $0\~20MPa$ and both closing and opening mode bending are employed. The results of analysis show that the reduction in collapse moment of the elbow by local wall thinning is more significant for a defect locating at crown than for a defect locating at intrados or at extrados. Also, the effect of internal pressure on the collapse moment of wall thinned elbow depends on the circumferential location of thinning defect and applied bending mode.

• Journal of Advanced Marine Engineering and Technology
• /
• v.40 no.4
• /
• pp.314-319
• /
• 2016

Flange bolt has a circular flange under the head that acts like a washer to distribute the clamping load over a large area. Flange bolt has usually been manufactured by cold forging. Flower shape defect occurs in the flange forging stage. This defect causes lack of dimensional accuracy and low quality. So it is needed to improve these forging defects. In this study, die design method for flower shape defect of flange bolt was suggested. In order to improve flower shape defect, inner diameter of the addition die in conventional forging process was modified. The forging process with applied modified die was simulated by commercial FEM code DEFORM-3D. The simulated results for modified die were confirmed by experimental trials with the same condition.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• 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.