• Korean Journal of Construction Engineering and Management
• /
• v.25 no.2
• /
• pp.36-44
• /
• 2024

This paper presents the application of Convolutional Neural Networks (CNNs) and Region of Interest (ROI) techniques for concrete crack analysis. Surfaces of concrete structures, such as beams, etc., are exposed to fatigue stress and cyclic loads, typically resulting in the initiation of cracks at a microscopic level on the structure's surface. Early detection enables preventative measures to mitigate potential damage and failures. Conventional manual inspections often yield subpar results, especially for large-scale infrastructure where access is challenging and detecting cracks can be difficult. This paper presents data collection, edge segmentation and ROI techniques application, and analysis of concrete cracks using Convolutional Neural Networks. This paper aims to achieve the following objectives: Firstly, achieving improved accuracy in crack detection using image-based technology compared to traditional manual inspection methods. Secondly, developing an algorithm that utilizes enhanced Sobel edge segmentation and ROI techniques. The algorithm provides automated crack detection capabilities for non-destructive testing.

• 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.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.10a
• /
• pp.320-324
• /
• 2013

A crack identification method using an equivalent bending stiffness for cracked beam and committee of neural networks is presented. The equivalent bending stiffness is constructed based on an energy method for a straight thin-walled pipe, which has a through-the-thickness crack, subjected to bending. Several numerical analysis for a steel cantilever pipe using the equivalent bending stiffness are carried out to extract the natural frequencies and mode shapes of the cracked beam. The extracted modal properties are used in constructing a training patterns of a neural network. The input to the neural network consists of the modal properties and the output is composed of the crack location and size. Multiple neural networks are constructed and each individual network is trained independently with different initial synaptic weights. Then, the estimated crack locations and sizes from different neural networks are averaged. Experimental crack detection is carried out for 3 damage cases using the proposed method, and the identified crack locations and sizes agree reasonably well with the exact values.

• Steel and Composite Structures
• /
• v.32 no.3
• /
• pp.305-312
• /
• 2019

In this study, we investigated the effect of fatigue crack propagation of the beams which have a vital importance in engineering applications, on the natural frequency of the system. Beams which have a wide range of applications, are used as fundamental structural elements in engineering structures. Therefore, early detection of any damages in these structures is of vital importance for the prevention of possible destructive damages. One of the widely used methods of early detection of damages is the vibration analysis of the structure. Hence, it is of vital importance to detect and monitor any changes in the natural frequencies of the structure. From this standpoint, in this study we experimentally investigated the effect of fatigue crack propagation on beams produced from 4140 steel, of the natural frequency of the beam. A crack was opened on the $8{\times}16{\times}500mm$ beam using a 3 mm long and 0.25 mm wide wire erosion. The beam, then, underwent 3 point bending tests at 10 Hz with a dynamic fatigue device and its natural frequencies were measured in scheduled intervals and any changes taking place on the natural frequencies of the beam were measured. This data allowed us to identify and measure the crack occurring on the beam subjected to dynamic loading, during the propagation phase. This method produced experimental data. The experimental data showed that the natural frequency of the beam decreased with the propagation of the fatigue crack on the beam.

• Journal of the Society of Naval Architects of Korea
• /
• v.39 no.2
• /
• pp.19-27
• /
• 2002

The early damage detection of large structures is very important to prevent the disaster due to its global failure. In this paper, a crack detection method of the beam-analogy structure based on the wavelet transformation of mode shape is presented. The method can effectively detect the singularity of mode shape caused to the inconsistency of bending moment and shear force at the damaged part using the discrete wavelet of mode shape and its inverse transforms of detail components. To investigate the validity and the applicability of the presented damage detection method, numerical simulation and experiment are carried out for the idealized beam and the real ship structures.

• Journal of the Korean Society of Industry Convergence
• /
• v.10 no.1
• /
• pp.39-46
• /
• 2007

The objective of this paper is to examine the detection limit, growth characteristics and notch curvature radius in short crack problem. Measurement techniques such as ultrasonic method and back-face strain compliance method were adapted. The fatigue crack growth rate of the short crack is slower than that of a long crack for a notched specimen. The short crack is detected effectively by ultrasonic method. A short surface crack occurs in the middle of specimen thickness and is transient to a through crack when maximum crack depth is larger than the notch curvature radius.

• Smart Structures and Systems
• /
• v.33 no.4
• /
• pp.301-311
• /
• 2024

This paper proposes a deep convolutional long short-term memory (ConvLSTM)-based crack growth prediction technique for predictive maintenance of structures. Since cracks are one of the critical damage types in a structure, their regular inspection has been mandatory for structural safety and serviceability. To effectively establish the structural maintenance plan using the inspection results, crack propagation or growth prediction is essential. However, conventional crack prediction techniques based on mathematical models are not typically suitable for tracking complex nonlinear crack propagation mechanism on civil structures under harsh environmental conditions. To address the technical issue, a field data-driven crack growth prediction technique using ConvLSTM is newly proposed in this study. The proposed technique consists of the four steps: (1) time-series crack image acquisition, (2) target image stabilization, (3) deep learning-based crack detection and quantification and (4) crack growth prediction. The performance of the proposed technique is experimentally validated using a concrete mock-up specimen by applying step-wise bending loads to generate crack growth. The validation test results reveal the prediction accuracy of 94% on average compared with the ground truth obtained by field measurement.

• International Journal of Automotive Technology
• /
• v.3 no.4
• /
• pp.157-163
• /
• 2002

It is well recognized that the ultrasonic method is one of the most common and reliable nondestructive testing (NDT) methods for the quantitative estimation of defects in welded structures. However, NDT techniques applying for adhesively bonded joints have not been clearly established yet. In this paper, the detection of interface crack by the ultrasonic method was applied for the measurement of interfacial crack length in the adhesively bonded joints of double-cantilever beam (DCB). An optimal condition of transmission coefficients and experimental accuracy by the ultrasonic method in the adhesively bonded joints have been investigated and discussed. The experimental values are in good agreement with the computed results by boundary element method (BEM) and Ripling's equation.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.3
• /
• pp.415-423
• /
• 2001

In is well recognized that the ultrasonic method is one of the most common and reliable nondestructive testing(NDT) methods for the quantitative estimation of defects in welded structures. However, NDT techniques applying for adhesively bonded joints have not been clearly established yet. In this paper, the detection of interface crack by the ultrasonic method was applied for the measurement of interface crack length in the adhesively bonded joints of double-cantilever beam(DCB). The optimum condition of transmission coefficients and experimental accuracy by the ultrasonic method in the adhesively bonded joints have been investigated. The experimental values are in good agreement with the computed results by boundary element method(BEM) and Riplings equation.

• Proceedings of the KSME Conference
• /
• 2000.04a
• /
• pp.97-102
• /
• 2000

It is well recognized that the ultrasonic methods is one of the most common and reliable nondestructive testing(NDT) methods for the quantitative estimation of defects in welded structures. However, NDT techniques applying for adhesively bonded joints have not been clearly established yet. In this paper, the detection of interface crack by the ultrasonic method was applied for the measurement of interfacial crack length in the adhesively bonded joints of double-cantilever beam(DCB). The optimum condition of transmission coefficients in the adhesively bonded joints and it's experimental accuracy by the ultrasonic method have been investigated. The experimental values are in good agreement with the computed results by boundary element method(BEM) and Ripling's equation.