• Journal of the Korean Society for Nondestructive Testing
• /
• v.32 no.4
• /
• pp.369-375
• /
• 2012

In order to overcome the detection limit by the current nondestructive evaluation technology, a nonlinear resonant ultrasound spectroscopy(NRUS) technique was applied for detection of micro-scale cracks in a material. A down-shift of the resonance frequency and a variation of normalized amplitude of the resonance pattern were suggested as the nonlinear parameter for detection of micro-scale cracks in a materials. A natural-like crack were produced in a standard compact tension(CT) specimen by a low cycle fatigue test and the resonance patterns were acquired in each fatigue step. As the exciting voltage increases, a down-shift of resonance frequency were increases as well as the normalized amplitude decrease. This nonlinear effects were significant and even greater in the cracked specimen, but not observed in a intact specimen.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.15-22
• /
• 2020

In this study, we propose an improvement method that can create U-Net model which detect fine concrete cracks by applying a weighted loss function. Because cracks in concrete are a factor that threatens safety, it is important to periodically check the condition and take prompt initial measures. However, currently, the visual inspection is mainly used in which the inspector directly inspects and evaluates with naked eyes. This has limitations not only in terms of accuracy, but also in terms of cost, time and safety. Accordingly, technologies using deep learning is being researched so that minute cracks generated in concrete structures can be detected quickly and accurately. As a result of attempting crack detection using U-Net in this study, it was confirmed that it could not detect minute cracks. Accordingly, as a result of verifying the performance of the model trained by applying the suggested weighted loss function, a highly reliable value (Accuracy) of 99% or higher and a harmonic average (F1_Score) of 89% to 92% was derived. The performance of the learning improvement plan was verified through the results of accurately and clearly detecting cracks.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.555-567
• /
• 2023

The cracks in the tunnel are currently determined through visual inspections conducted by inspectors based on images acquired using tunnel imaging acquisition systems. This labor-intensive approach, relying on inspectors, has inherent limitations as it is subject to their subjective judgments. Recently research efforts have actively explored the use of deep learning to automatically detect tunnel cracks. However, most studies utilize public datasets or lack sufficient objectivity in the analysis process, making it challenging to apply them effectively in practical operations. In this study, we selected test datasets consisting of images in the same format as those obtained from the actual inspection system to perform an objective evaluation of deep learning models. Additionally, we introduced ensemble techniques to complement the strengths and weaknesses of the deep learning models, thereby improving the accuracy of crack detection. As a result, we achieved high recall rates of 80%, 88%, and 89% for cracks with sizes of 0.2 mm, 0.3 mm, and 0.5 mm, respectively, in the test images. In addition, the crack detection result of deep learning included numerous cracks that the inspector could not find. if cracks are detected with sufficient accuracy in a more objective evaluation by selecting images from other tunnels that were not used in this study, it is judged that deep learning will be able to be introduced to facility safety inspection.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.5
• /
• pp.479-484
• /
• 2009

Nondestructive evaluation(NDE) of ceramic matrix composites is essential for developing reliable ceramics for industrial applications. In the work, C-Scan image analysis has been used to characterize surface crack of SiC ceramics nondestructively. The possibility of detection of surface crack were carried out experimentally by two types of ultrasonic equipment of SDS-win and $\mu$-SDS, and three types of transducer of 25, 50 and 125 MHz. A surface micro-crack of ceramics was not detected by transducer of 25 MHz and 50 MHz. Though the focus method was detected dimly the crack by transducer of 125 MHz, the defocus method could detect the shape of diamond indenter. As a whole, the focus method and the defocus method came to the conclusion that micro crack have a good possibility for detection.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.6
• /
• pp.257-268
• /
• 2006

To determine the faults of ceramic cup it is proposed to use pseudo reverberation time concept estimated by impact test in room. Schroeder curves estimated from impact test for a cup with small crack and without one are utilized to estimate pseudo reverberation time. Pseudo reverberation times are compared and discussed according to a sort of impact hammers and impact points and also boundary conditions. As a result. proposed method is proved to be very useful to detect the existence of faults for candidate cups.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.4
• /
• pp.56-64
• /
• 2021

Leakage due to deterioration and damage is one of the major causes of volume change by freezing and thawing, and it leads micro-cracking and surface scaling in concrete structures. The deterioration of damaged concrete accelerates with the chloride attack. Thus, in the detailed guidelines for facility performance evaluation (2020), the quality of cover concrete and the freeze-thaw (FT) repetition cycle were newly suggested for concrete durability assessment. The quality of cover concrete should be evaluated by the rebound hammer test and the FT repetition cycle should be also considered in the deterioration environmental assessment. This study suggested the application of fast dynamic based nonlinear ultrasound method to monitor initial micro-scale damage under freezing and thawing environment. Concrete specimens were fabricated with different water-cement ratios (40%, 60%) and air contents (1.5% and 3.0%). The compressive strength, rebound number, relative dynamic modulus, and nonlinear ultrasound were measured with different FT cycles. The scanning electron microscopy was also performed to investigate the micro-scale FT damage. As a result, both the rebound number and the relative dynamic modulus had difficulty to detect early damage but the proposed method showed a potential to detect initial micro-scale damage and predict the FT resistance performance of concrete.

• Tunnel and Underground Space
• /
• v.10 no.1
• /
• pp.59-69
• /
• 2000

Acoustic emission is n burst of microseismic waves generated by microscopic failure due to deformation in materials. The study on the detection of initiation and propagation of microcracks from acoustic emission measurement is very important for the evaluation of the stability of underground rock structures by the nondestructive letting method. In this study, acoustic emission was measured under uniaxial stiffness loading test used to obtain the complete stress-strain curves of marble and concrete used as reinforced materials of rock structures. The analysis of acoustic emission parameters and source location were performed to discuss the characteristics of the deformation and failure behavior of rock and concrete. And acoustic emission was measured under cyclic loading test to verify the Kaiser effect associated with the damage of materials, in situ stress of rock, and stress history of concrete structure.

• Geophysics and Geophysical Exploration
• /
• v.4 no.1
• /
• pp.8-18
• /
• 2001

To delineate the inhomogeneities including fractures and to estimate the freshness of rock borehole radar consisting of the reflection and tomography methods, and GPR surveys were conducted at a granite quarry mine. The borehole reflection survey using the direction finding antenna was also conducted to get the spatial orientations of reflectors. 20 MHz was adopted as the central frequency for the borehole radar reflection and tomography surveys and 100 MHz was for GPR. Through the interpretation of borehole reflection data using dipole and direction finding antenna as well as GPR images, which are good agreement with each other, we could determine the orientation of the major fractures in three dimensional way. Parts of travel time curves of tomography data showed the anisotropy, which is uncommon in granite quarry. By comparing the tomography data and TeleViewer images, the anisotropy effect in this area are closely related to fine fissures aligned in the same direction. The area confined by the two fractures, MF2 and MF5, might consist of the most fresh granite in the surveyed area, which was concluded from the borehole radar tomography, and GPR images as well as the distribution of anisotropy.