Development of a Crack Recognition Algorithm from Non-routed Pavement Images using Artificial Neural Network and Binary Logistic Regression

유현석,김영석 대한토목학회 2016 KSCE JOURNAL OF CIVIL ENGINEERING Vol.20 No.4

Road pavements require periodic maintenance and repair, which as a national infrastructure facility requires an enormous annual. The crack sealing method has been widely used in the implementation of pavement repair and maintenance. Developed countries have recognized the importance of the crack sealing method and have continuously pursued research on the development of automated crack sealing equipment such as ARMM(Automated Road Maintenance Machine), OCCSM(Operator Controlled Crack Sealing Machine), and TTLS(Transfer Tank Longitudinal Sealer) since the early 1990s. In 2004, APCS(Automated Pavement Crack Sealer), which seals routed cracks on the road, was developed in Korea, and since 2009, the development of ACSTM(Automated Crack Sealer with Telescopic Manipulator) for the sealing of non-routed cracks has been underway. Because the non-routed crack is characterized by a very narrow width of 2~3 mm, in comparison to the routed crack, it is necessary to use high-resolution pavement images of over five million pixels in order to detect non-routed cracks. Moreover, it is very effective to employ intelligent algorithms that can distinguish cracks and noise from the high-resolution images using the morphological characteristics of non-routed crack. The purpose of this study is to develop an intelligent algorithm, which can distinguish crack and noise by eliminating the noise, to enable the ACSTM equipment in easy detection of the non-routed cracks. This study subjects the binary high-resolution images of the non-routed cracks to artificial neural network and binary logistic regression analysis for this purpose of intelligently discerning the crack images from the noise. Actual pavement images have been used to compare and verify the accuracy of the proposed algorithm in identifying cracks.

아스팔트 콘크리트 포장용 균열실링재의 부착특성 평가

이재준,김승훈,백종은,임재규,김용주 한국도로학회 2015 한국도로학회논문집 Vol.17 No.2

Cracking is an inevitable fact of asphalt concrete pavements and plays a major role in pavement deterioration. Pavement cracking is one of the main factors determining the frequency and method of repair. Cracks can be treated with a number of preventative maintenance actions, including overlay surface treatments such as slurry sealing, crack sealing, or crack filling. Pavement cracks can show up as one or all of the following types: transverse, longitudinal, fatigue, block, reflective, edge, and slippage. Crack sealing is a frequently used pavement maintenance treatment because it significantly extends the pavement service life. However, crack sealant often fails prematurely due to a loss of adhesion. Because current test methods are mostly empirical and only provide a qualitative measure of the bond strength, they cannot accurately predict the adhesive failure of the sealant. This study introduces a laboratory test aimed at assessing the bonding of hot-poured crack sealant to the walls of pavement cracks. A pneumatic adhesion tensile testing instrument (PATTI) was adopted to measure the bonding strength of the hot-poured crack sealant as a function of the curing time and temperature. Based on a limited number of test results, the hot-poured crack sealants have very different bonding performances. Therefore, this test method can be proposed as part of a newly developed performancebased standard specification for hot-poured crack sealants for use in the future. PURPOSES : The purpose of this study was to evaluate both the adhesion and failure performance of a crack sealant as a function of its curing time and curing temperature. METHODS: A pneumatic adhesion tensile testing instrument (PATTI) was adopted to measure the adhesion performance of a crack sealant as a function of the curing time and curing temperature. RESULTS: With changes in the curing time, curing temperature, and sealant type, the bond strengths were found to be significantly different. Also, higher bond strengths were measured at lower temperatures. Different sealant types produced completely different bond strengths and failure behaviors. CONCLUSIONS: The bonding strength of an evaluated crack sealant was shown to differ depending on various factors. Two sealant types, which were composed of different raw materials, were shown to perform differently. The newly proposed test offers the possibility of evaluating anddifferentiatingbetweendifferentcracksealants.Basedonalimitednumberoftestresults,this test method can be proposed as part of a newly developed performance-based standard specification for crack sealants or as part of a guideline for the selection of hot-poured crack sealant in the future.

The effect of micro pore on the characteristics of crack tip plastic zone in concrete

Hadi Haeri,V. Sarfarazi 사단법인 한국계산역학회 2016 Computers and Concrete, An International Journal Vol.17 No.1

Concrete is a heterogeneous material containing many weaknesses such as micro-cracks, pores and grain boundaries. The crack growth mechanism and failure behavior of concrete structures depend on the plastic deformation created by these weaknesses. In this article the non-linear finite element method is used to analyze the effect of presence of micro pore near a crack tip on both of the characteristics of crack tip plastic zone (its shape and size) and crack growth properties (such as crack growth length and crack initiation angle) under pure shear loading. The FE Code Franc2D/L is used to carry out these objectives. The effects of the crack-pore configurations and the spacing between micro pore and pre-excising crack tip on the characteristics of crack tip plastic zone and crack growth properties is highlighted. Based on the obtained results, the relative distance between the crack tip and the micro pore affects in very significant way the shape and the size of the crack tip plastic zone. Furthermore, crack growth length and crack initiation angle are mostly influenced by size and shape of plastic zone ahead of crack tip. Also the effects of pore decrease on the crack tip by variation of pore situation from linear to perpendicular configuration. The critical position for a micro pore is in front of the crack tip.

Investigating the effects of non-persistent cracks’ parameters on the rock fragmentation mechanism underneath the U shape cutters using experimental tests and numerical simulations with PFC2D

Jinwei Fu,Hadi Haeri,Vahab Sarfarazi,Sh. Mohamadi Bolban Abad,Mohammad Fatehi Marji,Gholamreza Saeedi,Yibing Yu 국제구조공학회 2022 Structural Engineering and Mechanics, An Int'l Jou Vol.83 No.4

This paper aims to study the fracture mechanism of rocks under the ‘u’ shape cutters considering the effects of crack (pre-existing crack) distances, crack spacing and crack inclination angles. The effects of loading rates on the rock fragmentation underneath these cutters have been also studied. For this purpose, nine experimental samples with dimensions of 5 cm×10 cm×10 cm consisting of the non-persistent cracks were prepared. The first three specimens’ sets had one non-persistent crack (pre-existing crack) with a length of 2 cm and angularity of 0°, 45°, and 90°. The spacing between the crack and the “u” shape cutter was 2 cm. The second three specimens” set had one non-persistent crack with a length of 2 cm and angularity of 0°, 45°, and 90° but the spacing between pre-existing crack and the “u” shape cutter was 4 cm. The third three specimens’ set has two non-persistent cracks with lengths of 2 cm and angularity of 0°, 45° and 90°. The spacing between the upper crack and the “u” shape cutter was 2 cm and the spacing between the lower crack and the upper crack was 2 cm. The samples were tested under a loading rate of 0.005 mm/s. concurrent with the experimental investigation. The numerical simulations were performed on the modeled samples with non-persistent cracks using PFC2D. These models were tested under three different loading rates of 0.005 mm/s, 0.01 mm/sec and 0.02 mm/sec. These results show that the crack number, crack spacing, crack angularity, and loading rate has important effects on the crack growth mechanism in the rocks underneath the “u” shape cutters. In addition, the failure modes and the fracture patterns in the experimental tests and numerical simulations are similar to one another showing the validity and accuracy of the current study.

아스팔트 콘크리트 포장용 균열실링재의 부착특성 평가

이재준,김승훈,백종은,임재규,김용주 한국도로학회 2015 한국도로학회논문집 Vol.17 No.2

Cracking is an inevitable fact of asphalt concrete pavements and plays a major role in pavement deterioration. Pavement cracking is one of the main factors determining the frequency and method of repair. Cracks can be treated with a number of preventative maintenance actions, including overlay surface treatments such as slurry sealing, crack sealing, or crack filling. Pavement cracks can show up as one or all of the following types: transverse, longitudinal, fatigue, block, reflective, edge, and slippage. Crack sealing is a frequently used pavement maintenance treatment because it significantly extends the pavement service life. However, crack sealant often fails prematurely due to a loss of adhesion. Because current test methods are mostly empirical and only provide a qualitative measure of the bond strength, they cannot accurately predict the adhesive failure of the sealant. This study introduces a laboratory test aimed at assessing the bonding of hot-poured crack sealant to the walls of pavement cracks. A pneumatic adhesion tensile testing instrument (PATTI) was adopted to measure the bonding strength of the hot-poured crack sealant as a function of the curing time and temperature. Based on a limited number of test results, the hot-poured crack sealants have very different bonding performances. Therefore, this test method can be proposed as part of a newly developed performancebased standard specification for hot-poured crack sealants for use in the future. PURPOSES : The purpose of this study was to evaluate both the adhesion and failure performance of a crack sealant as a function of its curing time and curing temperature. METHODS: A pneumatic adhesion tensile testing instrument (PATTI) was adopted to measure the adhesion performance of a crack sealant as a function of the curing time and curing temperature. RESULTS: With changes in the curing time, curing temperature, and sealant type, the bond strengths were found to be significantly different. Also, higher bond strengths were measured at lower temperatures. Different sealant types produced completely different bond strengths and failure behaviors. CONCLUSIONS: The bonding strength of an evaluated crack sealant was shown to differ depending on various factors. Two sealant types, which were composed of different raw materials, were shown to perform differently. The newly proposed test offers the possibility of evaluating anddifferentiatingbetweendifferentcracksealants.Basedonalimitednumberoftestresults,this test method can be proposed as part of a newly developed performance-based standard specification for crack sealants or as part of a guideline for the selection of hot-poured crack sealant in the future.

ON CRACK INTERACTION EFFECTS OF IN-PLANESURFACE CRACKS USING ELASTIC AND ELASTIC-PLASTICFINITE ELEMENT ANALYSES

JONG-MIN KIM,허남수 한국원자력학회 2010 Nuclear Engineering and Technology Vol.42 No.6

The crack-tip stress fields and fracture mechanics assessment parameters for a surface crack, such as the elastic stressintensity factor or the elastic-plastic J-integral, can be affected significantly by the adjacent cracks. Such a crack interactioneffect due to multiple cracks can alter the fracture mechanics assessment parameters significantly. There are many factors tobe considered, for instance the relative distance between adjacent cracks, the crack shape, and the loading condition, to quantifythe crack interaction effect on the fracture mechanics assessment parameters. Thus, the current assessment codes on crackinteraction effects (crack combination rules), including ASME Sec. XI, BS7910, British Energy R6 and API 579-1/ASME FFS-1,provide different rules for combining multiple surface cracks into a single surface crack. The present paper investigates crackinteraction effects by evaluating the elastic stress intensity factor and the elastic-plastic J-integral of adjacent in-plane surfacecracks in a plate through detailed 3-dimensional elastic and elastic-plastic finite element analyses. The effects on the fracturemechanics assessment parameters of the geometric parameters, the relative distance between two cracks, and the crack shapeare investigated systematically. As for the loading condition, an axial tension is considered. Based on the finite elementresults, the acceptability of the crack combination rules provided in the existing guidance was investigated, and the relevantrecommendations on a crack interaction for in-plane surface cracks are discussed. The present results can be used to developmore concrete guidance on crack interaction effects for crack shape characterization to evaluate the integrity of defectivecomponents.

Automated assessment of cracks on concrete surfaces using adaptive digital image processing

Yufei Liu,조수진,Jiansheng Fan,Billie F. Spencer, Jr. 국제구조공학회 2014 Smart Structures and Systems, An International Jou Vol.14 No.4

Monitoring surface cracks is important to ensure the health of concrete structures. However, traditional visual inspection to monitor the concrete cracks has disadvantages such as subjective inspection nature, associated time and cost, and possible danger to inspectors. To alter the visual inspection, a complete procedure for automated crack assessment based on adaptive digital image processing has been proposed in this study. Crack objects are extracted from the images using the subtraction with median filter and the local binarization using the Niblack\' s method. To adaptively determine the optimal window sizes for the median filter and the Niblack\' s method without distortion of crack object, an optimal filter size index (OFSI) is proposed. From the extracted crack objects using the optimal size of window, the crack objects are decomposed to the crack skeletons and edges, and the crack width is calculated using 4-connected normal line according to the orientation of the local skeleton line. For an image, a crack width nephogram is obtained to have an intuitive view of the crack distribution. The proposed procedure is verified from a test on a concrete reaction wall with various types of cracks. From the crack images with different crack widths and patterns, the widths of cracks in the order of submillimeters are calculated with high accuracy.

다중 표면균열의 균열형상 이상화 기준 적용성 평가

김종민(Jong-Min Kim),허남수(Nam-Su Huh),최순(Suhn Choi),박근배(Keun-Bae Park),최재붕(Jae-Boong Choi) 대한기계학회 2009 대한기계학회 춘추학술대회 Vol.2009 No.5

The fracture mechanics assessment parameters, such as the elastic stress intensity factor and the elastic-plastic J-integral, for a surface crack can be significantly affected by adjacent cracks. Regarding such an interaction effect, the relative distance between adjacent cracks, crack aspect ratio and loading condition were known to be important factors for multiple cracks, which affects the fracture mechanics assessment parameters. Although several guidance (ASME Sec. XI, BS7910, British Energy R6 and API RP579) on a crack interaction effect (crack combination rule) have been proposed and used for assessing the interaction effect, each guidance provides different rules for combining multiple surface cracks into a single surface crack. Based on the systematic elastic and elatic-plastic finite element analyses, the present study investigated the acceptability of the crack combination rules provided in the existing guidance, and the relevant recommendations on a crack interaction for in-plane surface cracks in a plate were discussed. To quantify the interaction effect, the elastic stress intensity factor and elastic-plastic J-integral along the crack front were used. As for the loading condition, only axial tension was considered. As a result, BS7910 seems to provide the most relevant crack combination rule for in-plane dual surface cracks, whereas API RP579 provides the most conservative results. In particular, ASME Sec. XI still seems to have some room for a revision to shorten the critical distance between two adjacent cracks for a crack combination. The overall tendency of the elastic-plastic analyses results is identical to that of the elastic analyses results.

Automated assessment of cracks on concrete surfaces using adaptive digital image processing

Liu, Yufei,Cho, Soojin,Spencer, Billie F. Jr,Fan, Jiansheng Techno-Press 2014 Smart Structures and Systems, An International Jou Vol.14 No.4

Monitoring surface cracks is important to ensure the health of concrete structures. However, traditional visual inspection to monitor the concrete cracks has disadvantages such as subjective inspection nature, associated time and cost, and possible danger to inspectors. To alter the visual inspection, a complete procedure for automated crack assessment based on adaptive digital image processing has been proposed in this study. Crack objects are extracted from the images using the subtraction with median filter and the local binarization using the Niblack's method. To adaptively. determine the optimal window sizes for the median filter and the Niblack's method without distortion of crack object an optimal filter size index (OFSI) is proposed. From the extracted crack objects using the optimal size of window, the crack objects are decomposed to the crack skeletons and edges, and the crack width is calculated using 4-connected normal line according to the orientation of the local skeleton line. For an image, a crack width nephogram is obtained to have an intuitive view of the crack distribution. The proposed procedure is verified from a test on a concrete reaction wall with various types of cracks. From the crack images with different crack widths and patterns, the widths of cracks in the order of submillimeters are calculated with high accuracy.

다중 표면결함이 존재하는 배관의 응력확대계수에 미치는 결함상호작용 평가

이기범(Gi-Bum Lee),장윤영(Youn-Young Jang),허남수(Nam-Su Huh) 대한기계학회 2021 대한기계학회 춘추학술대회 Vol.2021 No.4

국내 원전설비에서는 건전성 평가를 위해 가동중검사를 주기적으로 시행하며, 이때 많은 다중 결함이 발견될 수 있다. 다중 결함이 발생하면 각 결함선단의 응력 분포와 파괴역학 매개변수는 인접 균열에 의해 크게 영향을 받을 수 있다. 따라서 결함상호작용을 평가하고, 영향이 클 경우 이를 새로운 단 일 결함으로 이상화 할 필요가 있다. 결함상호작용은 결함의 형상이나 하중 조건 등 많은 인자에 의해영향을 받기 때문에, 적절한 다중 결함 이상화에 대한 기준을 정립하기 위해서는 이러한 많은 인자를 고려한 체계적인 분석이 수행되어야 한다. 본 연구에서는3 차원 탄성 유한요소해석을 이용하여 배관에 존재하는 다중 반타원 표면결함에 대한 결함상호작용을 평가하였다. 이를 위해 3 차원 탄성 유한요소해석을 수행하여 결함 선단에 따른 응력확대계수를 산출하였으며, 결함 깊이, 결함 길이, 결함간의 거리 등 다양한 기하학적 변수를 고려하였다. 또한 기존 평판과 배관의 응력확대계수를 비교하여, 기하학적인 곡률에 따른 균열상호작용의 영향을 검토하였다. 또한 평가 결과를 기존 절차법의 기준(ASME Sec. XI, API RP 579 및 BS7910)과 비교하여, 기존절차법의 타당성과 적용성을 확인하였다. 본 연구의 결과는 배관의 다양한 형상에 따른 결함상호작용을 고려한 다중 표면결함 형상 이상화 절차 개선에 활용될 수 있으며, 향후 AI-FEM 을 통한 자연 결함성장을 예측하는데 시행될 예정이다. Periodic in-service inspection(ISI) has been carried out on components of nuclear power plants to evaluate integrity, and many multiple cracks can be found during ISI. When multiple cracks were detected, the stress fields at the crack-tip and fracture mechanics parameters, such as stress intensity factor, can be significantly affected by the adjacent cracks. For this reason, the crack interaction effect should be examined, and these multiple cracks should be idealized as a single crack when the interaction effect are significant. Since the crack interaction is largely affected by various factors, such as crack shape and the loading condition, systematical analyses considering these factors should be performed to establish suitable criteria for idealizing for multiple cracks. In this study, three-dimensional elastic finite element (FE) analyses were performed to evaluate the crack interaction effect for multiple semi-elliptic surface cracks in pipes. To quantify the crack interaction effect, the stress intensity factor was calculated considering various crack depth, crack length, and distance between each of crack. In addition, the stress intensity factors from the cracked plate were compared with those from the cracked pipe to investigate the effect of geometric curvature on crack interaction. The FE results were compared with the existing criteria of codes and standard(ASME Sec. XI, API RP 579, BS7910) to confirm the validity and applicability of the crack combination rule in the existing guidance. The present results can be used to improve the idealization procedure of multiple surface crack considering crack interaction effect for various pipe geometries. The present results will be implemented to AI-FEM to predict natural crack growth.