• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.5
• /
• pp.356-361
• /
• 2014

The eddy current testing performance directly affects the results of a steam generator tube integrity assessment because the integrity assessment of defected tubes is conducted based on eddy current testing results. This means that it may not be possible to accurately discriminate between adjacent flaws. This paper presents an investigation on the resolution of rotating pancake coils with multiple cracks and the effects on the structural integrity assessment of steam generator tubes.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.1
• /
• pp.22-28
• /
• 2010

To detect the damage in composite structure, nondestructive evaluation techniques are widely used. Tapping test is perhaps the most common technique used for the detection of damage in composite laminates. The method is accomplished by tapping the inspection area with light hammer-like device. The tapping test has the ability that indicates damages in a structure due to a localized change of stiffness. The change in vibration signature may be detected by measurement of the dynamic contact force during impact. In this study, it has been shown that the characteristics of impact force histories from a structure during tapping are changed by the presence of damage such as surface crack and delamination. And impact response analysis has been performed on composite rotor blade with crack to investigate the effect of damage.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.17-24
• /
• 2020

This study examined the spectral information and reflectance of cracks of an embankment with drone-based hyperspectral imagery for crack detection. A Nano-Hyperspec mounted on a drone was used as a sensor, and hyperspectral videos of different intensities of illumination of the cracks on the embankment located in the downstream of Andong-Dam were obtained. An analysis of the data value of the illumination and peak data-value, the coefficients of determination were calculated to be 0.9864 of the uncracked areas and 0.9851 of the cracked area. The reflectance of each area showed a similar value and pattern, regardless of the intensity of illumination. This result may have occurred because the reference values of the white reference as the calculation criteria of reflectance varied according to the intensity of illumination. The reflectance at the cracked area was 5.65% lower in visible light and 4.58% lower in near-infrared light than that at the uncracked area. The detection of cracks may offer more precise results in further studies when the gimbal direction and camera angles of the drone are calibrated. Because hyperspectral imagery enables the detection of crack depths and types of clay minerals, which are difficult to identify in general RGB imagery, it can serve as a preemptive measure for evaluating the embankment stability.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.13-14
• /
• 2023

집중 안전 점검의 대상인 노후 건축물에서 균열은 건물의 안전도를 점검할 수 있는 지표이다. 안전 점검에 드론을 활용하면서 고해상도의 드론 기반 균열 이미지 수집이 가능해졌고, 육안이 아닌 AI기반으로 균열을 탐지, 구획화할 수 있다. 본 연구에서는 주변 사물과 배경에 구애받지 않고 안전 점검이 가능한 구획화 알고리즘을 제안한다. METU와 POC데이터셋을 가공하여 데이터셋을 구축하고, 이를 바탕으로 ResNet50을 통해 균열과 유사한 배경을 분류하였으며, 균열 구획화 모델을 선정하여 DesneNet201-UNet++으로 mIoU 82.27%를 달성하였다. 본 연구는 노후 건축물 안전 점검에 필요한 균열 폭 추정에 도움이 될 것으로 기대된다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.515-528
• /
• 2020

Underground concrete structures are usually designed to be used for decades, but in recent years, many of them are nearing their original life expectancy. As a result, it is necessary to promptly inspect and repair the structure, since it can cause lost of fundamental functions and bring unexpected problems. Therefore, personnel-based inspections and repairs have been underway for maintenance of underground structures, but nowadays, objective inspection technologies have been actively developed through the fusion of deep learning and image process. In particular, various researches have been conducted on developing a concrete crack detection algorithm based on supervised learning. Most of these studies requires a large amount of image data, especially, label images. In order to secure those images, it takes a lot of time and labor in reality. To resolve this problem, we introduce a method to increase the accuracy of crack area detection, improved by 0.25% on average by applying adversarial learning in this paper. The adversarial learning consists of a segmentation neural network and a discriminator neural network, and it is an algorithm that improves recognition performance by generating a virtual label image in a competitive structure. In this study, an efficient deep neural network learning method was proposed using this method, and it is expected to be used for accurate crack detection in the future.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.4
• /
• pp.299-304
• /
• 2007

There are to be some cracks on the material degradation part or the stress concentration parts of the main members, which carry on over-loads, of structures. Because these cracks can be used to evaluate the structural health status, it is important to monitor the crack growth for maintaining the structural safety. In this study, the fiber Bragg grating sensor with a drop ball was developed as a sensor for crack growth detection of an existing crack. The crack growth detection sensor was constructed with three parts: a probe part, a wavelength controling light source and receiver part, and an impact part. The probe part was just formed with a fiber Bragg grating optical fiber The wavelength controling light source part was composed of a current supplying circuit, a DFB laser diode, and a TEC controling circuit for wavelength control. Also, the impact part was just implemented by dropping a steel ball. The performance of this sensor was confirmed by the experiments of the crack detection with an aluminum plate having one existing crack. According to these experiments, the difference of the sensor signal outputs was correlated with the crack length. So, it was confirmed that this sensor could be applied to monitor the crack growth.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.5
• /
• pp.611-617
• /
• 2018

The application of health monitoring, including a fault detection technique, is needed to secure the structural safety of large structures. A 2-step crack identification method for detecting the crack location and size of the beam structure is presented. First, a crack occurrence region was estimated using the modified Laplacian operator for the strain mode shape obtained from the distributed local strain data. The crack location and size were then identified based on the natural frequencies obtained from the acceleration data and the neural network technique for the pre-estimated crack occurrence region. The natural frequencies of a cracked beam were calculated based on an equivalent bending stiffness induced by the energy method, and used to generate the training patterns of the neural network. An experimental study was carried out on an aluminum cantilever beam to verify the present method for crack identification. Cracks were produced on the beam, and free vibration tests were performed. A crack occurrence region was estimated using the modified Laplacian operator for the strain mode shape, and the crack location and size were assessed using the natural frequencies and neural network technique. The identified crack occurrence region agrees well with the exact one, and the accuracy of the estimation results for the crack location and size could be enhanced considerably for 3 damage cases. The presented method could be applied effectively to the structural health monitoring of large structures.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.45-48
• /
• 2022

건축물 안전 점검은 대부분 전문가의 현장 방문을 통한 육안검사다. 그중 균열 검사는 건물 위험도를 나타내는 중요한 지표로써 발생 위치, 진행성, 크기를 조사하는데, 최근 균열 조사 방식에 대해 객관성과 체계성을 보완할 딥러닝 개발이 활발하다. 그러나 균열 이미지는 외부 현장에 모양, 규모도 많은 종류라 도메인이 다양해야 하는데 대부분 제한된 환경과 실제적인 균열 검사와는 무관한 데이터로 구성되어 실효적이지 않다. 본 연구에서는 균열 조사에 적합하고 Wild 환경에 적용 가능한 POC 데이터셋을 소개한다. 기존 균열 공인 데이터셋 4종의 특징과 한계점을 분석을 토대로 고해상도 이미지로써 균열의 세부 특징을 담았고 균열 유사 환경과 조건들을 추가 촬영해 균열 검출에 강인하게 학습되도록 지향하였다. 정제 및 라벨링 작업을 거친 POC 데이터 셋은 균열 검출모델인 YOLO-v5으로 성능을 실험하였고, mAP(mean Average Precision) 75.5%로 높은 검출률을 보였다. POC 데이터셋으로 더욱 도메인에 적응적(Domain-adapted)인 인공지능 모델을 개발하여 건물, 댐, 교량 등 각종 대형 건축물에 대한 안전하고 효과적인 안전 관리 도구로써 활용할 것을 기대한다.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.24 no.2
• /
• pp.136-141
• /
• 2004

A torsional guided wave mode was applied to detect a crack in a pipe. An array of electromagnetic acoustic transduce. (EMAT that can generate and receive torsional guided ultrasound with the frequency of 200kHz was designed and fabricated for testing a pipe of 2.5 inch diameter Artificial notches with various depths were fabricated in a bent feeder pipe mock-up and the detectability was examined from the distance of 2m of the specimen. The axial notches with the depth of 5% of wall thickness were successfully detected by a torsional mode (T(0,1)) generated by the EMAT However, it was found that the depth of defects was not related to the signal amplitude.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.377-380
• /
• 2023

본 논문에서는 합성곱 신경망(Convolutional Neural Networks, CNN)과 탄성왜곡(Elastic Distortion) 기법을 통한 데이터 증강 기법을 활용하여 학습 데이터를 구축하는 프레임워크를 제안한다. 실제 균열 이미지는 정형화된 형태가 없고 복잡한 패턴을 지니고 있어 구하기 어려울 뿐만 아니라, 데이터를 확보할 때 위험한 상황에 노출될 우려가 있다. 이러한 데이터베이스 구축 문제점을 본 논문에서 제안하는 데이터 증강 기법을 통해 비용적, 시간적 측면에서 효율적으로 해결한다. 세부적으로는 DeepCrack의 데이터를 10배 이상 증가하여 실제 균열의 특징을 반영한 메타 데이터를 생성하여 U-net을 학습하였다. 성능을 검증하기 위해 균열 탐지 연구를 진행한 결과, IoU 정확도가 향상되었음을 확인하였다. 데이터를 증강하지 않았을 경우 잘못 예측(FP)된 경우의 비율이 약 25%였으나, 데이터 증강을 통해 3%까지 감소하였음을 확인하였다.