Support construction elements in civil engineering are usually made of reinforced concrete. Cracks in pre-stressed steel bar bundles, which can be induced by hydrogen, may critically diminish the safe load of bridges. Non-destructive testing methods are required that are capable of detecting cracks as early as possible. These defects progressively reduce the effective diameter of the steel bar bundle until complete breakage. Dependent on special requirements, verification by drilling or observation of crack growth is to be decided upon from non-destructive measurements.
Automatic crack detection is always a challenging task due to the influence of stains, shadows, complex texture, uneven illumination, blurring, and multiple scenes [2]. In the past decades, scholars have proposed a variety of image-based algorithms to automatically detect cracks on concrete surfaces and pavement. In the early studies, most of the methods are based on the combination or improvement of traditional digital image processing techniques (IPTs) [3], such as thresholding [4,5,6] and edge detection [7,8,9,10]. However, these methods are generally based on the significant assumption that the intensities of crack pixels are darker than the background and usually continuous, which makes these methods difficult to use effectively in the environment of complex background noise [11,12]. In order to improve the accuracy and integrity of crack detection, the methods based on wavelet transform [13,14] are proposed to lift the crack regions. However, due to the anisotropic characteristics of wavelets, they may not deal well with cracks with large curvatures or poor continuities [2].
Fusion 360 crack
Download File: https://tlniurl.com/2vCNIt
In recent studies, several minimal path methods [15,16] have also been used for crack detection. Although these methods make use of crack features in a global view [3] and achieve good performance, their main limitation is that seed points for path tracking need to be set in advance [17], and the calculation cost is too high for practical application.
Unet [32], as a typical representative of semantic segmentation algorithm, has achieved great success in medical image segmentation. There are many similarities between pavement crack detection and medical image segmentation, so it is natural to apply Unet to pavement crack segmentation.
The patchwise detection method, which divides the original pavement images into many small patches, is adopted by more researchers due to its two advantages. First, more data can be generated, and second, the localization information of cracks can be obtained. Zhang et al. [39] proposed a six-layer CNN network with four convolutional layers and two fully connected layers and used their convolutional neural network to train 99 99 3 small patches, which were split from 3264 2248 road images collected by low-cost smartphones. The output of the network was the probability of whether a small patch was a crack or not. Their study shows that deep CNNs are superior to traditional machine learning techniques, such as SVM and boosting methods, in detecting pavement cracks. Pauly et al. [40] used a self-designed CNN model to study the relationship between network depth and network accuracy and proved the effectiveness of using a deeper network to improve detection accuracy in pavement crack detection based on computer vision. In contrast with [39], which used the same number of convolution kernels in all convolution layers, Nguyen et al. [41] used a convolution neural network with an increased number of convolution kernels in each layer because the features were more generic in the early layers and more original dataset specific in later layers [42]. Eisenbach et al. [43] presented the GAPs dataset, constructed a CNN network with eight convolution layers and three full connection layers, and analyzed the effectiveness of the state-of-the-art regularization techniques. However, its network input size was 64 64 pixels, which was too small to provide enough context information. The same problem also existed in [44,45,46].
Zhang et al. put forward CrackNet [52], which is an earlier study on pixel-level crack detection based on CNN. The prominent feature of CrackNet is using a CNN model without a pooling layer to retain the spatial resolution. Fei et al. have upgraded it to Cracknet-V [53]. While CrackNet and its series versions perform well, they are primarily used for 3D road crack images, and their performances on two-dimensional (2D) road crack images have not been validated. Fan et al. [3] proposed a pixel-level structured prediction method using CNN with full connections (FC) layers, but it has the disadvantage that it requires a long inference time for testing.
The CFD dataset, published in [23], consists of 118 RGB images with a resolution of 480 320 pixels. All of the images were taken using an iPhone5 smartphone on the road in Beijing, China, and can roughly reflect the existing urban road conditions in Beijing. These crack images have uneven illumination and contain noise such as shadows, oil spots, and lane lines, and most cracks in these images are thin cracks, which make crack detection difficult. We randomly divided 70% of the dataset (82 images) for training and 30% of the dataset (36 images) for testing.
The Crack500 dataset, shared by Yang et al. in the literature [60], contains 500 original images with a resolution of 2560 1440 collected at the main campus of Temple University. Each original image was cropped into a non-overlapping image area of 640 360, resulting in 1896 training images, 348 validation images, and 1123 test images. These images are characterized by low contrast between cracks and background, as well as noise such as oil pollution and occlusions, which increase the difficulty of detection.
The DeepCrack dataset [2] contains 537 crack images, including both concrete pavement and asphalt pavement, with complex background and various crack widths, ranging from 1 pixel to 180 pixels. We kept the same data split as the original paper, with 300 images for training and 237 images for testing.
Figure 3 shows the crack detection results of six typical input images of our method and the three methods to be compared. The first column is the original input crack image, the second column is the label image corresponding to the first column image, and the next four columns are the predicted output images of the four comparison algorithms. As can be seen from Figure 3, all these algorithms could detect the rough crack profile. However, in terms of details, all three algorithms, FCN, Unet, and SegNet, had false detection and missing cracks resulting in discontinuity of cracks to a varying degree. Our algorithm was obviously better than the three algorithms, with the least false detection and missing cracks, and the closest to the ground truth.
Studies have shown that grain boundary chromium carbides improve the stress corrosion cracking (SCC) resistance of nickel based alloys exposed to high temperature, high purity water. However, thermal cycles from welding can significantly alter the microstructure of the base material near the fusion line. In particular, the heat of welding can solutionize grain boundary carbides and produce locally high residual stresses and strains, reducing the SCC resistance of the Alloy 600 type material in the heat affected zone (HAZ). Testing has shown that the SCC growth rate in Alloy 600 heat affected zone specimens can be 30x faster than observed in the Alloy 600 base material under identical testing conditions due to fewer intergranular chromium rich carbides and increased plastic strain in the HAZ.1, 2 Stress corrosion crack initiation tests were conducted on Alloy 600 HAZ specimens at 360C in hydrogenated, deaerated water to determine if these microstructural differences significantly affect the SCC initiation resistance of Alloy 600 heat affected zones compared to the Alloy 600 base material. Alloy 600 to EN82H to Alloy 600 HAZ specimens were fabricated from an Alloy 600 to Alloy 600 narrow groove weld with EN82H filler metal. The approximate middle third of the specimen gauge region was EN82H such that each specimen had two HAZ regions. Tests were conducted with in-situ monitored smooth tensile specimens under a constant load, and direct current electric potential drop was used for in-situ detection of SCC. Test results suggest that the SCC initiation resistance of Alloy 600 and its weld metal follows the following order: EN82H > Alloy 600 HAZ > Alloy 600. The high SCC initiation resistance observed to date in Alloy 600 heat affected zones compared to wrought Alloy 600 is unexpected based on the microstructure of HAZ versus wrought material and based on prior SCC growth rate studies. The observed behavior for the HAZ specimens is likely not related to differences in the environment, differences in stress/strain between the various specimen regions, differences in surface residual stress, or differences in the grain boundary microstructure of the various specimen regions (weld, HAZ, wrought). The behavior may be related to differences in the intragranular microstructure and creep resistance of the various weld regions or differences in the surface area of the various materials (weld, HAZ
Nickel-chromium-iron alloys exhibit intergranular stress corrosion cracking (SCC) at temperatures greater than 250C (480F) when exposed to high purity water. Studies have shown that grain boundary chromium carbides improve the SCC resistance of nickel based alloys exposed to high temperature, high purity water.3-9 However, thermal cycles from fusion welding can solutionize beneficial grain boundary carbides, produce locally high residual stresses and strains, and promote SCC in the heat affected zone (HAZ). Studies have shown that SCC growth rates in Alloy 600 heat affected zones are 30X faster than the Alloy 600 base material under the same test conditions.1, 2 The increased crack growth rate of the Alloy 600 HAZ relative to the base metal was attributed to fewer intergranular chromium rich carbides and to increased plastic strain in the HAZ. 2ff7e9595c
Comments