• Smart Structures and Systems
• /
• v.33 no.6
• /
• pp.449-463
• /
• 2024

Automated crack detection is crucial for structural health monitoring and post-earthquake rapid damage detection. However, realizing high precision automatic crack detection in the absence of corresponding manual labeling presents a formidable challenge. This paper presents a novel crack segmentation transfer learning method and a novel crack segmentation model called Swin-CrackFormer. The proposed method facilitates efficient crack image style transfer through a meticulously designed data preprocessing technique, followed by the utilization of a GAN model for image style transfer. Moreover, the proposed Swin-CrackFormer combines the advantages of Transformer and convolution operations to achieve effective local and global feature extraction. To verify the effectiveness of the proposed method, this study validates the proposed method on three unlabeled crack datasets and evaluates the Swin-CrackFormer model on the METU dataset. Experimental results demonstrate that the crack transfer learning method significantly improves the crack segmentation performance on unlabeled crack datasets. Moreover, the Swin-CrackFormer model achieved the best detection result on the METU dataset, surpassing existing crack segmentation models.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.22 no.9
• /
• pp.786-791
• /
• 2009

Transformer failures are mostly due to partial discharges (PDs) caused by the deteriorated insulation. It is, therefore, important to monitor PD occurrence in insulation system and prevent their deterioration. The presented paper deals with a PD detection method by a capacitive probe, which easily apply to cast - resin dry - type transformers. The PD detection system consists of a capacitive probe and a low noise amplifier having the frequency bandwidth of 500 $Hz{\sim}30$ MHz. In the experimental set-up, sensitivity of the system is 7.16 mV/pC.

• Proceedings of the KIEE Conference
• /
• 1996.11a
• /
• pp.186-189
• /
• 1996

Convential inrush current detection method is used to harmonic restraint method by filtered second frequency component. Nowadays this technique must be modified because harmonics are occurred in steady state of power system. A purpose of this study is to develop of inrush current detection relaying algorithm for power transformer based on flux-current derivative curve method. We used the relaying signals obtained from EMTP simulation.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.166-173
• /
• 2024

This study explores lip-sync detection, focusing on the synchronization between lip movements and voices in videos. Typically, lip-sync detection techniques involve cropping the facial area of a given video, utilizing the lower half of the cropped box as input for the visual encoder to extract visual features. To enhance the emphasis on the articulatory region of lips for more accurate lip-sync detection, we propose utilizing a pre-trained visual attention-based encoder. The Visual Transformer Pooling (VTP) module is employed as the visual encoder, originally designed for the lip-reading task, predicting the script based solely on visual information without audio. Our experimental results demonstrate that, despite having fewer learning parameters, our proposed method outperforms the latest model, VocaList, on the LRS2 dataset, achieving a lip-sync detection accuracy of 94.5% based on five context frames. Moreover, our approach exhibits an approximately 8% superiority over VocaList in lip-sync detection accuracy, even on an untrained dataset, Acappella.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.15-30
• /
• 2023

Recently, various services using artificial intelligence(AI) are emerging in the media field as well However, most of the video editing, which involves finding an editing point and attaching the video, is carried out in a passive manner, requiring a lot of time and human resources. Therefore, this study proposes a methodology that can detect the edit points of video according to whether person in video are spoken by using Video Swin Transformer. First, facial keypoints are detected through face alignment. To this end, the proposed structure first detects facial keypoints through face alignment. Through this process, the temporal and spatial changes of the face are reflected from the input video data. And, through the Video Swin Transformer-based model proposed in this study, the behavior of the person in the video is classified. Specifically, after combining the feature map generated through Video Swin Transformer from video data and the facial keypoints detected through Face Alignment, utterance is classified through convolution layers. In conclusion, the performance of the image editing point detection model using facial keypoints proposed in this paper improved from 87.46% to 89.17% compared to the model without facial keypoints.

• Proceedings of the KIEE Conference
• /
• 1998.07c
• /
• pp.1036-1038
• /
• 1998

The while, PD source detection in the oil TR was the level of the planar source detection. and it is to respected scientific research. The planar source detection technique had limits which have difficulties finding out the point of deterioration generation. In this study, our purpose is a development of PD source detection technique with Three-Dimensional using a principle and a technique of the planar source location.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2000.05a
• /
• pp.50-54
• /
• 2000

Recently, the HFPD measurement testing is widely used in partial discharge measurement of HV machines because HFPD measurement testing receives less influence of external noise and has a merit of good sensitivity. Also HFPD testing is able to offer the judgement standard of degradation level of HV machine and can detect discharge signals in live-line. Therefore it is very useful method compare to previous conventional PD testing method and effective diagnosis method in power transformer that requires live-line diagnosis. But partial discharges have very complex characteristics of discharge pattern so it is required continuous research to development of precise analysis method. In recent, the study of partial discharge is carrying out discover of initial defect of power equipment through condition diagnosis and system development of degradation diagnosis using HFPD(High Frequency Partial Discharge) detection. In this study, simulated transformer is manufactured and HFPD occurred from transformer is measured with broad band antenna in real time, the degradation grade of transformer is analyzed through produced patterns in simulated transformer according to applied voltages.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.66-76
• /
• 1995

In this research, a mesh connected VLSI structure is proposed for the real time computation of the generalized Hough transform(GHT). The purpose of the research is to design a generalized Hough transformer that can be realized as a single chip processor. The GHT has been modified to yield a highly parallel structure consisting of simple processing elements(PEs) and communication networks. In the proposed structure, the GHT can be computed by first assigning an image pixel to a PE and performing shift and add operations. The result of the CAD circuit simulation shows that it can be computed in the time proportional to the number of pixels in the pattern. In addition to the Hough transformer, the peak detector has been designed to reduce 1)the number of the I/O operations between the transformer and the host computer and 2) the host computer's burden for peak detection by transmitting only the local peaks detected from the transformed accumulator. It is expected that the proposed single chip Hough transformer with peak detector makes a fast and inexpensive edge based object recognition systems possible for many industrial and military applications.

• KIEE International Transactions on Power Engineering
• /
• v.4A no.3
• /
• pp.146-151
• /
• 2004

The most widely used primary protection for the internal fault detection of the power transformer is current ratio differential relaying (CRDR) with harmonic restraint. However, the second harmonic component could be decreased by magnetizing inrush when there have been changes to the material of the iron core or its design methodology. The higher the capacitance of the high voltage status and underground distribution, the more the differential current includes the second harmonic during the occurrence of an internal fault. Therefore, the conventional second harmonic restraint CRDR must be modified. This paper proposes a numerical algorithm for enhanced power transformer protection. This algorithm enables a clear distinction regarding internal faults as well as magnetizing inrush and steady state. It does this by analyzing the RMS fluctuation of terminal voltage, instantaneous value of the differential current, RMS changes, harmonic component analysis of differential current, and analysis of flux-differential slope characteristics. Based on the results of testing with WatATP99 simulation data, the proposed algorithm demonstrated more rapid and reliable performance.

• Proceedings of the KIEE Conference
• /
• 2005.07e
• /
• pp.73-75
• /
• 2005

In present measurement of moisture contents is used as one of method for estimating degradation of transformer. Most of people use Karl-Fischer titration method for detection moisture contents but this measurement is inconvenient method because we must analyze transformer oil-paper after dismounting transformer and sampling in field. Therefore we don't directly investigate them in field. In this paper we will introduce Recovery Voltage Method(RVM) that is new method for estimating measurement in field though dismounting facility. For measure of moisture contents using RVM in accordance with accelerated thermal aging we have made experimental test cell and aged at a temperature up to 140$^{\circ}C$ for 300 hours. And we have been measured at intervals of 100 hours using RVM 5462 made in fetter company.