• 도시과학
• /
• 제11권2호
• /
• pp.1-8
• /
• 2022

This study proposed how to identify window defects by using photos uploaded by occupants during the pre-handover inspection of mulch-family housing. A total of 1168 door images were acquired to generate training data and validation data. Subsequently, through the proposed algorithms, every pixel in images labeled a door was binarized using the OTSU threshold, and then dark pixels were identified as defects. Experimental results demonstrated that our computer vision-based defects identification method detects the door with a recall of 57.9%, and door defects with 63.6%. Although it is still a challenge to automatically identify building defects because of the distortion and brightness of photos, this study has the potential to support better defects management. Ultimately, the improved pre-handover inspection may lead to increased customer satisfaction.

• 정보처리학회논문지B
• /
• 제13B권4호
• /
• pp.377-382
• /
• 2006

본 논문에서는 자동결함검출 방법으로 도광판의 다양한 패턴에 나타나는 돌출, 함몰, 점 등과 같은 작은 결함들을 검출하기 위해 모폴로지의 닫힘, 열림 방법을 이용하는 템플레이트 검사 방법을 사용하였고, 얼룩, 스크래치와 같은 큰 결함을 검출하기 위해 영상에서 격자와 같은 일정한 블록을 형성하여 각 블록을 비교하여 결함을 찾는 블록매칭 방법을 사용하였다. 또한 일정한 패턴이 없는 도광판의 결함에 대해 결함을 검출할 수 있는 개선된 오쯔 방법을 이용하였다. 이 알고리즘을 적용한 결과 결함 검출에 좋은 성능이 있음을 보여준다. 제안된 알고리즘은 자체 개발한 장비에서 실제 도광판의 영상을 얻어 테스트 하였다.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제17권3호
• /
• pp.224-235
• /
• 2017

Purpose: Reliability is the most important factor to detect defects as wind turbines are deployed in large blades. The methods of detecting defects are various, such as non-destructive inspection and thermal imaging inspection. We propose the phased array ultrasonic testing method of non-destructive testing. Methods: We propose the active pressure mechanism for wind power blade. The phase array ultrasonic inspection method is used for fault detection inner blade surface. Controlled pressure of mechanism with respect to z-axis is important for guarantee the result of phase array ultrasonic inspection. The model based control and proposed mechanism are utilized for overall system stability and effectiveness of system. Result: The result of proposed pressure mechanism B is more stable than A. Convergence speed is also faster than A. Conclusion: We confirmed the performance of the proposed constant pressure mechanism through experiments. Non-destructive testing was applied to the specimen to confirm the reliability of detecting defects.

• Corrosion Science and Technology
• /
• 제17권6호
• /
• pp.292-300
• /
• 2018

The modeling of 3D finite elements based on CAD data has been used to detect sites of corrosion defects in buried pipes. The results generated sophisticated profiles of electrolytic potential and vectors of current distributions on the earth surface. To identify the location of defects in buried pipes, the current distribution on the earth surface was projected to a plane of incidence that was identical to the pipe locations. The locations of minimum electrolytic potential value were found. The results show adequate match between the locations of real and expected defects based on modeling. In addition, the defect size can be calculated by integrating the current density curve. The results show that the defect sizes were $0.74m^2$ and $0.69m^2$, respectively. This technology may represent a breakthrough in the detection of indirect damage in various cases involving multiple defects in size and shape, complex/cross pipe systems, multiple anodes and stray current.

• 한국컴퓨터정보학회논문지
• /
• 제25권3호
• /
• pp.19-26
• /
• 2020

일반적으로 품질 관리는 많은 제조 공정, 특히 주조 또는 용접과 관련된 공정의 기본 구성 요소가 된다. 그러나 사람이 일일이 수동으로 품질 관리 절차를 하는 것은 종종 시간이 걸리고 오류가 발생하기 쉽다. 최근 고품질 제품에 대한 요구를 만족시키기 위해 지능형 육안 검사 시스템의 사용이 생산 라인에서 필수적이 되고 있다. 본 논문에서는 이를 위해 딥 러닝 기반의 ShuffleDefectNet 결함 감지 시스템을 제안하고자 한다. 제안된 결함 검출 시스템은 NEU 데이터 세트의 결함 검출에 대한 여러 최신 성능들보다 높은 평균 정확도 99.75% 정도를 얻는다. 이 논문에서 여러 다른 트레이닝 데이터로부터 최상의 성능을 탐지하고 탐지 성능을 관찰하였다. 그 결과 ShuffleDefectNet의 전체 아키텍처를 사용할 때 정확성과 속도가 크게 향상됨을 알 수 있었다.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2005년도 춘계학술발표대회 개요집
• /
• pp.194-196
• /
• 2005

Ultrasonic guided waves are gaining increasing attention for the inspection of platelike and rodlike structures. At the same time, inspection methods that do not require contact with the test piece are being developed for advanced applications. This paper capitalizes on recent advances in the areas of guided wave ultrasonics and noncontact ultrasonics to demonstrate a superior method for the nondestructive detection of thinning defects simulating hidden corrosion in thin aluminum plates. The proposed approach uses EMAT(electro-magnetic acoustic transducer) for the noncontact generation and detection of guided plate waves. Interesting features in the dispersive behavior of selected guided modes are used for the detection of plate thinning. It is shown that mode cutoff measurements provide a qualitative detection of thinning defects. Measurement of the mode group velocity can be also used to quantify of thinning depth.

• 한국안전학회지
• /
• 제11권4호
• /
• pp.29-33
• /
• 1996

In this study, specimens were prepared which have some defects on the buttweld joint of mild steel. In order to detect the defects of specimens, the following tests were put to : AUT and RT. When the results of the three tests were compared, the conclusion could be brought to as follows. 1) AUT outstrips RT in the abillity to detect plane defects like slags or cracks, but RT excels AUT in the ability to detect spheroidal defects like blowholes. 2) RT detects neither taper cracks nor very closed cracks, whereas AUT detects both of them. 3) AUT can detect at once plane defects like cracks and spheroidal defects like blowholes.

• 반도체디스플레이기술학회지
• /
• 제9권3호
• /
• pp.59-63
• /
• 2010

This paper proposes computer visual inspection algorithms for various LCD defects which are found in a manufacturing process. Modular vision processing steps are required in order to detect different types of LCD defects. Those key modules include RGB filtering for pixel defects, gray-scale morphological processing and Hough transform for line defects, and adaptive threshold for spot defects. The proposed algorithms can give users detailed information on the type of defects in the LCD panel, the size of defect, and its location. The machine vision inspection system is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithms are quite successful.

• 대한전자공학회논문지SP
• /
• 제41권3호
• /
• pp.9-16
• /
• 2004

• 한국철도학회논문집
• /
• 제18권5호
• /
• pp.401-409
• /
• 2015

철도에서 차량의 가이드 역할을 하는 레일에 결함이 발생할 경우 빠르게 진전하는 특성이 있으며 차량의 탈선과 같은 대형사고로 이어질 수 있어 레일 결함 탐상 기술은 매우 중요하다. 본 연구에서는 증속에 따른 누설자속기반 철도레일 결함탐상 기술의 적용성 검토를 위해 증속이 가능한 레일 탐상 시험 장치 제작 및 결함 레일 시편에 대한 탐상 시험을 수행하였다. 이를 위해, 철도레일 형상에 맞는 센서부 및 자화부를 설계하였고 인공결함을 갖는 결함 레일 시편을 제작하였다. 제작된 시험 장치를 이용해 4km/h에서 12km/h까지 속도를 증가시키며 결함에 의해 생성되는 누설자속을 측정하였고 원 신호의 미분을 통한 가시성 향상으로 결함 판별 및 결함 위치를 성공적으로 확인하였다. 향후 리프트 오프 유지 등 고속화에 필요한 점을 보완할 경우 고속 검측차에도 적용가능 할 것으로 생각된다.