• Journal of the Korean Society of Safety
• /
• v.18 no.4
• /
• pp.28-34
• /
• 2003

In the present study, three-dimensional finite element analysis was performed to investigate the effects of internal wall thinning defect on the failure pressure of elbow in the piping system and to develop the failure pressure evaluation model. From the results of finite element analysis, the failure pressure was derived by employing local stress criteria, and the effects of thinning location, bend radius, and defect geometry on the failure pressure of internally wall thinned elbow were investigated. Also, based on these investigations and previous model developed to estimate the failure pressure of elbow with an external pitting defect, the failure pressure evaluation model to be applicable to the elbow containing an internal thinning defect was proposed and compared with the results of finite element analysis. The failure pressure calculated by the model agreed well with the results of finite element analysis.

• Proceedings of the KIEE Conference
• /
• 2003.07b
• /
• pp.702-704
• /
• 2003

In this paper, analysis of bobbin probe signal in steam generator tube with bulge defect on CE system 80 nuclear power plant is represented. The CE system 80 steam generator is adopted in ULJIN-4 nuclear power plant. From Maxwell's equation, the electromagnetic governing equation for eddy current problem is derived and by performing the finite element formulation the 3-dimensional finite element code with brick element is developed. For the ease of the comparison the numerical results with experimental ones, the calculated signals are adjusted by using the ASME standard 100[%] through hole signal. For analysis of the effect of variation of the bulge depth on the impedance signal 0.2[mm] and 0.4[mm] depth of bulge defect signals are calculated and analyzed. As the depth of the bulge defect is increased, the magnitude of the signal is increased, too. But the rate of the increment of the signal is less than that of the depth of defect. From the result of this paper, we can obtained the information of the effect of bulge defect on the impedance signal.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.1
• /
• pp.64-69
• /
• 2021

In this paper, a method for improving the defect classification performance in low contrast, ununiformity and featureless steel plate surfaces has been studied based on deep convolution neural network and transfer-learning neural network. The steel plate surface images have low contrast, ununiformity, and featureless, so that the contrast between defect and defect-free regions are not discriminated. These characteristics make it difficult to extract the feature of the surface defect image. A classifier based on a deep convolution neural network is constructed to extract features automatically for effective classification of images with these characteristics. As results of the experiment, AlexNet-based transfer-learning classifier showed excellent classification performance of 99.43% with less than 160 seconds of training time. The proposed classification system showed excellent classification performance for low contrast, ununiformity, and featureless surface images.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.128-135
• /
• 2021

WDM(Wavelength Division Multiplexing) is called a wavelength division multiplexing optical transmission method and is a next-generation optical transmission technology. Case company F has recently developed and sold PLC(Planar Lightwave Circuit), a key element necessary for WDM system production. Although Chinese processing companies are being used as a global outsourcing strategy to increase price competitiveness by lowering manufacturing unit prices, the average defect rate of products manufactured by Chinese processing companies is more than 50%, causing many problems. However, Chinese processing companies are trying to avoid responsibility, saying that the cause of the defect is the defective PLC Wafer provided by Company F. Therefore, in this study, the responsibility of the PLC defect is clearly identified through estimating the defect rate of PLC using the sampling inspection method, and the improvement plan for each cause of the PLC defect for PLC yeild improvement is proposed. The result of this research will greatly contribute to eliminating the controversy over providing the cause of defects between global outsourcing companies and the head office. In addition, it is expected to form a partnership with Company F and a Chinese processing company, which will serve as a cornerstone for successful global outsourcing. In the future, it is necessary to increase the reliability of the PLC yield calculation by extracting more precisely the number of defects.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.2
• /
• pp.135-140
• /
• 2014

Pressure vessels are used in various industrial fields. If a defect occurs on the inner or outer surface of a pressure vessel, it may cause a massive accident. A defect on the outer surface can be detected by visual inspection. However, a defect on the inner surface is generally impossible to detect with visual inspection. Nondestructive testing can be used to detect this type of defect. Laser speckle shearing interferometry is one nondestructive testing method that can optically detect a defect; its advantages include noncontact, full field, and real time inspection. This study evaluated the detectable size for an internal defect of a pressure vessel. The material of the pressure vessel was ASTM A53 Gr.B. The internal defect was detected when the pressure vessel was loaded by internal pressure controlled by a pneumatic system. The internal pressure was controlled from 0.2 MPa to 0.6 MPa in increments of 0.2 MPa. The results confirmed that an internal defect with a 25 % defect depth could be detected even at 0.2 MPa pressure variation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.1
• /
• pp.691-696
• /
• 2015

The interest in software defects is growing. Companies are working on reducing them by various ways with a software development part, customer service part and quality management part. The defect data collected from them will be analyzed according to the condition and purpose to minimize the defect, and it will contribute to improving the quality of products. This study analyzed the software defect progress for companies based on the test maturity model, and set up the defect preventing process. They were applied to the project, and the number of defects decreased from 106 to 16. This study focused on the existing defect, which is a basic requirement for software quality management, and have importance by presenting a way to improve the software product quality with minimum resources.

• 전자공학회논문지 IE
• /
• v.48 no.4
• /
• pp.1-6
• /
• 2011

In this paper we show the LCD simulator for defect inspection using image processing algorithm and neural network. The defect inspection algorithm of the LCD consists of preprocessing, feature extraction and defect classification. Preprocess removes noise from LCD image, using morphology operator and neural network is used for the defect classification. Sample images with scratch, pinhole, and spot from real LCD color filter image are used. From some experiments results, the proposed algorithms show that defect detected and classified in the ratio of 92.3% and 94.5 respectively. Accordingly, in this paper, a possibility of practical implementation of the LCD defect inspection system is finally suggested.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.3
• /
• pp.1-6
• /
• 2020

In this paper, a method for improving the defect classification performance in steel plate surface has been studied, based on DWT(discrete wavelet transform) and SVM(support vector machine). Surface images of the steel plate have low contrast, uneven, and featureless, so that the contrast between defect and defect-free regions is not discriminated. These characteristics make it difficult to extract the feature of the surface defect image. In order to improve the characteristics of these images, a synthetic images based on discrete wavelet transform are modeled. Using the synthetic images, edge-based features are extracted and also geometrical features are computed. SVM was configured in order to classify defect images using extracted features. As results of the experiment, the support vector machine based classifier showed good classification performance of 94.3%. The proposed classifier is expected to contribute to the key element of inspection process in smart factory.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.108-111
• /
• 2022

Applying deep learning to machine vision systems for defect detection of products requires vast amounts of training data about various defect cases. However, since data imbalance occurs according to the type of defect in the actual manufacturing industry, it takes a lot of time to collect product images enough to generalize defect cases. In this paper, we apply a Siamese neural network that can be learned with even a small amount of data to product defect detection, and modify the image pairing method and contrastive loss function by properties the situation of product defect image data. We indirectly evaluated the embedding performance of Siamese neural networks using AUC-ROC, and it showed good performance when the images only paired among same products, not paired among defective products, and learned with exponential contrastive loss.

• Korean Journal of Construction Engineering and Management
• /
• v.2 no.4 s.8
• /
• pp.69-79
• /
• 2001

Characteristics of Contactor's Defect Liability was too many discussed. But it's not clearly defined yet. Because recent Government Construction Projects are very complex and executed through long time, too many conflicts were appeared related to Contactor's Defect Liability. Therefore to analyse and to resolve the conflicts legal aspects of Contactor's Defect Liability stated in Civil Law and Government Contract Act was systematically compared. The result of this research is as follows : (1) Characteristic of Contactor's Defect must be regarded as a breach of Contract and be an incomplete contract implementation. (2) To decide the range of Damage, Characteristic of Defect must be regarded. (3) Contactor's Defect Liability must be effectual from the day of delivery. (4) Retainage must be added to secure the completion during the Contract Period and Defect Repairing Liability must be omitted in the Contract performance Security.