• Journal of the Korean Geotechnical Society
• /
• v.34 no.12
• /
• pp.145-154
• /
• 2018

The damage investigation and inspection methods performed in concrete facilities such as bridges, tunnels, retaining walls and so on, are usually visually examined by the inspector using the surveying tool in the field. These methods highly depend on the subjectivity of the inspector, which may reduce the objectivity and reliability of the record. Therefore, the new image processing techniques are necessary in order to automatically detect the cracks and objectively analyze the characteristics of cracks. In this study, deep learning and image processing technique were developed to detect cracks and analyze characteristics in images for concrete facilities. Two-stage image processing pipeline was proposed to obtain crack segmentation and its characteristics. The performance of the method was tested using various crack images with a label and the results showed over 90% of accuracy on crack classification and segmentation. Finally, the crack characteristics (length and thickness) of the crack image pictured from the field were analyzed, and the performance of the developed technique was verified by comparing the actual measured values and errors.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.65-73
• /
• 2023

In this paper, we propose a data augmentation method based on CNN(Convolutional Neural Network) learning for efficiently obtaining concrete crack image datasets. Real concrete crack images are not only difficult to obtain due to their unstructured shape and complex patterns, but also may be exposed to dangerous situations when acquiring data. In this paper, we solve the problem of collecting datasets exposed to such situations efficiently in terms of cost and time by using vector and thickness-based data augmentation techniques. To demonstrate the effectiveness of the proposed method, experiments were conducted in various scenes using U-Net-based crack detection, and the performance was improved in all scenes when measured by IoU accuracy. When the concrete crack data was not augmented, the percentage of incorrect predictions was about 25%, but when the data was augmented by our method, the percentage of incorrect predictions was reduced to 3%.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.1547-1548
• /
• 2011

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2001.05a
• /
• pp.250-253
• /
• 2001

Recently, based on the smart structure concept, optical fiber sensors have been increasingly applied to monitor the various engineering and civil structural components. Repairs based on adhesively bonded fiber reinforce composite patches are more structurally efficient and much less damaging to the parent structure than standard repairs based on mechanically fastened metallic patches. As a result of the high reinforcing efficiency of bonded patches fatigue cracks can be successfully repaired. However, when such repairs are applied to primary structures, it is needed to demonstrate that its loss can be immediately detected. This approach is based on the "smart patch" concept in which the patch system monitors its own health. The objective of this study is to evaluate the potentiality of application of transmission-type extrinsic Fabry-Perot optical fiber sensor (TEFPI) to the monitoring of crack growth behavior of composite patch repaired structures. The sensing system of TEFPI and the data reduction principle for the detection of crack detection are presented. Finally, experimental results from the tests of center-cracked-tension aluminum specimens repaired with bonded composite patch is presented and discussed.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.11
• /
• pp.30-36
• /
• 2010

Previous researches show that linearly integrated Hall sensor arrays (LIHaS) can detect cracks in the steel structure fast and effectively This paper proposes an algorithm that estimates the size and shape of cracks for the developed LIHaS. In most nondestructive testing (NDT), just crack existence and location are obtained by processing 1-dimensional data from the sensor that scans the object with relative speed in single direction. The proposed method is composed with two steps. The first step is constructing 2-dimensionally mapped data space by combining the converted position data from the time-based scan data with the position information of sensor arrays those are placed in the vertical direction to the scan direction. The second step is applying designed Laplacian filter and smoothing filter to estimate the size and shape of cracks. The experimental results of express train wheels show that the proposed algorithm is not only more reliable and accurate to detecting cracks but also effective to estimate the size and shape of cracks.

• Smart Structures and Systems
• /
• v.8 no.1
• /
• pp.93-105
• /
• 2011

This paper presents a flexible low-profile antenna sensor for fatigue crack detection and monitoring. The sensor was inspired by the sense of pain in bio-systems as a protection mechanism. Because the antenna sensor does not need wiring for power supply or data transmission, it is an ideal candidate as sensing elements for the implementation of engineering sensor skins with a dense sensor distribution. Based on the principle of microstrip patch antenna, the antenna sensor is essentially an electromagnetic cavity that radiates at certain resonant frequencies. By implementing a metallic structure as the ground plane of the antenna sensor, crack development in the metallic structure due to fatigue loading can be detected from the resonant frequency shift of the antenna sensor. A monostatic microwave radar system was developed to interrogate the antenna sensor remotely. Fabrication and characterization of the antenna sensor for crack monitoring as well as the implementation of the remote interrogation system are presented.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.4 no.3
• /
• pp.185-195
• /
• 2000

Detection of cracks in concrete beams using optical fiber sensors is useful for monitoring of concrete structures. In this study, optical time domain reflectometry (OTDR) is used to detect cracks. Resolution of OTDR is the main contributor to detect cracks in concrete structures. The OTDR used in this study can detect cracks with high precision of 0.5 m. Two mortar beams, reinforced with a 19 mm diameter steel bar, are made with the dimensions of 140 mm (width) ${\times}$ 200 mm (depth) ${\times}$ 2.000 mm (length). Two fibers are embedded inside each beam and two fibers are attached under the beams. The application of measurement system which consists of fiber and FC/PC connecter is studied. For this, theory of optics, resolution, crack moment, and size of specimens are investigated. From the measured data, it is verified that fibers which are attached under the beam can detect the crack in beams effectively. However, fibers embedded inside the beam are unable to detect cracks in beams using the OTDR in this study.

• Corrosion Science and Technology
• /
• v.16 no.4
• /
• pp.194-200
• /
• 2017

Stress-corrosion cracking (SCC) of alloy 600 and alloy 800 in 0.5 mol/L thiosulfate solution during constant strain was investigated using electrochemical noise (EN) combined with 3-D microscope techniques. The in-situ morphology observation and EN results indicate that the SCC process could be divided into three stages: (1) passive film stabilization and growth, (2) crack initiation, (3) and crack growth. Power Spectral Density (PSD) and the probability distribution obtained from EN were used as the "fingerprint" to distinguish the different processes. During passive film stabilization and growth, the current noise signals resembled "white noise": when the crack initiated, many transient peaks could be seen in the current noise and the wavelet energy at low frequency as well as the noise resistance decreased. After crack propagation, the noise amplitudes increased, particularly the white noises at low and high frequencies ($W_L$ and $W_H$) in the PSDs. Finally, the detection of metal structure corrosion in a simulated sea splash zone and pipeline corrosion in the atmosphere are established.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.1E
• /
• pp.44-53
• /
• 1998

Bolt degradation has become a major issue in the nuclear industry since the 1980's due to failure during operation. If small cracks in stud bolt are not detected early enough, they grow rapidly and cause catastrophic disasters. Their detection, despite its importance, is known to be a very difficult problem due to the complicated structures of the stud bolts. This paper presents a method of detecting and sizing a small crack in the root between two adjacent crests in threads. The key idea is from the fact that the Rayleigh wave propagates slowly along a crack from the tip to the opening and is reflected from the opening mouth. When there exists a crack, a small delayed pulse due to the Rayleigh wave is detected between large regularly spaced pulses from the thread. The delay time is the same as the propagation delay time of the slow Rayleigh wave and is proportional to the size of the crack. To efficiently detect the slow Rayleigh wave, three methods based on digital signal processing are proposed : modified wave shaping, dynamic predictive deconvolution, and dynamic predictive deconvolution combined with wave shaping.

• Computers and Concrete
• /
• v.32 no.5
• /
• pp.475-486
• /
• 2023

Nondestructive evaluation (NDE) is an important task of civil engineering structure monitoring and inspection, but minor damage such as small cracks in local structure is difficult to observe. If cracks continued expansion may cause partial or even overall damage to the structure. Therefore, monitoring and detecting the structure in the early stage of crack propagation is important. The crack detection technology based on machine vision has been widely studied, but there are still some problems such as bad recognition effect for small cracks. In this paper, we proposed a deep learning method based on sweep signals to evaluate concrete surface crack with a width less than 1 mm. Two convolutional neural networks (CNNs) are used to analyze the one-dimensional (1D) frequency sweep signal and the two-dimensional (2D) time-frequency image, respectively, and the probability value of average damage (ADPV) is proposed to evaluate the minor damage of structural. Finally, we use the standard deviation of energy ratio change (ERVSD) and infrared thermography (IRT) to compare with ADPV to verify the effectiveness of the method proposed in this paper. The experiment results show that the method proposed in this paper can effectively predict whether the concrete surface is damaged and the severity of damage.