• 콘크리트학회논문집
• /
• 제17권3호
• /
• pp.369-374
• /
• 2005

이 연구의 목적은 화상처리 기법과 신경회로망을 이용하여 다섯가지 균열 패턴 즉, 횡방향, 종방향, 대각선($-45^{\circ}$) 대각선($+45^{\circ}$) 그리고 비방향성 균열의 패턴을 인식할 수 있는 기법을 제안하는 것이다. 제안된 화상처리 알고리즘과 인공 신경회로망 모델은 MATLAB 언어를 이용하여 구현하였다. 인공 신경회로망의 입력층에 들어갈 패턴인자는 Total projection technique를 통해 구하였으며, 인공 신경회로망의 구조(은닉층의 수와 은닉노드의 수)와 가중치 값은 가상 균열 화상을 사용하여 학습을 통해 결정하였다. 인공 신경회로망의 학습은 Bayesian regularization 기법을 도입함으로써 과적합 문제가 발생하지 않도록 하였으며, 이 연구에서 제안한 기법의 적합성을 판정하기 위하여 총 38개의 실제 균열 화상을 사용하여 시험하였다. 검증 시험 결과내에서는 이 연구에서 제안한 기법이 사람의 균열 패턴 인식결과와 정확히 일치하는 결과것으로 나타났다.

• 한국해양공학회지
• /
• 제16권4호
• /
• pp.13-18
• /
• 2002

The magnitude of the plastic zone around the crack tip of DENT(Double Edge Notched Tension) specimen and the crack growth length under cyclic loading were measured by ESPI(Electronic Speckle Pattern Interferometry) system. The measured magnitude of plastic zone was compared with the equations proposed by Irwin and calculated by a nonlinear static method of MSC/NASTRAN. The measured crack growth length by ESPI system was also compared with the obtained data by the image analysis system. From the study, it is confirmed that the plastic zone and crack growth length can be measured accurately with the high-tech equipment.

• 비파괴검사학회지
• /
• 제22권6호
• /
• pp.643-648
• /
• 2002

In this study, shearography and ESPI have been used for quantitative analysis of an inside crack of pipeline and both of them appeared suitable to qualitatively detect inside crack. However, shearography needs several effective factors including the amount of shearing, shearing direction and induced load for the quantitative evaluation of the inside crack. In this study, the factors were optimized for the quantitative analysis and the site of cracks has been determined. Although the effective factors in shearography has been optimized, it is difficult to determine the factors exactly because they are related to the details of tracks. On the other hand, ESPI is independent on the details of a crack and only the induced load plays an important role. The out-of-plane displacement was measured under the optimized load and the measured were numerically differentiated, which resulted in an equivalent to the shearogram. The size of cracks can be determined quantitatively without any detail of a crack.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 추계학술대회 논문집
• /
• pp.80-84
• /
• 2002

In this study, researchers developed the est algorithm for artificial defects in the semic packages and performed to it by pattern recogn technology. For this purpose, this algorithm was I that researcher made software with matlab. The so consists of some procedures including ultrasonic acquistion, equalization filtering, self-organizing backpropagation neural network. self-organizing ma backpropagation neural network are belong to metho neural networks. And the pattern recognition tech has applied to classify three kinds of detective pa semiconductor packages. that is, crack, delaminat normal. According to the results, it was found estimative algorithm was provided the recognition r 75.7%( for crack) and 83.4%( for delamination) 87.2 % ( for normal).

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2005년도 춘계학술대회 논문집
• /
• pp.91-96
• /
• 2005

In this study, researchers developed the estimative algorithm for artificial defects in semiconductor packages and performed it by pattern recognition technology. For this purpose, the estimative algorithm was included that researchers made software with MATLAB. The software consists of some procedures including ultrasonic image acquisition, equalization filtering, Self-Organizing Map and Backpropagation Neural Network. Self-Organizing Map and Backpropagation Neural Network are belong to methods of Neural Networks. And the pattern recognition technology has applied to classify three kinds of detective patterns in semiconductor packages: Crack, Delamination and Normal. According to the results, we were confirmed that estimative algorithm was provided the recognition rates of $75.7\%$ (for Crack) and $83_4\%$ (for Delamination) and $87.2\%$ (for Normal).

• Computers and Concrete
• /
• 제24권1호
• /
• pp.51-61
• /
• 2019

Compressive ability is one of the most important mechanical properties of concrete material. The compressive failure process of concrete is pretty complex with internal tension, shear damage and friction between cracks. To simulate the complex fracture process of concrete at meso level, methodology for meso-structural analysis of concrete specimens is developed; the zero thickness cohesive elements are pre-inserted to simulate the crack initiation and propagation; the constitutive applied in cohesive element is established to describe the mechanism of crack separation, closure and friction behavior between the fracture surfaces. A series of simulations were carried out based on the model proposed in this paper. The results reproduced the main fracture and mechanical feature of concrete under compression condition. The effect of key material parameters, structure size, and aggregate content on the concrete fracture pattern and loading carrying capacities was investigated. It is found that the inner friction coefficient has a significant influence on the compression character of concrete, the compression strength raises linearly with the increase of the inner friction coefficient, and the fracture pattern is sensitive to the mesostructure of concrete.

• 한국컴퓨터그래픽스학회논문지
• /
• 제28권2호
• /
• pp.1-9
• /
• 2022

본 논문에서는 균열을 감지 할 때 필요한 데이터를 생성할 수 있는 벡터 기반 증강 기법과 이를 학습할 수 있는 합성곱 인공신경망(Convolution Neural Networks, ConvNet) 기법을 제안한다. 균열을 빠르고 정확하게 감지하는 것은 건물 붕괴와 낙하 사고를 사전에 방지할 수 있는 중요한 기술이다. 이 문제를 인공지능으로 해결하기 위해서는 대량의 데이터 확보가 필수적이지만, 실제 균열 이미지를 얻기 위한 상황은 대부분 위험하기 때문에 대량의 균열 데이터를 확보하기는 어렵다. 이런 데이터베이스 구축의 문제점은 인위적인 특정 부분에 변형을 주어 데이터의 양을 늘리는 탄성왜곡(Elastic distortion)으로 완화시킬 수 있지만, 본 논문에서는 이보다 향상된 균열 패턴 결과를 ConvNet을 활용하여 모델링한다. 탄성왜곡보다 우리의 방법이 실제 균열 패턴과 유사하게 추출된 결과를 얻을 수 있었고, 일반적인 데이터 증강에서 사용되는 픽셀 단위가 아닌, 벡터 기반으로 균열 데이터 증강을 설계함으로써 균열의 변화량 측면에서 우수한 결과를 얻을 수 있다. 결과적으로 본 논문에서는 적은 개수의 균열 데이터를 입력으로 사용했음에도 불구하고 균열의 방향 및 패턴을 다양하게 생성하여 효율적으로 균열 데이터베이스를 구축할 수 있다.

• 한국철도학회논문집
• /
• 제20권3호
• /
• pp.374-381
• /
• 2017

국내 대부분의 선구에 부설된 콘크리트침목은 적절히 유지관리되지 않을 경우 열차 운행의 안전성을 심각하게 위협하는 요소가 될 수 있다. 이 연구에서는 최근 가장 강력한 적응성(adaptive)을 갖는 기법으로 활용 범위를 넓히고 있는 Adaboost를 이용하여 고해상도카메라로 촬영한 침목이미지에서 균열을 자동검출할 수 있는 알고리즘을 개발하였다. 개발된 알고리즘은 실제 침목에 발생한 균열 및 비균열 이미지를 분석한 후 도출한 균열특징을 이용하여 학습하였다. 침목균열 자동검출 알고리즘의 적용성은 48개의 학습이미지와 11개의 비학습이미지를 이용하여 검토하였다. 검토 결과 학습이미지와 비학습이미지 모두 균열폭과 균열길이에 대한 인식률이 90% 이상으로 나타났으며, 충분한 균열인식 성능을 갖는 것으로 나타났다.

• Structural Monitoring and Maintenance
• /
• 제1권3호
• /
• pp.309-322
• /
• 2014

Detection of fatigue cracks at an early stage of their development is important in structural health monitoring. The breathing of cracks in a structure generates higher harmonic components of the exciting frequency in the frequency spectrum. Previously, the residual operational deflection shape (R-ODS) method was successfully applied to beams with a single crack. The method is based on the ODSs at the exciting frequency and its higher harmonic components which consider both amplitude and phase information of responses to map the deflection pattern of structures. Although the R-ODS method shows the location of a single crack clearly, its identification for the location of multiple cracks in a structure is not always obvious. Therefore, an improvement to the R-ODS method is presented here to make the identification process distinct for the beams with multiple cracks. Numerical and experimental examples are utilised to investigate the effectiveness of the improved method.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1997년도 봄 학술발표회 논문집
• /
• pp.235-240
• /
• 1997

The purpose of this experiment is to verify processing crack direction and state by the corrosion of electrifying re-bar in the salt water. The result of this experiment is the fact that the first crack appear on the surface of water-because of supplying of oxygen and water. The crack processing is on a surface to be contacted by air and to bottom as mainly the vertical direction from a surface of water. The crack by corrosion of steel reinforcing is emerged by the inside of concrete rather than surface concrete.