Crack Contour Research Articles

An improved EnlightenGAN shadow removal framework for images of cracked concrete

The concrete crack images in engineering are usually obscured by unexpected shadow and their removal is usually required which is always a challenging task due to its complexity and diversity. An improved Enlighten Generative Adversarial Networks (IEnlightenGAN) is developed in a proposed framework to improve shadow removal results. The Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN) is firstly developed to improve the concrete image resolution. Residual-in-residual-dense blocks module and Atrous Spatial Pyramid Pooling module are then integrated into the IEnlightenGAN to improve its shadow removal capability. A quality assessment methodology on the shadow removal results is also proposed. The crack contour is extracted based on U-Net, and denoising is conducted based on morphological closing. Image segmentation metrics are used for the evaluation. The proposed IEnlightenGAN and the evaluation method are trained and verified using a dataset containing both normal and shadowed concrete crack images with comparison of results from the state-of-the-art models. The proposed shadow removal framework is found able to improve the quality of shadowed crack images, and the proposed quality assessment method is also found better than existing approach.

Improved U-net network asphalt pavement crack detection method.

Road crack detection is one of the important parts of road safety detection. Aiming at the problems such as weak segmentation effect of basic U-Net on pavement crack, insufficient precision of crack contour segmentation, difficult to identify narrow crack and low segmentation accuracy, this paper proposes an improved U-net network pavement crack segmentation method. VGG16 and Up_Conv (Upsampling Convolution) modules are introduced as backbone network and feature enhancement network respectively, and the more abstract features in the image are extracted by using the Block depth separable convolution blocks, and the multi-scale features are captured and enhanced by higher level semantic information to improve the recognition accuracy of narrow cracks in the road surface. The improved network embedded the Ca(Channel Attention) attention mechanism in U-net's jump connection to enhance the crack portion to suppress background noise. At the same time, DG_Conv(Depthwise GSConv Convolution) module and UnetUp(Unet Upsampling) module are added in the decoding part to extract richer features through more convolutional layers in the network, so that the model pays more attention to the detailed part of the crack, so the segmentation accuracy can be improved. In order to verify the model's ability to detect cracks in complex backgrounds, experiments were carried out on CFD and Deepcrack datasets. The experimental results show that compared with the traditional U-net network F1-score and mIoU have increased by 13.6% and 9.9% respectively. Superior to advanced models such as U-net, Segnet and Linknet in accuracy and generalization ability, the improved model provides a new method for asphalt pavement crack detection. The model is more conducive to practical application and ground deployment, and can be applied in road maintenance projects.

Modeling Corrosion Product Film Formation and Hydrogen Diffusion at the Crack Tip of Austenitic Stainless Steel.

Corrosion product films (CPFs) have significant effects on hydrogen permeation and the corrosion process at the crack tip. This paper established a two-dimensional calculation model to simulate the formation of CPFs at the crack tip and its effects on the crack tip stress status and hydrogen diffusion. The CPFs were simplified as a single-layer structure composed of Fe2O3, the effective CPFs boundary was modeled by the diffusion of oxygen, and the CPF-induced stress was modeled by hygroscopic expansion. The simulation was conducted with two stages; the first stage was to simulate the formation of CPFs formation and its effects on the crack tip stress status, while the second stage focused on the hydrogen diffusion with and without CPF formation under different external tensile loads. The results indicate that the highest compressive stress induced by the formation of CPFs is located at 50~60° of the crack contour and dramatically weakens the crack tip tensile stress at low-stress status. The CPFs can inhibit the hydrogen permeation into the crack tip, and the hydrostatic pressure effects on the redistribution of the permeated hydrogen are significant under larger external load conditions.

Application of high‐performance DIC for a comprehensive evaluation of biaxial fatigue crack growth experiments

AbstractPrecise determination of the remaining service life of technical components requires sufficient knowledge of fatigue crack growth behaviour and the growth rate of defects. Cracks in real components often experience multiaxial far field stresses due to their complex geometry and composite loadings acting on it. Digital image correlation (DIC) is well established for crack length and displacement measurements, but it usually requires sample preparation with speckle paint and interferes with mechanical extensometers. To overcome these limitations, we use a novel 2D DIC system combining a graphics processing unit (GPU) with a CoaXPress 2.0 camera, acquiring up to 3 GB/s of image data. It enables real‐time evaluation of both integral strain like an extensometer and full‐field DIC on images selected automatically in real‐time. This combination enables the use of one single sensor for strain‐controlled testing and fatigue crack growth characterisation. The full‐field displacement is compared to a finite‐element model (FEM) simulating the actual crack contour measured by the DIC system. The results show that high‐performance DIC has the potential to simultaneously simplify crack‐growth experiments and provide comprehensive fracture mechanical information.

Measurement Method for Wall Crack Size Based on Pixel Ratio

The identification and measurement of building cracks can reduce the harm caused by accidents to people’s lives. Reducing manual work can improve the efficiency of crack inspection and reduce inspection errors. In this paper, (1) Machine vision with high measurement accuracy and fast response speed is used, the crack contour is extracted by OpenCV splicing, segmentation, morphological processing, and wall cracks can be accurately detected. (2) The crack size is calculated using the pixel ratio algorithm, the image pixel ratio is calculated by the reference object method, and the size of the wall crack is measured. (3) The measurement error is small. In comparing the experimental results and manual measurement, the width measurement error rate is the highest, 0.314%, and the height error rate is the highest, 2.9%. (4) Size information can be displayed to prevent the hazard caused by cracks in advance. So, the system has a good wall crack identification and measurement effect, which reduces labor costs.

Three-Stage Pavement Crack Localization and Segmentation Algorithm Based on Digital Image Processing and Deep Learning Techniques.

The image of expressway asphalt pavement crack disease obtained by a three-dimensional line scan laser is easily affected by external factors such as uneven illumination distribution, environmental noise, occlusion shadow, and foreign bodies on the pavement. To locate and extract cracks accurately and efficiently, this article proposes a three-stage asphalt pavement crack location and segmentation method based on traditional digital image processing technology and deep learning methods. In the first stage of this method, the guided filtering and Retinex methods are used to preprocess the asphalt pavement crack image. The processed image removes redundant noise information and improves the brightness. At the information entropy level, it is 63% higher than the unpreprocessed image. In the second stage, the newly proposed YOLO-SAMT target detection model is used to locate the crack diseases in asphalt pavement. The model is 5.42 percentage points higher than the original YOLOv7 model on mAP@0.5, which enhances the recognition and location ability of crack diseases and reduces the calculation amount for the extraction of crack contour in the next stage. In the third stage, the improved k-means clustering algorithm is used to extract cracks. Compared with the traditional k-means clustering algorithm, this method improves the accuracy by 7.34 percentage points, the true rate by 6.57 percentage points, and the false positive rate by 18.32 percentage points to better extract the crack contour. To sum up, the method proposed in this article improves the quality of the pavement disease image, enhances the ability to identify and locate cracks, reduces the amount of calculation, improves the accuracy of crack contour extraction, and provides a new solution for highway crack inspection.

Semantic segmentation with deep learning: detection of cracks at the cut edge of glass

In this paper, artificial intelligence (AI) will be applied for the first time in the context of glass processing. The goal is to use an algorithm based on artificial intelligence to detect the fractured edge of a cut glass in order to generate a so-called mask image by AI. In the context of AI, this is a classical problem of semantic segmentation, in which objects (here the cut-edge of the cut glass) are automatically surrounded by the power of AI or detected and drawn. An original image of a cut glass edge is implemented into a deep neural net and processed in such a way that a mask image, i.e. an image of the cut edge, is automatically generated. Currently, this is only possible by manual tracing the cut-edge due to the fact that the crack contour of glass can sometimes only be recognized roughly. After manually marking the crack using an image processing program, the contour is then automatically evaluated further. AI and deep learning may provide the potential to automate the step of manual detection of the cut-edge of cut glass to great extent. In addition to the enormous time savings, the objectivity and reproducibility of detection is an important aspect, which will be addressed in this paper.

Propagation of a Fatigue Crack on the Surface of Side Frame of a Freight Bogie under Irregular Operating Loads

We study the kinetics of propagation of fatigue cracks on the surface of side frame of a rail car with regard for the stochastic nature of the operating load. Its dependence on the initial geometry of the crack is established. Moreover, under given loading conditions, we determine the shape of semielliptic contour of the fatigue crack characterized by the highest growth rate into the depth of the frame wall. We also formulate a mathematical model suitable for the evaluation of the residual service life of the side frame containing a surface cracklike defect with given initial area.

ANALYSIS OF THE KINETICS AND DIRECTIONALITY OF ELASTOPLASTIC DEFORMATION AND FRACTURE

Safety, survivability, and serviceability of the equipment are governed by the strength characteristics of the separate units and elements which can contain initial or operational defects such as superficial differently oriented semi-elliptical cracks. Numerical methods of calculation provide a large bulk of information about the stress-strain state (SSS) of those elements proceeding from the given algorithms for calculating the corresponding fracture models. Change in the type of the SSS near the crack contour when going from the bulk to the surface depends on the constraint of deformations along their front, i.e., on the 3D character of the SSS. Diagnostics of the form change of the defects (surface differently oriented semi-elliptic low-cycle cracks) is carried out on the basis of experimental results and numerical solutions. The data of the finite element modeling are implemented on the basis of macros of the ANSYS program complex. The regularity of the directionality of developing the elastoplastic fracture under low-cycle loading is studied. The proposed methodology is proved by the parametric equations of the kinetics of forming changes of the cracks under study in the fractographic analysis of the surfaces of their development. The results of testing samples with semi-elliptic cracks under low-cycle loading are used in analysis of the parameters of the morphology of the surfaces of the developed defects. The results of measuring fields of elastoplastic deformation intensity in the crack tip and geometrical characteristics of the fracture surface development are presented. Analysis of the dynamics of the local stress-strain state near the contour of multi-oriented defects in parts and structural units of the equipment showed a good agreement between the experimental parameters of the geometry of developing cracks and characteristics obtained by numerical methods. The presented parametric equations specify the characteristics of nonlinear fracture mechanics thus providing reliable estimation and forecasting of survivability, and safety of serviceability of the critical equipment. The deformation criteria of nonlinear fracture mechanics are used to demonstrate the dependence of fracture development on the 3D character of the stress-strain state indicating to the directionality of the geometric development of the fracture surface form.

A Two-Stage Data-Driven Approach for Image-Based Wind Turbine Blade Crack Inspections

A two-stage approach for precisely detecting wind turbine blade surface cracks via analyzing blade images captured by unmanned aerial vehicles (UAVs) is proposed in this paper. The proposed approach includes two main detection procedures, the crack location and crack contour detection. In locating cracks, a method for extracting crack windows based on extended Haar-like features is introduced. A parallel sliding window method is developed to scan images and the cascading classifier is developed to classify sliding windows into two classes, crack and noncrack. Based on detected windows containing cracks, a novel clustering algorithm, the parallel Jaya K -means algorithm, is developed to assign each pixel in crack windows into crack and noncrack segments. Crack contours are obtained based on boundaries of crack segments. The effectiveness and efficiency of the proposed crack detection approach are validated by executing it on a personal computer and an embedded device with UAV-taken images collected from a commercial wind farm. Computational results demonstrate that the proposed approach can successfully identify both the blade crack locations and crack contours in UAV-taken images.

An efficient numerical method for quasi-static crack propagation in heterogeneous media

The paper is devoted to the problem of slow crack growth in heterogeneous media. The crack is subjected to arbitrary pressure distribution on the crack surface. The problem relates to construction of the so-called equilibrium crack. For such a crack, stress intensity factors are equal to the material fracture toughness at each point of the crack contour. The crack shape and size depend on spatial distributions of the elastic properties and fracture toughness of the medium, and the type of loading. In the paper, attention is focused on the case of layered elastic media when a planar crack propagates orthogonally to the layers. The problem is reduced to a system of surface integral equations for the crack opening vector and volume integral equations for stresses in the medium. For discretization of these equations, a regular node grid and Gaussian approximating functions are used. For iterative solution of the discretized equations, fast Fourier transform technique is employed. An iteration process is proposed for the construction of the crack shape in the process of crack growth. Examples of crack evolution for various properties of medium and types of loading are presented.

Determination of the diameter of columnar jointed volcanics using bifurcation analysis

AbstractThe development of the typical hexagonal pattern of solidifying volcanic material can be described by fracture mechanics. While following the moving inhomogeneous temperature field, these columns reach a steady growth with a certain diameter. This spacing increases sometimes instantaneously. Using a bifurcation analysis based on the free Helmholtz energy this phenomenon is investigated and presented with this contribution. In order to handle the complex three‐dimensional geometry, regularity in the pattern and a Fourier series expansion of the crack contour are used. (© 2017 Wiley‐VCH Verlag GmbH & Co. KGaA, Weinheim)

Identification of residual stress layers at glass surfaces via crack terminating angles

AbstractCracks terminating at free surfaces are affected by local stresses in the surface region. Under residual compression the crack front must retard compared with the crack contour in the absence of stresses. This effect can be used for an identification of residual stresses at glass surfaces. For an illustration of the procedure, Vickers indentation tests in soda‐lime glass are considered. Specimens treated by ion exchange and chemically toughening showed reduced terminating angles compared with untreated glass.

Thermoelastic State of a Half Plane with Curvilinear Crack Under the Conditions of Local Heating

We consider a two-dimensional problem of stationary heat conduction and thermoelasticity for a half plane containing an internal curvilinear crack and heated by a heat flow in a local region. We reduce the problem to two singular integral equations on the crack contour. The numerical solution of the integral equations is obtained by the method of mechanical quadratures. The stress intensity factors at the tips of a parabolic crack are determined.

In Situ Monitoring of Rail Squats in Three Dimensions Using Ultrasonic Technique

Rail squats and studs are typically classified as the growth of any cracks that have grown longitudinally through the subsurface of rails. This study highlights in situ monitoring of squat/stud distribution and its growth in the field. Squat/stud growth has been determined and plotted using the ultrasonic measurement device and the crack depths at each reference grid node form a three-dimensional contour of rail squat crack. In this study, the crack propagation of squats/studs is roughly estimated to be almost linear to repeated train loads called as accumulated passing tonnages up to a certain degree of propagated crack length. This in situ monitoring is of significance to railway authorities in order to effectively and efficiently prioritize maintenance functions, which will improve safety and reliability of the rail network.

Contours for Planar Cracks Growing in Three Dimensions: Influence of Kinetic Energy

Dynamic steady-state growth in 3D of a semi-infinite plane brittle crack in isotropic elastic solids is considered. Loads cause growth by translating on the crack surfaces at constant, subcritical speed. An analytical solution is obtained and subjected to a criterion for brittle crack growth based on dynamic energy release rate, with kinetic energy included. The result is a nonlinear differential equation for the crack contour, i.e., the curve formed by the crack edge in the crack plane. The equation is studied for the case of compression loading by translating point forces. At large distances from the forces, the crack edge asymptotically approaches the rectilinear and kinetic energy effects can be negligible. A bulge forms around the forces, however, the effect of kinetic energy on its size can be pronounced.

Influence of the Shape of Curvilinear Cracks on the Dynamic Stress Intensity Factors

We study the influence of the shapes of smooth curvilinear cracks in infinite two-dimensional elastic domains on the time dependences of the stress intensity factors for various kinds of dynamic loads on the crack faces. By using a modified finite-difference method with respect to time, we reduce the dynamic problem to the solution of a system of singular integrodifferential equations for the jumps of displacements in passing through the crack contour at each analyzed time. The numerical solutions of the integral equations are obtained by the method of mechanical quadratures. We also analyze the time dependences of the dynamic stress intensity factors at the tips of curvilinear cracks located along the arc of a circle, of a parabola, or of a semiellipse for different impact and impulsive loads applied to the crack faces.

Deformation and fracture mechanisms and structural changes in coarse-grained copper under shock-wave loading

Results of experiments on shock-wave deformation of M2 copper under uniaxial loading are presented. Light, scanning, and transmission electron microscopy methods are used to reveal specific features of mechanisms of deformation and fracture of copper during the formation of a main spall crack. The parameters of spall strength, damage, and self-similarity of the spall crack contour are determined.

Influence of a Gas-Filled Cavity of Complex Shape on Stresses in the Vicinity of a Neighboring Crack

We solve the problem of modeling of the stress-strain state in an infinite, elastic, isotropic body containing a crack and a gas-filled cavity of any shape by the boundary-element method. A system of six boundary integral equations for the components of displacements on the surface of the cavity and the jumps of displacements on the surface of the crack is obtained. We find the stress intensity factors on the contour of a circular plane crack depending on its location relative to the cavity, the shape of the cavity, and internal pressure in the cavity.

Finite Element Method for Numerical Analysis of Post-tension Anchorage Zone

Construction duration of cast in place segmental bridges can be accelerated by using rapid hardening concrete, so that the jacking force can be given at earlier age. Jacking force raise high concentration stress in pre-stressing tendon anchorage zone, so that stress and deformation of the anchorage zone should be analyzed to confirm that nothing crack happened. Finite element method is one of the solutions to analyze this case. This study concerned bridge of Lemah Ireng II at Semarang - Solo highway (3-spans, 2-Piers). The anchorage zone of a bridge segment was numerically modelled by using nonlinear finite element solid 3D using Abaqus. This study to get information of stress distribution and concrete crack indication in anchorage zones due to the age of concrete jacking variation that take in 0.5, 1, 1.5, 2, and 3 days. FEA analyze of anchorage zone conclude that based on the stiffness, stress and crack contour distribution of anchorage zone, jacking force to the tendon anchorage can be approved at one day of concrete age.