• Smart Structures and Systems
• /
• v.30 no.1
• /
• pp.17-34
• /
• 2022

For steel structures, fatigue cracks are critical damage induced by long-term cycle loading and distortion effects. Vision-based crack detection can be a solution to ensure structural integrity and performance by continuous monitoring and non-destructive assessment. A critical issue is to distinguish cracks from other features in captured images which possibly consist of complex backgrounds such as handwritings and marks, which were made to record crack patterns and lengths during periodic visual inspections. This study presents a parametric study on image-based crack identification for orthotropic steel bridge decks using captured images with complicated backgrounds. Firstly, a framework for vision-based crack segmentation using the atrous convolution-based Deeplapv3+ network (ACDN) is designed. Secondly, features on crack images are labeled to build three databanks by consideration of objects in the backgrounds. Thirdly, evaluation metrics computed from the trained ACDN models are utilized to evaluate the effects of obstacles on crack detection results. Finally, various training parameters, including image sizes, hyper-parameters, and the number of training images, are optimized for the ACDN model of crack detection. The result demonstrated that fatigue cracks could be identified by the trained ACDN models, and the accuracy of the crack-detection result was improved by optimizing the training parameters. It enables the applicability of the vision-based technique for early detecting tiny fatigue cracks in steel structures.

• Structural Monitoring and Maintenance
• /
• v.9 no.3
• /
• pp.289-303
• /
• 2022

In this study, the impact of assigned pixel labels on the accuracy of crack image identification of steel structures is examined by using an atrous separable convolution neural network (ASCNN). Firstly, images containing fatigue cracks collected from steel structures are classified into four datasets by assigning different pixel labels based on image features. Secondly, the DeepLab v3+ algorithm is used to determine optimal parameters of the ASCNN model by maximizing the average mean-intersection-over-union (mIoU) metric of the datasets. Thirdly, the ASCNN model is trained for various image sizes and hyper-parameters, such as the learning rule, learning rate, and epoch. The optimal parameters of the ASCNN model are determined based on the average mIoU metric. Finally, the trained ASCNN model is evaluated by using 10% untrained images. The result shows that the ASCNN model can segment cracks and other objects in the captured images with an average mIoU of 0.716.

• Smart Structures and Systems
• /
• v.31 no.1
• /
• pp.13-27
• /
• 2023

Fatigue crack is a fatal problem for steel structures. Early detection and maintenance can help extend the service life and prevent hazards. This paper presents the ultrasonic guided waves-based (UGWs-based) fatigue crack detection of a steel I-beam. The semi-analytical finite element model has been built to obtain the wave propagation characteristics. Damage indices in both time and frequency domains were analyzed by considering the characteristic variations of UGWs including the amplitude, phase angle, and wave packet energy. The pulse-echo and pitch-catch methods were combined in the detection scheme. Lab-scale experiments were conducted on welded steel I-beams to verify the proposed method. Results show that the damage indices based on the characteristic variations in the time domain can identify and localize the fatigue crack before it enters the rapid growth stage. The damage severity can be reasonably evaluated by analyzing the time-domain damage indices. Two nonlinear damage indices in the frequency domain give earlier warnings of the fatigue crack than the time-domain damage indices do. The identification results based on the above two nonlinear indices are found to be less consistent under various excitation frequencies. More robust nonlinear techniques needed to be searched and tested for early crack detection in steel I-beams in further study.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4A
• /
• pp.693-700
• /
• 2006

To detect and evaluate the damage present in bridge, static identification method is known to be simple and effective, compared to dynamic method. In this study, the damage detection method in steel box girder bridge using static responses including displacement, slope and curvature is examined. The static displacement is calculated using finite element analysis and the slope and curvature are determined from the displacement using central difference method. The location of damage is detected using the absolute differences of these responses in intact and damaged bridge. Steel box girder bridge with corner crack is modeled using singular element in finite element method. The results show that these responses were significantly useful in detecting and predicting the location of damage present in bridge.

• 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.28 no.3
• /
• pp.279-288
• /
• 2018

In this paper, a new method has been proposed to detect crack in beam structures under moving mass using regularized extreme learning machine. For this purpose, frequencies of beam under moving mass used as input to train machine. This data is acquired by the analysis of cracked structure applying the finite element method (FEM). Also, a validation study used for verification of the FEM. To evaluate performance of the presented method, a fixed simply supported beam and two span continuous beam are considered containing single or multi cracks. The obtained results indicated that this method can provide a reliable tool to accurately identify cracks in beam structures under moving mass.

• Structural Engineering and Mechanics
• /
• v.75 no.6
• /
• pp.723-736
• /
• 2020

In this paper, acoustic emission (AE) and pattern recognition are utilized to identify the AE signal signatures caused by propagation of stress corrosion cracking (SCC) in a 304 stainless steel plate. The surface of the plate is under almost uniform tensile stress at a notch. A corrosive environment is provided by exposing the notch to a solution of 1% Potassium Tetrathionate by weight. The Global b-value indicated an occurrence of the first visible crack and damage stages during the SCC. Furthermore, a method based on linear regression has been developed for damage identification using AE data.

• Structural Engineering and Mechanics
• /
• v.40 no.5
• /
• pp.719-743
• /
• 2011

A hybrid damage monitoring scheme using parallel acceleration-impedance approaches is proposed to detect girder damage and support damage in steel plate-girder bridges which are under ambient train-induced excitations. The hybrid scheme consists of three phases: global and local damage monitoring in parallel manner, damage occurrence alarming and local damage identification, and detailed damage estimation. In the first phase, damage occurrence in a structure is globally monitored by changes in vibration features and, at the same moment, damage occurrence in local critical members is monitored by changes in impedance features. In the second phase, the occurrence of damage is alarmed and the type of damage is locally identified by recognizing patterns of vibration and impedance features. In the final phase, the location and severity of the locally identified damage are estimated by using modal strain energy-based damage index methods. The feasibility of the proposed scheme is evaluated on a steel plate-girder bridge model which was experimentally tested under model train-induced excitations. Acceleration responses and electro-mechanical impedance signatures were measured for several damage scenarios of girder damage and support damage.