• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.9-16
• /
• 2004

• Journal of Navigation and Port Research
• /
• v.28 no.1
• /
• pp.43-49
• /
• 2004

Defects inspection of commodities are very important with those design and manufacturing process and essential to strengthen the competitiveness of those. If on-line automatic defects detection is performed without damaging to products, the production cost shall be curtailed through the reducing man-power, economical management of Q.C(Quality Control). In this paper, it is suggested three spatial filtering methods which can extract the necessary information in case of defects being on the surface of object like iron plate. In addition, the dependence of filtering characteristics on parameters such as the pitch and width of slits is analyzed and the surface defect detection system is constructed. Several experiments were carried out for determining the adequate spatial filtering method through comparing and analyzing effects of parameters like defect's size and shape, intensity of light, noise of coherent source and slit number.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.6
• /
• pp.1092-1098
• /
• 2007

Since one decade, the detection of HFPD (High frequency Partial Discharge) has been proposed as one of the effective method for the diagnosis of the power component under service in power grids. As a tool for HFPD detection, Metal Foil sensor based on the embedded technology has been commercialized for mainly power cable due to its advantages. Recently, for the on-site noise discrimination, several PA (Pulse analysis) methods have been reported and the related software, such as Neural Network and Fuzzy, have been proposed to separate the PD (Partial Discharge) signals from the noises since their wave shapes are completely different from each other. On the other hand, the relevant fundamental investigation has not yet clearly made while it is reported that the effectiveness of the current methods based on PA is dependant on the types of sensors. Moreover, regarding the identification of the vital defects introducible into the Power Cable, the direct identification of the nature of defects from the PD signals through Metal Foil coupler has not yet been realized. As a trial for solving above shortcomings, different types of software have been proposed and employed without any convincing probability of identification. In this regards, our novel algorithm 'PA Map' based on the pulse analysis is suggested to identify directly the defects inside the power cable from the HFPD signals which is output of the HFCT and metal foil sensors. This method enables to discriminate the noise and then to make the data analysis related to the PD signals. For the purpose, the HFPD detection and PA (Pulse Analysis) system have been developed and then the effect of noise discrimination has been investigated by use of the artificial defects using real scale mockup. Throughout these works, our system is proved to be capable of separating the small void discharges among the very large noises such as big air corona and ground floating discharges at the on-site as well as of identifying the concerned defects.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.31-41
• /
• 2022

Steel is one of the most fundamental components to mechanical industry. However, the quality of products are greatly impacted by the surface defects in the steel. Thus, researchers pay attention to the need for surface defects detector and the deep learning methods are the current trend of object detector. There are still limitations and rooms for improvements, for example, related works focus on developing the models but don't take into account real-time application with practical implication on industrial settings. In this paper, a real-time application of steel surface defects detection based on YOLOv4 is proposed. Firstly, as the aim of this work to deploying model on real-time application, we studied related works on this field, particularly focusing on one-stage detector and YOLO algorithm, which is one of the most famous algorithm for real-time object detectors. Secondly, using pre-trained Yolov4-Darknet platform models and transfer learning, we trained and test on the hot rolled steel defects open-source dataset NEU-DET. In our study, we applied our application with 4 types of typical defects of a steel surface, namely patches, pitted surface, inclusion and scratches. Thirdly, we evaluated YOLOv4 trained model real-time performance to deploying our system with accuracy of 87.1 % mAP@0.5 and over 60 fps with GPU processing.

• Journal of Advanced Navigation Technology
• /
• v.18 no.4
• /
• pp.304-311
• /
• 2014

In this paper, we propose a ultra sound inspection technique for automatic defect detection and classification in aircraft composite materials. Using local maximum values of ultra sound wave, we choose peak values for defect detection. Distance data among peak values are used to construct histogram and to determine surface and back-wall echo from the floor of composite materials. C-scan image is then composed through this method. A threshold value is determined by average and variance of the peak values, and defects are detected by the values. PCA(principal component analysis) and QDA(quadratic discriminant analysis) are carried out to classify the types of defects. In PCA, 512 dimensional data are converted into 30 PCs(Principal Components), which is 99% of total variances. Computational cost and misclassification rate are reduced by limiting the number of PCs. A decision boundary equation is obtained by QDA, and defects are classified by the equation. Experimental result shows that our proposed method is able to detect and classify the defects automatically.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.316-319
• /
• 2014

People's interests in coffee are increasing with the expansion of coffee market. In this trend, people's taste becomes more luxurious and coffee bean's quality is considered to be very important. Currently, bean defects are mainly detected by experienced specialists. In this paper, a detection system of bean defects using machine learning is presented. This system concentrates on detecting two main defect types : bean's shape and insect damage. Convolutional Neural Networks are used for machine learning. The neural networks are comprised of two neural networks. The first neural network detects defects in the bean's shape, and the second one detects the bean's insect damage. The development of this system could be a starting point for automated coffee bean defects detection. Later, further research is needed to detect other bean defect types.

• Journal of the Korean Society for Railway
• /
• v.18 no.5
• /
• pp.401-409
• /
• 2015

Defects generated in a railroad track that guides the railroad vehicle have the characteristic of growing fast; as such, the detection technology for railroad track defects is very important because defects can eventually cause mass disasters like derailments. In this study, a speed-up test facility was fabricated to investigate the feasibility of using magnetic flux leakage (MFL) technology for defect detection in a railroad track under speed-up condition; a test was conducted using a railroad track specimen with defects. For this purpose, an MFL sensor head dedicated to the configuration of the railroad was designed and test specimens with artificial defects on their surfaces were manufactured. Using the test facility, a speed-up test ranging from 4km/h to 12km/h was performed and defects including locations were successfully detected from MFL signals induced by defects with enhanced visibility by differentiating raw MFL signals. In the future, it should be possible to apply this system to a high-speed railroad inspection car by improving the lift-off stability that is necessary for speed-up of the developed MFL sensor system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.107-116
• /
• 2024

Copper Filter Dryer (CFD) are responsible for removing impurities from the circulation of refrigerant in refrigeration and cooling systems to maintain clean refrigerant, and defects in CFD can lead to product defects such as leakage and reduced lifespan in refrigeration and cooling systems, making quality assurance essential. In the quality inspection stage, human inspection and defect judgment methods are traditionally used, but these methods are subjective and inaccurate. In this paper, YOLOv7 object detection algorithm was used to detect defects occurring during the CFD Shaft pipe and welding process to replace the existing quality inspection, and the detection performance of F1-Score 0.954 and 0.895 was confirmed. In addition, the cause of defects occurring during the welding process was analyzed by analyzing the sensor data corresponding to the Timestamp of the defect image. This paper proposes a method for manufacturing quality assurance and improvement by detecting defects that occur during CFD process and analyzing their causes.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.4_2
• /
• pp.687-697
• /
• 2022

An automated system is needed for the effectiveness of non-destructive testing. In order to utilize the radiographic testing data accumulated in the film, the types of welding defects were classified into 9 and the shape of defects were analyzed. Data was preprocessed to use deep learning with high performance in image classification, and a combination of one-stage/two-stage method and convolutional neural networks/Transformer backbone was compared to confirm a model suitable for welding defect detection. The combination of two-stage, which can learn step-by-step, and deep-layered CNN backbone, showed the best performance with mean average precision 0.868.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.135-142
• /
• 2024

Cu-Cu bonding, one of the key technologies in advanced packaging, enhances semiconductor chip performance, miniaturization, and energy efficiency by facilitating rapid data transfer and low power consumption. However, the quality of the interface bonding can significantly impact overall bond quality, necessitating strategies to quickly detect and classify in-process defects. This study presents a methodology for detecting defects in wafer junction areas from Scanning Acoustic Microscopy images using a ResNet-50 based deep learning model. Additionally, the use of the defect map is proposed to rapidly inspect and categorize defects occurring during the Cu-Cu bonding process, thereby improving yield and productivity in semiconductor manufacturing.