• Journal of the Korean Society of Safety
• /
• v.34 no.6
• /
• pp.50-57
• /
• 2019

In this study, various types of deep learning models that have been proposed recently are classified according to data input / output types and analyzed to find the deep learning model suitable for constructing a crack detection model. First the deep learning models are classified into image classification model, object segmentation model, object detection model, and instance segmentation model. ResNet-101, DeepLab V2, Faster R-CNN, and Mask R-CNN were selected as representative deep learning model of each type. For the comparison, ResNet-101 was implemented for all the types of deep learning model as a backbone network which serves as a main feature extractor. The four types of deep learning models were trained with 500 crack images taken from real concrete structures and collected from the Internet. The four types of deep learning models showed high accuracy above 94% during the training. Comparative evaluation was conducted using 40 images taken from real concrete structures. The performance of each type of deep learning model was measured using precision and recall. In the experimental result, Mask R-CNN, an instance segmentation deep learning model showed the highest precision and recall on crack detection. Qualitative analysis also shows that Mask R-CNN could detect crack shapes most similarly to the real crack shapes.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.9
• /
• pp.194-200
• /
• 2013

In this paper, we propose a multi-scale crack detection method using scaling. It is based on morphology algorithm, crack features, and scaling. We use a morphology operator which extracts patterns of crack. It segments cracks and background using opening and closing operations. Morphology based segmentation is better than existing integration methods using subtraction in detecting a crack it has small width. However, morphology methods using only one structure element could detect only fixed width crack. Thus, we use a scaling method. We use bilinear interpolation for scaling. Our method calculates values of properties such as the number of pixels and the maximum length of the segmented region. We decide whether the segmented region belongs to cracks according to those data. Experimental results show that our proposed multi-scale crack detection method has better results than those of existing detection methods.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.9
• /
• pp.935-942
• /
• 2009

In this paper, the purpose is to investigate the natural frequency of a cracked Timoshenko cantilever beams by FEM(finite element method) and experiment. In addition, a method for detection of crack in a cantilever beams is presented based on natural frequency measurements. The governing differential equations of a Timoshenko beam are derived via Hamilton's principle. The two coupled governing differential equations are reduced to one fourth order ordinary differential equation in terms of the flexural displacement. The crack is assumed to be in the first mode of fracture and to be always opened during the vibrations. The detection method of a crack location in a beam based on the frequency measurements is extended here to Timoshenko beams, taking the effects of both the shear deformation and the rotational inertia into account. The differences between the actual and predicted crack positions and sizes are less than 6 % and 23 % respectively.

• Composites Research
• /
• v.22 no.1
• /
• pp.9-14
• /
• 2009

This paper suggested the electric potential method with a bridge circuit concept for the detection of the location and crack growth of carbon fiber reinforced composites to reduce the measurement numbers. 2 pairs of electrodes were fabricated on the center cracked thin composite plates, and potential changes at one pair of adjacent electrodes were observed while external voltage input was applied to the other pair of adjacent electrodes. The effects of the size and interval of electrodes, location and propagating direction of center cracks were investigated by experiments and finite element analyses. Detectable crack size was influenced by the electrode interval rather than the electrode size, and crack detection was enhanced as the size and interval of electrodes were smaller. Besides, output potential changes were larger as the crack grew and was nearer the voltage input electrodes.

• Smart Structures and Systems
• /
• v.32 no.4
• /
• pp.219-233
• /
• 2023

Crack width is an important indicator to evaluate the health condition of the concrete structure. The crack width is measured by manual using crack width gauge commonly, which is time-consuming and laborious. In this paper, we have proposed a fast and simplified crack width quantification method via deep Q learning and geometric calculation. Firstly, the crack edge is extracted by using U-Net network and edge detection operator. Then, the intelligent decision of is made by the deep Q learning model. Further, the geometric calculation method based on endpoint and curvature extreme point detection is proposed. Finally, a case study is carried out to demonstrate the effectiveness of the proposed method, achieving high precision in the real crack width quantification.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Journal of Biosystems Engineering
• /
• v.23 no.1
• /
• pp.67-74
• /
• 1998

A nondestructive quality inspection technique using acoustic impulse response method was developed for eggshell inspection. An experimental system was built to generate the impact force, to measure the response signal and to analyze the frequency spectrum. This system includes an impulse generating unit, an egg holding seal a microphone with preamplifier, and a DSP board installed on Personal Computer. A simple algorithm .was developed for crack detection. Using the developed system with algorithm, crack detection ability was evaluated and the error rate to estimate the normal egg as cracked was found to be 4% and the error rate to estimate the cracked egg as normal was also found to be 4%. This system could be adopted in industry with some modification.

• Structural Engineering and Mechanics
• /
• v.91 no.2
• /
• pp.163-175
• /
• 2024

The objective of this research is to improve public safety in civil engineering by recognizing fractures in concrete structures quickly and correctly. The study offers a new crack detection method based on advanced image processing and machine learning techniques, specifically transfer learning with convolutional neural networks (CNNs). Four pre-trained models (VGG16, AlexNet, ResNet18, and DenseNet161) were fine-tuned to detect fractures in concrete surfaces. These models constantly produced accuracy rates greater than 80%, showing their ability to automate fracture identification and potentially reduce structural failure costs. Furthermore, the study expands its scope beyond crack detection to identify concrete health, using a dataset with a wide range of surface defects and anomalies including cracks. Notably, using VGG16, which was chosen as the most effective network architecture from the first phase, the study achieves excellent accuracy in classifying concrete health, demonstrating the model's satisfactorily performance even in more complex scenarios.

• Structural Monitoring and Maintenance
• /
• v.1 no.3
• /
• pp.309-322
• /
• 2014

Detection of fatigue cracks at an early stage of their development is important in structural health monitoring. The breathing of cracks in a structure generates higher harmonic components of the exciting frequency in the frequency spectrum. Previously, the residual operational deflection shape (R-ODS) method was successfully applied to beams with a single crack. The method is based on the ODSs at the exciting frequency and its higher harmonic components which consider both amplitude and phase information of responses to map the deflection pattern of structures. Although the R-ODS method shows the location of a single crack clearly, its identification for the location of multiple cracks in a structure is not always obvious. Therefore, an improvement to the R-ODS method is presented here to make the identification process distinct for the beams with multiple cracks. Numerical and experimental examples are utilised to investigate the effectiveness of the improved method.

• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.779-789
• /
• 2021

Cracks in railway sleeper are an inevitable condition and has a significant influence on the safety of railway system. Although the technology of railway sleeper condition monitoring using machine learning (ML) models has been widely applied, the crack recognition accuracy is still in need of improvement. In this paper, a two-stage method using edge detection and convolutional neural network (CNN) is proposed to reduce the burden of computing for detecting cracks in railway sleepers with high accuracy. In the first stage, the edge detection is carried out by using the 3×3 neighborhood range algorithm to find out the possible crack areas, and a series of mathematical morphology operations are further used to eliminate the influence of noise targets to the edge detection results. In the second stage, a CNN model is employed to classify the results of edge detection. Through the analysis of abundant images of sleepers with cracks, it is proved that the cracks detected by the neighborhood range algorithm are superior to those detected by Sobel and Canny algorithms, which can be classified by proposed CNN model with high accuracy.