• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.36 no.3
• /
• pp.113-120
• /
• 2020

The purpose of this study is to compare the models of Deep Learning-based Convolution Neural Network(CNN) for concrete crack detection. The comparison models are AlexNet, GoogLeNet, VGG16, VGG19, ResNet-18, ResNet-50, ResNet-101, and SqueezeNet which won ImageNet Large Scale Visual Recognition Challenge(ILSVRC). To train, validate and test these models, we constructed 3000 training data and 12000 validation data with 256×256 pixel resolution consisting of cracked and non-cracked images, and constructed 5 test data with 4160×3120 pixel resolution consisting of concrete images with crack. In order to increase the efficiency of the training, transfer learning was performed by taking the weight from the pre-trained network supported by MATLAB. From the trained network, the validation data is classified into crack image and non-crack image, yielding True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), and 6 performance indicators, False Negative Rate (FNR), False Positive Rate (FPR), Error Rate, Recall, Precision, Accuracy were calculated. The test image was scanned twice with a sliding window of 256×256 pixel resolution to classify the cracks, resulting in a crack map. From the comparison of the performance indicators and the crack map, it was concluded that VGG16 and VGG19 were the most suitable for detecting concrete cracks.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.5
• /
• pp.611-617
• /
• 2018

The application of health monitoring, including a fault detection technique, is needed to secure the structural safety of large structures. A 2-step crack identification method for detecting the crack location and size of the beam structure is presented. First, a crack occurrence region was estimated using the modified Laplacian operator for the strain mode shape obtained from the distributed local strain data. The crack location and size were then identified based on the natural frequencies obtained from the acceleration data and the neural network technique for the pre-estimated crack occurrence region. The natural frequencies of a cracked beam were calculated based on an equivalent bending stiffness induced by the energy method, and used to generate the training patterns of the neural network. An experimental study was carried out on an aluminum cantilever beam to verify the present method for crack identification. Cracks were produced on the beam, and free vibration tests were performed. A crack occurrence region was estimated using the modified Laplacian operator for the strain mode shape, and the crack location and size were assessed using the natural frequencies and neural network technique. The identified crack occurrence region agrees well with the exact one, and the accuracy of the estimation results for the crack location and size could be enhanced considerably for 3 damage cases. The presented method could be applied effectively to the structural health monitoring of large structures.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.12
• /
• pp.2062-2069
• /
• 2001

It has been established that a crack has an important effect on the dynamic behavior of a structure. This effect depends mainly on the location and depth of the crack. To identify the location and depth of a crack in a structure, a method is presented in this paper which uses synthetic artificial intelligent technique, that is, Adaptive-Network-based Fuzzy Inference System(ANFIS) solved via hybrid learning algorithm(the back-propagation gradient descent and the least-squares method) are used to learn the input(the location and depth of a crack)-output(the structural eigenfrequencies) relation of the structural system. With this ANFIS and a continuous evolutionary algorithm(CEA), it is possible to formulate the inverse problem. CEAs based on genetic algorithms work efficiently for continuous search space optimization problems like a parameter identification problem. With this ANFIS, CEAs are used to identify the crack location and depth minimizing the difference from the measured frequencies. We have tried this new idea on a simple beam structure and the results are promising.

• Proceedings of the KSME Conference
• /
• 2001.06c
• /
• pp.182-188
• /
• 2001

It has been established that a crack has an important effect on the dynamic behavior of a structure. This effect depends mainly on the location and depth of the crack. To identify the location and depth of a crack in a structure, a method is presented in this paper which uses synthetic artificial intelligent technique, that is, Adaptive-Network-based Fuzzy Inference System(ANFIS) solved via hybrid learning algorithm(the back-propagation gradient descent and the least-squares method) are used to learn the input(the location and depth of a crack)-output(the structural eigenfrequencies) relation of the structural system. With this ANFIS and a continuous evolutionary algorithm(CEA), it is possible to formulate the inverse problem. CEAs based on genetic algorithms work efficiently for continuous search space optimization problems like a parameter identification problem. With this ANFIS, CEAs are used to identify the crack location and depth minimizing the difference from the measured frequencies. We have tried this new idea on a simple beam structure and the results are promising.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.77-82
• /
• 2007

In this paper, we proposed the image processing techniques for extracting the cracks in a concrete surface crack image and the enhanced Max-Min neural network for recognizing the directions of the extracted cracks. The image processing techniques used are the closing operation or morphological techniques, the Sobel masking for extracting for edges of the cracks, and the iterated binarization for acquiring the binarized image from the crack image. The cracks are extracted from the concrete surface image after applying two times of noise reduction to the binarized image. We proposed the method for automatically recognizing the directions of the cracks with the enhanced Max-Min neural network. Also, we propose an enhanced Max-Min neural network by auto-tuning of learning rate using delta-bar-delta algorithm. The experiments using real concrete crack images showed that the cracks in the concrete crack images were effectively extracted and the enhanced Max-Min neural network was effective in the recognition of direction of the extracted cracks.

• Korean Journal of Construction Engineering and Management
• /
• v.5 no.2 s.18
• /
• pp.90-105
• /
• 2004

Machines for crack sealing automation have been continually developed since the early 1990's because of the effectiveness of crack sealing that would be able to improve safety, quality and productivity. It has been considered challenging problem to detect crack network in pavement which includes noise (oil marks, skid marks, previously sealed cracks and inherent noise). Moreover, it is required to develop crack network mapping and modeling algorithm in order to accurately inject sealant along to the middle of cut crack network. The primary objective of this study is to propose machine vision algorithms (digital image processing algorithm and path planning algorithm) for fully automated pavement crack sealing. It is anticipated that the effective use of the proposed machine vision algorithms would be able to reduce error rate in image processing for detecting, mapping and modeling crack network as well as improving quality and productivity compared to existing vision algorithms.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

• Journal of the Korean Society of Safety
• /
• v.28 no.6
• /
• pp.57-63
• /
• 2013

This paper discusses 2D models of beams for simulating the fracture of brittle materials. A simulation of an experiment on a concrete beam subjected to bending, in which two overlapping cracks occur, is used to study the effect of individual beam characteristics and different arrangements of the beams in the overall network mesh. It was found that any regular orientation of the beams influences the resulting crack patterns. Methods to implement a wide range of poisson's ratios are also developed, the use of the mesh to study arbitrary micro-structures is outlined. The crack pattern that are obtained with mesh are in good agreement with the experimental results. Also, numerical simulations of the tests were performed by means of a model, and non-integer dimensions were measured on the predicted mesh damage patterns.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.2
• /
• pp.173-182
• /
• 2007

Cracks in concrete structures should be measured to periodically assess potential problems in durability and serviceability. Conventional crack measurement systems depend on visual inspections and manual measurements of the crack features such as width, length, and direction using microscope and crack gage. However, conventional methods take long time as well as manpower, and lack quantitative objectivity resulted by inspectors. In this study, an evaluation technique for concrete surface cracks is developed using image processing and artificial neural network. Developed technique consists of three major parts: (1) crack detection (2) crack analysis and (3) pattern recognition. To examine validity of the technique developed in this study, crack analyzing tests were performed on the images obtained from various types of concrete surface cracks. The test results revealed that the system is highly effective in automatically analyzing concrete surface cracks in terms of features and patterns of cracks.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2022

In this paper, we propose a vector-based augmentation technique that can generate data required for crack detection and a ConvNet(Convolutional Neural Network) technique that can learn it. Detecting cracks quickly and accurately is an important technology to prevent building collapse and fall accidents in advance. In order to solve this problem with artificial intelligence, it is essential to obtain a large amount of data, but it is difficult to obtain a large amount of crack data because the situation for obtaining an actual crack image is mostly dangerous. This problem of database construction can be alleviated with elastic distortion, which increases the amount of data by applying deformation to a specific artificial part. In this paper, the improved crack pattern results are modeled using ConvNet. Rather than elastic distortion, our method can obtain results similar to the actual crack pattern. By designing the crack data augmentation based on a vector, rather than the pixel unit used in general data augmentation, excellent results can be obtained in terms of the amount of crack change. As a result, in this paper, even though a small number of crack data were used as input, a crack database can be efficiently constructed by generating various crack directions and patterns.