• Journal of the Korea Concrete Institute
• /
• v.17 no.3 s.87
• /
• pp.369-374
• /
• 2005

This study proposes a technique for the recognition of crack patterns, which includes horizontal, vertical, diagonal($-45^{\circ}$), diagonal($+45^{\circ}$), and random cracks, based on image processing technique and artificial neural network. A MATLAB code was developed for the proposed image processing algorithm and artificial neural network. Features were determined using total projection technique, and the structure(no. of layers and hidden neurons) and weight of artificial neural network were determined by learning from artificial crack images. In this process, we adopted Bayesian regularization technique as a generalization method to eliminate overfitting Problem. Numerical tests were performed on thirty-eight crack images to examine validity of the algorithm. Within the limited tests in the present study, the proposed algorithm was revealed as accurately recognizing the crack patterns when compared to those classified by a human expert.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.22 no.1
• /
• pp.1-8
• /
• 2002

The high frequency ultrasonic transducers using polyvinyliden fluoride(PVDF) and polyvinylidene fluoride trifluorethyylene(P(VDF-TrFE)) were developed. The characteristics of fabricated high frequency ultrasonic transducer such as beam diameter, high frequency ultrasonic detection field and amplitude of the first pulse echo signal from the test target in the water were analyzed. The high frequency ultrasonic detection field was affected by the length of coaxial cable between high frequency transducer and ultrasonic pulser/receiver. As the size of the test target increased, the high frequency detection field decreased and the amplitude of a reflection signal increased. The peak amplitude of the first pulse echo signal of P(VDF-TrFE) transducer was higher than that of PVDF transducer. The high frequency ultrasonic detection field of PVDF transducer was wider than that of P(VDF-TrFE) transducer. With C-scan testing, the developed high frequency ultrasonic transducer could detect the 30 to $100{\mu}m$ of hydrogen induced crack of steel specimen by C-scan testing.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.4 s.22
• /
• pp.77-84
• /
• 2002

Recently, damage of pavement represented by crack is depened by the increase of traffic demand up to ten million and wight, and interest about the efficient management of pavement is being increased gradually according to the growth of maintenance expense of road surface. In this study, the possibility of application for acquisition of crack information was tested by appling DCRP and digital image processing technique and measuring crack on road surface precisely. Based on this, objective and efficient road surface measurement was planned and done. Measuring crack width, acquire result of comparative high accuracy. So, it is considered that it can be utilized as plan draft data for deterioration estimation and repair reinforcement work of pavement.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.5
• /
• pp.493-500
• /
• 2001

The detection of axial cracks using conventional MFL pig is a significant challenge in the gas pipeline inspection. In this study, a technique using interaction of circumferentially induced torrents with axial stress corrosion crack is presented. The feasibility of this technique is investigated using finite element modeling. Finite element analysis of such interaction is a difficult problem in terms of both computation time and memory requirements. The challenges arise due to the nonlinearity of material properties, the small sire of tight cracks relative to that of the magnetizer, and also time stepping involved in modeling velocity effects. This paper presents an approach based on perturbation methods. The overall analysis procedure is divided into 4 simple steps that can be performed sequentially. Modeling results show that this technique can effectively detect colonies of SCC as well as single SCC.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2011.04a
• /
• pp.419-423
• /
• 2011

Unlike other non-destructive inspection method, AE Structural defects that are likely to grow in the operation status can be detected, and the advantage of being due to the continuous monitoring of large structures has been widely used to evaluate the stability. AE sensor used to detect sound wave that occurs between 20kHz to 20MHz. and Sound wave result may vary depending on sensor's sensitivity. In this paper, Tensile test conducted on STS 304 and SS400, and tries to detect the crack signal. In tensile test, specimens were conducted using different sensor sensitivity to the same tensile test condition. The crack signal parameters divided into 4 types of communities by conducting cluster analysis. It was demonstrated that crack signal of two sensor is not different by statistical analysis of null hypotheses. Based on the results, waveform of this tension test is crack signal.

• Journal of Korea Multimedia Society
• /
• v.10 no.8
• /
• pp.1068-1077
• /
• 2007

This paper proposes a method that extracts characteristics of cracks such as length, thickness and direction from a concrete slab surface image with image processing techniques. These techniques extract the cracks from the concrete surface image in variable conditions including bad image conditions) using the ART2-based RBF network to recognize the dominant directions -45 degree, 45 degree, horizontal and vertical) of the extracted cracks from the automatically calculated specifications like the lengths, directions and widths of the cracks. Our proposed extraction algorithms and analysis of the concrete cracks used a Robert operation to emphasize the cracks, and a Multiple operation to increase the difference in brightness between the cracks and background. After these treatments, the cracks can be extracted from the image by using an iterated binarization technique. Noise reduction techniques are used three separate times on this binarized image, and the specifications of the cracks are extracted form this noiseless image. The dominant directions can be recognized by using the ART2-based RBF network. In this method, the ART2 is used between the input layer and the middle layer to learn, and the Delta learning method is used between the middle layer and the output layer. The experiments using real concrete images showed that the cracks were effectively extracted, and the Proposed ART2-based RBF network effectively recognized the directions of the extracted cracks.

• Journal of Welding and Joining
• /
• v.12 no.4
• /
• pp.35-40
• /
• 1994

비파괴검사(NDT)란 시험품에 손상을 주지 않고 내.외부에 존재하는 불연속부(결함)을 찾아내는 방법으로 다음과 같이 그 종류를 분류할 수 있다. (1) 표면결함 검출을 위한 비파괴검사 - 육안검사(VT) : 확대경 등에 의한 치수, 형상확인 - 자분탐상검사(MT) : 강자성체에 적용, 표면(하) 결함검출 - 침투탐상검사(PT) : 금속, 비철금속에 적용, 표면개구 결함검출 - 와류탐상검사(ET) : 도체 표층부(봉, 관 등) (2) 내부결함 검출을 위한 비파괴검사 - 방사선 투과검사(RT) : 결함의 종류, 형상의 판별 우수 - 초음파 탐상검사(UT) : 균열 등 면상 결함검출 등 우수 (3) 기타 비파괴검사 - Strain 측정 : 안전성 평가 - 음향방출시험(AET) - 누설시험(LT) - 중성자 방사선시험(NRT) 이상에서 보는 바와 같이 여러 종류의 비파괴검사가 있으나, 그 중에서 용접부에 적용되는 가장 일반적인 검사방법인 방사선 투과검사에 대해 기술하고자 한다.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.35-42
• /
• 2020

In this study, we propose a crack detection method using limited data with a U-Net based image inpainting technique that is a modified unsupervised anomaly detection method. Concrete cracking occurs due to a variety of causes and is a factor that can cause serious damage to the structure in the long term. In general, crack investigation uses an inspector's visual inspection on the concrete surfaces, which is less objective in judgment and has a high possibility of human error. Therefore, a method with objective and accurate image analysis processing is required. In recent years, the methods using deep learning have been studied to detect cracks quickly and accurately. However, when the amount of crack data on the building or infrastructure to be inspected is small, existing crack detection models using it often show a limited performance. Therefore, in this study, an unsupervised anomaly detection method was used to augment the data on the object to be inspected, and as a result of learning using the data, we confirmed the performance of 98.78% of accuracy and 82.67% of harmonic average (F1_Score).

• 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 the Korean Society for Nondestructive Testing
• /
• v.18 no.4
• /
• pp.278-291
• /
• 1998

Fracture process of continuous fiber reinforced composites is very complex because various fracture mechanisms such as matrix cracking, debonding, delamination and fiber breaking occur simultaneously during crack growth. If fibers cause crack bridging during crack growth, the stable crack growth and unstable crack growth appear repeatedly. Therefore, it is very difficult to exactly determine tile starting point of crack growth and the fracture toughness at the critical crack length in composites. In this research, fracture toughness test for CFRP was accomplished by using acoustic emission(AE) and recording of tile fracture process in real time by video-microscope. The starting point of crack growth, pop-in point and the point of unstable crack growth can be exactly determined. Each fracture mechanism can be classified by analyzing the fracture process through AE and video-microscope. The more reliable method ior the fracture toughness measurement of composite materials was proposed by using the combination of R-curve method, AE and video microscope.