• 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 Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2022

In this paper, we propose a vector-based augmentation technique that can generate data required for crack detection and a ConvNet(Convolutional Neural Network) technique that can learn it. Detecting cracks quickly and accurately is an important technology to prevent building collapse and fall accidents in advance. In order to solve this problem with artificial intelligence, it is essential to obtain a large amount of data, but it is difficult to obtain a large amount of crack data because the situation for obtaining an actual crack image is mostly dangerous. This problem of database construction can be alleviated with elastic distortion, which increases the amount of data by applying deformation to a specific artificial part. In this paper, the improved crack pattern results are modeled using ConvNet. Rather than elastic distortion, our method can obtain results similar to the actual crack pattern. By designing the crack data augmentation based on a vector, rather than the pixel unit used in general data augmentation, excellent results can be obtained in terms of the amount of crack change. As a result, in this paper, even though a small number of crack data were used as input, a crack database can be efficiently constructed by generating various crack directions and patterns.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.5
• /
• pp.493-500
• /
• 2009

An ultrasonic signal processing algorithm was developed for extracting the information of cracks generated around the keyway of a turbine rotor disk. B-scan images were obtained by using keyway specimens and an ultrasonic scan system with x-y position controller. The B-scan images were used as input images for 2-Dimensional signal processing, and the algorithm was constructed with four processing stages of pre-processing, crack candidate region detection, crack region classification and crack information extraction. It is confirmed by experiments that the developed algorithm is effective for the quantitative evaluation of cracks generated around the keyway of turbine rotor disk.

• Journal of the Korean Society of Safety
• /
• v.36 no.1
• /
• pp.18-25
• /
• 2021

In many developed countries, such as South Korea, efficiently maintaining the aging infrastructures is an important issue. Currently, inspectors visually inspect the infrastructure for maintenance needs, but this method is inefficient due to its high costs, long logistic times, and hazards to the inspectors. Thus, in this paper, a novel crack inspection approach for concrete bridges is proposed using integrated image processing techniques. The proposed approach consists of four steps: (1) training a deep learning model to automatically detect cracks on concrete bridges, (2) acquiring in-situ images using a drone, (3) generating orthomosaic images based on 3D modeling, and (4) detecting cracks on the orthmosaic image using the trained deep learning model. Cascade Mask R-CNN, a state-of-the-art instance segmentation deep learning model, was trained with 3235 crack images that included 2415 hard negative images. We selected the Tancheon overpass, located in Seoul, South Korea, as a testbed for the proposed approach, and we captured images of pier 34-37 and slab 34-36 using a commercial drone. Agisoft Metashape was utilized as a 3D model generation program to generate an orthomosaic of the captured images. We applied the proposed approach to four orthomosaic images that displayed the front, back, left, and right sides of pier 37. Using pixel-level precision referencing visual inspection of the captured images, we evaluated the trained Cascade Mask R-CNN's crack detection performance. At the coping of the front side of pier 37, the model obtained its best precision: 94.34%. It achieved an average precision of 72.93% for the orthomosaics of the four sides of the pier. The test results show that this proposed approach for crack detection can be a suitable alternative to the conventional visual inspection method.

• Journal of the Korean Geosynthetics Society
• /
• v.21 no.2
• /
• pp.11-19
• /
• 2022

In this paper, we propose a GoogleNet transfer learning and CNN-LSTM combination method to improve the time-series prediction performance for crack detection using crack data captured inside the sewer pipes. LSTM can solve the long-term dependency problem of CNN, so spatial and temporal characteristics can be considered at the same time. The predictive performance of the proposed method is excellent in all test variables as a result of comparing the RMSE(Root Mean Square Error) for time series sections using the crack data inside the sewer pipe. In addition, as a result of examining the prediction performance at the time of data generation, the proposed method was verified that it is effective in predicting crack detection by comparing with the existing CNN-only model. If the proposed method and experimental results obtained through this study are utilized, it can be applied in various fields such as the environment and humanities where time series data occurs frequently as well as crack data of concrete structures.

• International Journal of Automotive Technology
• /
• v.5 no.4
• /
• pp.303-309
• /
• 2004

In this paper, an interfacial crack length has been detected by using the ultrasonic attenuation coefficient on the adhesively bonded double-cantilever beam (DCB) joints. The correlations between energy release rates which were investigated by experimental measurement, the boundary element method (BEM) and Ripling's equation are compared with each other. The experimental results show that the interfacial crack length for the ultrasonic attenuation coefficient and energy release rate increases proportionally. From the experimental results, we propose a method to detect the interfacial crack length by using the ultrasonic attenuation coefficient and discuss it.

• Proceedings of the KSME Conference
• /
• 2001.06a
• /
• pp.96-101
• /
• 2001

The development of a new experimental method is required to easily observe the growth behavior of fatigue cracks. To satisfy the requirement, an image processing technique was introduced to fatigue testing. The length of surface fatigue crack could be successfully measured by the image processing system. At first, the image data of cracks were stored into the computer while the cyclic loading was interrupted. After testing, crack length was determined using image processing software which was developed by ourselves. Block matching method was applied to the detection of surface fatigue cracks. By comparing the data measured by image processing system with the data measured by manual measurement with a microscope, the effectiveness of the image processing system was established. If the proposed method is used to monitor and observe the crack growth behavior automatically, the time and efforts for fatigue test could be dramatically reduced.

• Journal of Mechanical Science and Technology
• /
• v.14 no.10
• /
• pp.1072-1080
• /
• 2000

Leakage magnetic flux (LMF) is widely used for non-contact detection of cracks. The combination of optics and LMF offers advantages such as real time inspection, elimination of electrical noise, high spatial resolution, etc. This paper describes a new nondestructive evaluation method based on an original magneto-optical inspection system, which uses a magneto-optical sensor, LMF, and an improved magnetization method. The improved magnetization method has the following characteristics: high observation sensitivity, independence of the crack orientation, and precise transcription of the geometry of a complex crack. The use of vertical magnetization enables the visualization of the length and width of a crack. The inspection system provides the images of the crack, and shows a possibility for the computation of its depth.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.22 no.6
• /
• pp.573-577
• /
• 2009

When ultrasound propagates to a crack, transmitted and reflected waves are generated. These waves have useful information for the detection of the crack lying in a structure. In this paper, using finite element analysis, displacements round a inclined crack were obtained for 4 different inclination angles. Fourier transformation is applied to the results to research the frequency characteristics depending on the various locations around the crack. 2-dimensional plane stress model is considered, and finite element software ABAQUS/Explicit is used.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.1
• /
• pp.65-72
• /
• 2024

This paper aims to advance our understanding of extensible beams with multiple cracks by presenting a crack energy and motion equation, and mathematically justifying the energy functions of axial and bending deformations caused by cracks. Utilizing an extended form of Hamilton's principle, we derive a normalized governing equation for the motion of the extensible beam, taking into account crack energy. To achieve a closed-form solution of the beam equation, we employ a simple approach that incorporates the crack's patching condition into the eigenvalue problem associated with the linear part of the governing equation. This methodology not only yields a valuable eigenmode function but also significantly enhances our understanding of the dynamics of cracked extensible beams. Furthermore, we derive a governing equation that is an ordinary differential equation concerning time, based on orthogonal eigenmodes. This research lays the foundation for further studies, including experimental validations, applications, and the study of damage estimation and detection in the presence of cracks.