• 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.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.35 no.1
• /
• pp.61-67
• /
• 2015

Recently, the initiation of outside diameter stress corrosion cracking (ODSCC) at the tube support plate region of domestic steam generators (SG) with Alloy600 HTMA tubes has been increasing. As a result, SGs with Alloy600 HTMA tubes must be replaced early or are scheduled to be replaced prior to their designed lifetime. ODSCC is one of the biggest threats to the integrity of SG tubes. Therefore, the accurate evaluation of tube integrity to determine ODSCC is needed. Eddy current testing (ECT) is conducted periodically, and its results could be input as parameters for evaluating the integrity of SG tubes. The reliability of an ECT inspection system depends on the performance of the inspection technique and abilty of the analyst. The detection probability and ECT sizing error of degradation are considered to be the performance indices of a nondestructive evaluation (NDE) system. This paper introduces an optimized evaluation method for ECT, as well as the sizing error, including the analyst performance. This study was based on the results of a round robin program in which 10 inspection analysts from 5 different companies participated. The analysis of ECT sizing results was performed using a linear regression model relating the true defect size data to the measured ECT size data.

• Geophysics and Geophysical Exploration
• /
• v.21 no.1
• /
• pp.8-14
• /
• 2018

For the purpose of maintenance and prevention of earth fill dams against damage from natural hazards, automatic monitoring through various measuring instruments and resistivity survey has been carried out. Reservoirs and embankments have the structural vulnerability on the agricultural usages since most of them were built more than thirty years ago. The main aim to use monitoring method is to verify the safety and integrity of the dam. Resistivity survey can detect potential weaknesses, such as defective zones, anomalous seepages or internal erosion processes. Permanent resistivity monitoring systems were installed at a reservoir, which daily measurements have been taken every 6 hour. Using monitoring data for one year, anomalous seepage and structural defects were clarified for dam safety. Annual water level fluctuations are around 10 m. During their operation, reservoir dams are subject to a never-ending hydraulic load from the reservoir, which over the years may cause changes in the properties of the inner parts of the dam construction. Detailed analysis of the monitoring results was performed and showed that resistivities at most locations have been very stable over the full monitoring period excluding the effects of water fluctuation and seasons. To investigate the detectability of weak zone using the DC resistivity monitoring, numerical modeling with a simplified model for the drainage at a reservoir dam was also performed. The results showed that the seepage zone near drainage in a reservoir dam could be detected by resistivity response change.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.24 no.3
• /
• pp.259-267
• /
• 2004

A finite element method is used to simulate interaction of laser-based ultrasounds with surface breaking tracks in elastic media. The laser line source focused on the surface of semi-infinite medium is modeled as a shear dipole in 2-D plane strain finite elements. The shear dipole-finite clement model is found to give correct directivity patterns for generated longitudinal and shear waves. The interaction of surface waves with surface breaking cracks (2-D machined slot) is considered in two ways. Both the source and receiver are fixed with respect to the cracks in the first case, while the source is moving in another case. It is shown that the crack depth tested in the range of 0.3-5.0mm $({\lambda}_R/d=0.21{\sim}3.45)$ can be measured using the corner reflected waves produced by the fixed laser source. The moving laser source is found to cause a large amplitude change of reflected waves near crack, and the crack whose depth is one order lower than the wavelength ran be detected from this change.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2010.08a
• /
• pp.163-163
• /
• 2010

중적외선 영역 ($3{\sim}5\;{\mu}m$)은 공기 중에 존재하는 이산화탄소나 수증기에 의해 흡수가 일어나지 않기 때문에 군사적으로 중요한 파장 영역이며, 야간에 적을 탐지하는데 응용되고 있다. InSb는 77 K에서 중적외선 파장 흡수에 적합한 밴드갭 에너지 (0.228 eV)를 갖고 있으며, 다른 화합물 반도체와 달리 전하 수송자 이동도 (전자: $10^6\;cm^2/Vs$, 정공: $10^4\;cm^2/Vs$)가 매우 빠르기 때문에 적외선 화상 감지기 재료로 매우 적합하다. 또한 현재 중적외선 영역대에서 널리 사용되는 HgCdTe (MCT)와 대등한 소자 성능을 나타냄과 동시에 낮은 기판 가격, 소자의 제작 용이성 때문에 MCT를 대체할 물질로 주목 받고 있다. 하지만, 기판과 절연막의 계면에 존재하는 결함 때문에 에너지 밴드갭 내에 에너지 준위를 형성하여 높은 누설 전류 특성을 보인다. 따라서 InSb 적외선 소자의 구현을 위하여 고품질의 절연막의 연구가 필수적이라고 할 수 있겠다. 절연막의 특성을 알아보기 위해, n형 InSb 기판에 플라즈마 화학 기상 증착법 (PECVD)을 이용하여 $SiO_2$, $Si_3N_4$를 증착하였으며, 증착 온도를 $120^{\circ}C$에서 $240^{\circ}C$까지 $40^{\circ}C$ 간격으로 변화하여 증착온도가 미치는 영향에 대하여 알아보았다. 절연막과 기판의 계면 특성을 분석하기 위하여 77 K에서 커패시턴스-전압 (C-V) 분석을 하였으며, 계면 트랩 밀도는 Terman method를 이용하여 계산하였다 [1]. $Si_3N_4$를 증착하였을 경우, $120{\sim}240^{\circ}C$의 증착 온도에서 $2.4{\sim}4.9{\times}10^{12}\;cm^{-2}eV^{-1}$의 계면 트랩 밀도를 가졌으며, 증착 온도가 증가할수록 계면 트랩 밀도가 증가하는 경향을 보였다. 또한 모든 증착 온도에서 flat band voltage가 음의 전압으로 이동하였다. $SiO_2$의 경우 $120{\sim}200^{\circ}C$의 증착온도에서 $7.1{\sim}7.3{\times}10^{11}\;cm^{-2}eV^{-1}$의 계면 트랩 밀도 값을 보였으나, $240^{\circ}C$ 이상에서 계면 트랩밀도가 $12{\times}10^{11}\;cm^{-2}eV^{-1}$로 크게 증가하였다. $SiO_2$ 절연막을 사용함으로써, $Si_3N_4$ 대비 약 25% 정도 낮은 계면 트랩 밀도를 얻을 수 있었으며, 모든 증착 온도에서 양의 전압으로 flat band voltage가 이동하였다. 두 절연막에 대한 계면 트랩의 원인을 분석하기 위하여 XPS 측정을 진행하였으며, 깊이에 따른 조성 분석을 하였다. 본 실험에서 최적화된 $SiO_2$ 절연막을 이용하여 InSb 소자의 pn 접합 연구를 진행하였다. Be+ 이온 주입을 진행하고, 급속열처리(RTA) 공정을 통하여 p층을 형성하였다. -0.1 V에서 16 nA의 누설 전류 값을 보였으며, $2.6{\times}10^3\;{\Omega}\;cm^2$의 RoA (zero bias resistance area)를 얻을 수 있었다.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.23 no.2
• /
• pp.98-106
• /
• 2003

Nondestructive test (NDT) provides much information on concrete without damage of structural functions. Of NDT methods, elastic wave propagation methods, such as ultrasonic pulse velocity (UPV) method and impact-echo (IE) method, have been successfully used to estimate the strength, elastic modulus, and Poisson's ratio of concrete as well as to detect the internal microstructural change and defects. In this study, the concretes with water-binder ratio ranging from 0.27 to 0.50 and fly ash content of 20% were made and then their longitudinal wave velocities were measured by UPV and IE method, respectively. Test results showed that the UPV is greater than the longitudinal wave velocity measured by the If method, i.e., rod-wave velocity obtained from the same concrete cylinder. It was found that the difference between the two types of velocities decreased with increasing the ages of concrete and strength level. Moreover, for the empirical formula, the dynamic Poisson's ratio, static and dynamic moduli of elasticity, and velocity-strength relationship were determined. It was observed that the Poisson's ratio and the modulus of elasticity determined by the dynamic method are greater than those determined by the static test. Consequently, for the more accurate estimation of concrete properties using the elastic wave velocities, the characteristics of these velocities should be understood.

• Journal of the Korean Wood Science and Technology
• /
• v.38 no.6
• /
• pp.526-531
• /
• 2010

For efficient use of wood, it is important to control moisture of wood in processing wood. Near-infrared (NIR) spectroscopy can be used to estimate the physical and chemical properties of materials quickly and nondestructively. In this study, it was intended to measure the moisture contents on the surface of wood using NIR spectroscopy coupled with multivariate analytic statistical techniques. Because NIR spectroscopy is affected by the chemical components of the specimens and contains signal noise, a regression model for detecting moisture content of wood was established after carrying out several numerical pretreatments such as Smoothing, Derivative and Normalization in this study. It shows that the regression model using NIR absorbance in the range of 750~2,500 nm predicts the actual surface moisture content very well. Near-infrared spectroscopy technique developed in this study is expected to improve a technology to control moisture content of wood in using and drying process.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.1-11
• /
• 2024

Bridges crack and become damaged due to age and external factors such as earthquakes, lack of maintenance, and weather conditions. With the number of aging bridge on the rise, lack of maintenance can lead to a decrease in safety, resulting in structural defects and collapse. To prevent these problems and reduce maintenance costs, a system that can monitor the condition of bridge and respond quickly is needed. To this end, existing research has proposed artificial intelligence model that use sensor data to identify the location and extent of cracks. However, existing research does not use data from actual bridge to determine the performance of the model, but rather creates the shape of the bridge through simulation to acquire data and use it for training, which does not reflect the actual bridge environment. In this paper, we propose a bridge safety determination edge AI model that detects bridge abnormalities based on artificial intelligence by utilizing acceleration data from bridge occurring in the field. To this end, we newly defined filtering rules for extracting valid data from acceleration data and constructed a model to apply them. We also evaluated the performance of the proposed bridge safety determination edge AI model based on data collected in the field. The results showed that the F1-Score was up to 0.9565, confirming that it is possible to determine safety using data from real bridge, and that rules that generate similar data patterns to real impact data perform better.