Crack Detection In Structures Research Articles

Bridging Convolutional Neural Networks and Transformers for Efficient Crack Detection in Concrete Building Structures.

Detecting cracks in building structures is an essential practice that ensures safety, promotes longevity, and maintains the economic value of the built environment. In the past, machine learning (ML) and deep learning (DL) techniques have been used to enhance classification accuracy. However, the conventional CNN (convolutional neural network) methods incur high computational costs owing to their extensive number of trainable parameters and tend to extract only high-dimensional shallow features that may not comprehensively represent crack characteristics. We proposed a novel convolution and composite attention transformer network (CCTNet) model to address these issues. CCTNet enhances crack identification by processing more input pixels and combining convolution channel attention with window-based self-attention mechanisms. This dual approach aims to leverage the localized feature extraction capabilities of CNNs with the global contextual understanding afforded by self-attention mechanisms. Additionally, we applied an improved cross-attention module within CCTNet to increase the interaction and integration of features across adjacent windows. The performance of CCTNet on the Historical Building Crack2019, SDTNET2018, and proposed DS3 has a precision of 98.60%, 98.93%, and 99.33%, respectively. Furthermore, the training validation loss of the proposed model is close to zero. In addition, the AUC (area under the curve) is 0.99 and 0.98 for the Historical Building Crack2019 and SDTNET2018, respectively. CCTNet not only outperforms existing methodologies but also sets a new standard for the accurate, efficient, and reliable detection of cracks in building structures.

A robust self-supervised approach for fine-grained crack detection in concrete structures

This work addresses a critical issue: the deterioration of concrete structures due to fine-grained cracks, which compromises their strength and longevity. To tackle this problem, experts have turned to computer vision (CV) based automated strategies, incorporating object detection and image segmentation techniques. Recent efforts have integrated complex techniques such as deep convolutional neural networks (DCNNs) and transformers for this task. However, these techniques encounter challenges in localizing fine-grained cracks. This paper presents a self-supervised 'you only look once' (SS-YOLO) approach that utilizes a YOLOv8 model. The novel methodology amalgamates different attention approaches and pseudo-labeling techniques, effectively addressing challenges in fine-grained crack detection and segmentation in concrete structures. It utilizes convolution block attention (CBAM) and Gaussian adaptive weight distribution multi-head self-attention (GAWD-MHSA) modules to accurately identify and segment fine-grained cracks in concrete buildings. Additionally, the assimilation of curriculum learning-based self-supervised pseudo-labeling (CL-SSPL) enhances the model's ability when applied to limited-size data. The efficacy and viability of the proposed approach are demonstrated through experimentation, results, and ablation analysis. Experimental results indicate a mean average precision (mAP) of at least 90.01%, an F1 score of 87%, and an intersection over union threshold greater than 85%. It is evident from the results that the proposed method yielded at least 2.62% and 4.40% improvement in mAP and F1 values, respectively, when tested on three diverse datasets. Moreover, the inference time taken per image is 2 ms less than that of the compared methods.

Numerical study on ultrasonic detection of cracks in metallic structures with variable cross-sectional thickness

The metal structures are widely used in aerospace engineering, especially in joints and spars. The safety of these parts is important to ensure the safe service of the whole structures. The ultrasonic wave is a traditional technique to detect cracks in metals. However, it is usually difficult to find all the cracks because of its difficulty in variable directions of the crack and the irregular shapes of the metals. This paper aims to address the challenge of detecting cracks in metallic structures with varying cross-sectional thicknesses using ultrasonic methods. The research investigates the behavior of ultrasonic longitudinal and transverse waves as they propagate through aluminum plates with variable cross sections. Additionally, it examines how cracks in different orientations influence these wave types. The theoretical analyses are performed which explore the reflection of oblique incidence waves and the diffraction of ultrasonic waves when they encounter semi-infinite cracks. Subsequently, numerical simulations are performed to validate the theoretical findings and to detect both horizontal and vertical cracks within metal plates of varying cross-sectional thicknesses. The findings indicate that both longitudinal and transverse waves are effective in identifying the location of damage caused by horizontal cracks. However, when it comes to vertical cracks, only transverse waves are successful in detecting their precise location. From the research of this paper, transverse ultrasonic wave is suggested to detect cracks in metal structures with irregular cross sections.

Crack detection and dimensional assessment using smartphone sensors and deep learning

This paper addresses the crucial need for effective crack detection and dimensional assessment in civil infrastructure materials to ensure safety and functionality. It proposes a cost-effective crack detection and dimensional assessment solution by applying state-of-the-art deep learning on smartphone sensor imagery and positioning data. The proposed methodology integrates three-dimensional (3D) data from LiDAR sensors with Mask R-convolutional neural network (CNN) and YOLOv8 object detection networks, for automated crack detection in concrete structures, allowing for accurate measurement of crack dimensions, including length, width, and area. The study finds that YOLOv8 produces superior precision and recall results in crack detection compared to Mask R-CNN. Furthermore, the calculated crack-straight-length closely aligns with the ground-truth straight-length, with an average error of 1.5%. These research contributions include developing a multi-modal solution combining LiDAR observations with image masks for precise 3D crack measurements, establishing a dimensional assessment pipeline to convert segmented cracks into measurements, and comparing state-of-the-art CNN-based networks for crack detection in real-life images.

A shallow 2D-CNN network for crack detection in concrete structures

PurposeThis study aims to obtain methods to identify and find the place of damage, which is one of the topics that has always been discussed in structural engineering. The cost of repairing and rehabilitating massive bridges and buildings is very high, highlighting the need to monitor the structures continuously. One way to track the structure's health is to check the cracks in the concrete. Meanwhile, the current methods of concrete crack detection have complex and heavy calculations.Design/methodology/approachThis paper presents a new lightweight architecture based on deep learning for crack classification in concrete structures. The proposed architecture was identified and classified in less time and with higher accuracy than other traditional and valid architectures in crack detection. This paper used a standard dataset to detect two-class and multi-class cracks.FindingsResults show that two images were recognized with 99.53% accuracy based on the proposed method, and multi-class images were classified with 91% accuracy. The low execution time of the proposed architecture compared to other valid architectures in deep learning on the same hardware platform. The use of Adam's optimizer in this research had better performance than other optimizers.Originality/valueThis paper presents a framework based on a lightweight convolutional neural network for nondestructive monitoring of structural health to optimize the calculation costs and reduce execution time in processing.

Portable Structure Surface Crack Detection System Based on Android Platform

Cracks, potholes, and other defects often occur on infrastructure such as bridges, among which cracks are one of the most frequent defects. They have diverse shapes and are difficult to detect. Traditional manual inspection methods are inefficient and have low accuracy, while automated inspection machines are bulky and inconvenient to carry and use. Based on the shortcomings of existing detection technologies, this paper proposes a portable structural surface crack detection system based on the Android platform using a portable handheld image acquisition device. The system captures cracks on the structure's surface and obtains high-definition crack images. Then, these images are transmitted to portable smartphone terminals through Wi-Fi. Next, the image is pre-processed using weighted averaging, grayscale linear transformation, and adaptive median filtering. Then, the improved Canny edge detection algorithm is applied to identify crack information, and the edge segmentation algorithm is used to determine the crack width. Finally, based on camera calibration, the pixels are converted into the length data required for actual measurement. The results show that the system is easy to operate, and it not only has crack storage and tracking functions, but also can effectively measure the crack width on the surface of components. The measurement accuracy of this system reaches the sub-pixel level, and in actual testing, compared with the crack width gauge, the maximum relative error does not exceed 6.25%.

Enhanced high-resolution structural crack detection using hybrid interacting Particle-Kalman filter

Monitoring the health of large-scale infrastructure with the required precision necessitates high-dimensional support models and extensive instrumentation. However, in a model-based structural health monitoring (SHM) framework, the ability to localize damage is constrained by the discretization of the model. To enhance the resolution of discretization, dense instrumentation is essential to address the inherent challenges in solving the inverse problem. Yet, increasing dimensionality can introduce detection delays, a critical concern in SHM. Additionally, addressing uncertainties stemming from the model, measurements, or external factors is crucial for reliable real-world SHM. This study focuses on localized damages, such as cracks, where detection precision is paramount. To tackle these challenges, this study proposes an innovative hybrid interacting Particle-Kalman filter (h-IPKF)-based SHM approach that surpasses model discretization limitations for detection resolution. This approach employs two distinct indices for crack localization: global (GDI) and local (LDI) damage indices. GDI identifies the affected element using a coarsely discretized predictor model, while LDI precisely pinpoints the crack location within the element. This paper represents the crack as a massless rotational spring with deteriorated stiffness (γ) and parameterizes it using GDI, LDI, and γ. Subsequently, the h-IPKF framework is employed to estimate the crack parameters, capable of handling both continuous and discrete random variables, which is advantageous for addressing discrete variables like GDI. Extensive numerical and real validation tests on beam structures were conducted to assess the algorithm’s sensitivity to noise and damage severity, demonstrating its efficiency, promptness, and precision in detecting cracks within structures.

Detection of a Submillimeter Notch-Type Defect at Multiple Orientations by a Lamb Wave A0 Mode at 550 kHz for Long-Range Structural Health Monitoring Applications.

The early detection of small cracks in large metal structures is a crucial requirement for the implementation of a structural health monitoring (SHM) system with a low transducers density. This work tackles the challenging problem of the early detection of submillimeter notch-type defects with a semielliptical shape and a groove at a constant width of 100 µm and 3 mm depth in a 4.1 mm thick aluminum plate. This defect is investigated with an ultrasonic guided wave (UGW) A0 mode at 550 kHz to investigate the long range in thick metal plates. The mode selection is obtained by interdigital transducers (IDTs) designed to operate with a 5 mm central wavelength. The novel contribution is the validation of the detection by pulse-echo and pitch and catch with UGW transducers to cover a distance up to 70 cm to reduce the transducers density. The analysis of scattering from this submillimeter defect at different orientations is carried out using simulations with a Finite Element Model (FEM). The detection of the defect is obtained by comparing the scattered signals from the defect with baseline signals of the pristine laminate. Finally, the paper shows that the simulated results are in good agreement with the experimental ones, demonstrating the possible implementation in an SHM system based on the efficient propagation of an antisymmetric mode by IDTs.

Automatic high-precision crack detection of post-earthquake structure based on self-supervised transfer learning method and SegCrackFormer

Accurate crack detection is essential for structural damage assessment after earthquake disasters. However, due to the gap between the target domain of the detected structure and the source domain, it is challenging to achieve high-precision crack segmentation when performing crack detection based on deep learning (DL) in actual engineering. This article proposes a crack segmentation transfer learning method based on a self-supervised learning mechanism and a high-quality pseudo-label generation method, which can significantly improve the detection accuracy in the target domain without pre-made annotations. Besides, to improve the crack segmentation model’s ability to extract local and global features, this article proposes a SegCrackFormer model, which embeds convolutional layers and multi-head self-attention modules. An experiment of the crack segmentation transfer learning method is performed on two open-source crack datasets, METU and Crack500, and a newly proposed LD dataset. The experimental results show that the crack segmentation transfer learning method proposed in this article can improve the mean intersection over union (mIoU) by 38.41% and 15.66% on the Crack500 and LD datasets, respectively. The proposed SegCrackFormer is evaluated through comparative experiments, which demonstrate its superiority over existing crack segmentation models on the METU dataset. Additionally, the proposed method is shown to require significantly less computational resources than other existing models, which highlights the potential of SegCrackFormer as a powerful and efficient model for crack segmentation in practical applications.

Real-time structural crack detection in buildings using YOLOv3 and autonomous unmanned aerial systems

Real-time structural crack detection in buildings using YOLOv3 and autonomous unmanned aerial systems

Crack detection in historic structures using an improved Prewitt filter: Case study of the Historic Si-o-se-pol Bridge in Iran

In contrast to new and modern structures, historical structures have cultural significance, and it is essential to make an effort to preserve them. For this purpose, fast and accurate damage detection of historical structures plays a crucial role. Thus, the current study introduces a novel and effective tool for detecting cracks in historic structures. A new and modified version of the Prewitt filter is proposed to detect cracks in the Si-o-se-pol Bridge, a historic bridge in Iran. Results of crack detection using vertical and horizontal Prewitt filters are compared to those obtained from the proposed improved filter. The findings show that the improved Prewitt filter has significantly better performance compared to the vertical and horizontal Prewitt filters.

Autonomous Identification of Bridge Concrete Cracks Using Unmanned Aircraft Images and Improved Lightweight Deep Convolutional Networks

The identification of the development of structural defects is an important part of bridge structure damage diagnosis, and cracks are considered the most typical and highly dangerous structural disease. However, existing deep learning-based methods are mostly aimed at the scene of concrete cracks, while they rarely focus on designing network architectures to improve the vision-based model performance from the perspective of unmanned aircraft system (UAS) inspection, which leads to a lack of specificity. Because of this, this study proposes a novel lightweight deep convolutional neural network-based crack pixel-level segmentation network for UAS-based inspection scenes. Firstly, the classical encoder-decoder architecture UNET is utilized as the base model for bridge structural crack identification, and the hourglass-shaped depthwise separable convolution is introduced to replace the traditional convolutional operation in the UNET model to reduce model parameters. Then, a kind of lightweight and efficient channel attention module is used to improve model feature fuzzy ability and segmentation accuracy. We conducted a series of experiments on bridge structural crack detection tasks by utilizing a long-span bridge as the research item. The experimental results show that the constructed method achieves an effective balance between reasoning accuracy and efficiency with the value of 97.62% precision, 97.23% recall, 97.42% accuracy, and 93.25% IOU on the bridge concrete crack datasets, which are significantly higher than those of other state-of-the-art baseline methods. It can be inferred that the application of hourglass-shaped depth-separable volumes can actively reduce basic model parameters. Moreover, the lightweight and efficient attention modules can achieve local cross-channel interaction without dimensionality reduction and improve the network segmentation performance.

An Ensemble Approach for Robust Automated Crack Detection and Segmentation in Concrete Structures.

To prevent potential instability the early detection of cracks is imperative due to the prevalent use of concrete in critical infrastructure. Automated techniques leveraging artificial intelligence, machine learning, and deep learning as the traditional manual inspection methods are time-consuming. The existing automated concrete crack detection algorithms, despite recent advancements, face challenges in robustness, particularly in precise crack detection amidst complex backgrounds and visual distractions, while also maintaining low inference times. Therefore, this paper introduces a novel ensemble mechanism based on multiple quantized You Only Look Once version 8 (YOLOv8) models for the detection and segmentation of cracks in concrete structures. The proposed model is tested on different concrete crack datasets yielding enhanced segmentation results with at least 89.62% precision and intersection over a union score of 0.88. Moreover, the inference time per image is reduced to 27 milliseconds which is at least a 5% improvement over other models in the comparison. This is achieved by amalgamating the predictions of the trained models to calculate the final segmentation mask. The noteworthy contributions of this work encompass the creation of a model with low inference time, an ensemble mechanism for robust crack segmentation, and the enhancement of the learning capabilities of crack detection models. The fast inference time of the model renders it appropriate for real-time applications, effectively tackling challenges in infrastructure maintenance and safety.

Bayesian-optimized unsupervised semantic segmentation model for structural crack detection

To reduce the reliance of existing mainstream vision-based crack detection algorithms on annotated datasets, this paper presents an unsupervised semantic segmentation-based approach. The proposed method first employs the Felzenszwalb-Huttenlocher algorithm for pre-segmenting the image, generating superpixels. Subsequently, a with an autoencoder model is designed to progressively approximate the superpixel segmentation results, and the optimal model is obtained by Bayesian optimization. Through comparative experiments with existing algorithms, it has been demonstrated that the proposed method performance comparable to supervised algorithms, even without the need for labeled data. As a result, the deployment complexity of the algorithm is significantly reduced, while expanding its applicability.

Deep-Learning- and Unmanned Aerial Vehicle-Based Structural Crack Detection in Concrete

Deep-learning- and unmanned aerial vehicle (UAV)-based methods facilitate structural crack detection for tall structures. However, contemporary datasets are generally established using images taken with handheld or vehicle-mounted cameras. Thus, these images might be different from those taken by UAVs in terms of resolution and lighting conditions. Considering the difficulty and complexity of establishing a crack image dataset, making full use of the current datasets can help reduce the shortage of UAV-based crack image datasets. Therefore, the performance evaluation of existing crack image datasets in training deep neural networks (DNNs) for crack detection in UAV images is essential. In this study, four DNNs were trained with different architectures based on a publicly available dataset and tested using a small UAV-based crack image dataset with 648 +pixel-wise annotated images. These DNNs were first tested using the four indices of precision, recall, mIoU, and F1, and image tests were also conducted for intuitive comparison. Moreover, a field experiment was carried out to verify the performance of the trained DNNs in detecting cracks from raw UAV structural images. The results indicate that the existing dataset can be useful to train DNNs for crack detection from UAV images; the TransUNet achieved the best performance in detecting all kinds of structural cracks.

Crack detection of masonry structure based on thermal and visible image fusion and semantic segmentation

The integration of visible and thermal images has demonstrated the potential ability to enhance crack segmentation accuracy. However, due to the intricate texture of masonry structures and the challenges posed in precisely aligning these cross-modality images, it is necessary to explore pixel-level alignment and develop a comprehensive dataset to enable deep-learning based methods. Therefore, a dataset, Crack900, including five image types, is developed together with a proposed two-step registration to achieve highly accurate pixel-level alignment. In addition, both Train from Scratch and Transfer Learning (TL) strategies are applied on eleven models to investigate the impact of different fused image types. Our findings reveal that the concatenation strategy markedly improves segmentation accuracy, and the performance of TL depends on the compatibility of channel numbers and domain difference between pre-trained and target models. These findings pave the way for further development of cross-modality in masonry crack segmentation methodologies for structural health monitorin.

On using the DFOS for damage identification in civil engineering structures

AbstractThe application of distributed fiber optic sensing (DFOS) technologies to the monitoring of civil engineering structures has been widely developed in recent years. In particular, fiber optic sensing (FOS) using the Rayleigh backscattering phenomenon of the laser frequency spectrum has been used to continuously measure strain along the fiber optic sensor with high spatial resolution. However, the practical implementation of fiber optic sensorsin the field is still a challenge. These include, but are not limited to, the bonding between fiber sensor cables and the surrounding medium, the practical way in which fiber optic sensors can be installed in concrete structures, and the analysis of crack width using the strain distribution along the fiber. Compared to classical discrete sensors, the DFOS has a great potential to detect, localize and quantify crack formation even in the early stages of microcracking. This paper discusses the potential and challenges of using distributed fiber optic sensors for crack detection in concrete structures. In this sense, different types of mechanical tests on concrete structures using different fiber optic sensors, and different bonding techniques are presented to explore the possibilities of crack detection in concrete structures and its potential for practical structural health monitoring (SHM) systems of civil structures.

Detection of cracks in aircraft structures using digital image processing technology

Full-scale aircraft structural fatigue testing exposes structural weaknesses by simulating the use of the aircraft in service and monitoring the development and expansion of fatigue cracks to guide the optimisation of aircraft structural design, the determination of service life and the development of maintenance and repair programmes. If crack damage is not detected in time, the uncontrolled expansion of the crack may lead to structural damage and prolong the test cycle. Therefore, it is crucial to achieve accurate detection of early cracks in fatigue testing of aircraft structures. Digital image technology is a new technology supported by a number of technical and theoretical achievements. In practical application, it relies on the support of computer functions, by converting image information into two-dimensional digital signals, thus realising various operations. In this paper, digital image processing techniques are used to deepen the backbone feature extraction network structure and improve the prediction scale of small targets, thus improving the performance of the model in terms of feature extraction and small defect detection. Experimental results show that the method can achieve accurate detection of small cracks, providing an effective technical approach for the automatic detection of cracks in aircraft structural fatigue tests. The technique of detecting cracks in aircraft structures using digital image processing also provides a new idea for research into improving aircraft endurance testing, which can be further developed with the aid of image technology.

A novel criterion for crack identification in beam-like structures using distributed piezoelectric sensor and controlled moving load

The present study addresses the problem of crack identification in beam-like structures using a distributed piezoelectric sensor and controlled moving load. First, governing equations for the vibration of a cracked Timoshenko beam integrated with a piezoelectric layer and subjected to a moving load are established and their solution in the frequency domain is derived and acknowledged as electro-mechanical response of the beam. Then, variation of the electro-mechanical frequency response is examined versus crack and moving load parameters with the aim to propose a novel indicator, called herein spectral assurance criterion, for crack detection in beam-like structures. Finally, a procedure is developed for crack identification from moving load-induced frequency response measured by the distributed piezoelectric sensor based on the proposed spectral assurance criterion. The numerical analysis demonstrates that (a) the piezoelectric layer can be used as a distributed sensor for reliably measuring the mechanical response of beam subjected to moving load; (b) the speed-controlled moving harmonic force is a useful tool for exciting a beam-like structure for its health monitoring purpose and (c) the proposed spectral assurance criterion is actually a novel and efficient indicator for crack identification in beam-like structures.

Weakly-supervised structural surface crack detection algorithm based on class activation map and superpixel segmentation

This paper proposes a weakly-supervised structural surface crack detection algorithm that can detect the crack area in an image with low data labeling cost. The algorithm consists of a convolutional neural networks Vgg16-Crack for classification, an improved and optimized class activation map (CAM) algorithm for accurately reflecting the position and distribution of cracks in the image, and a method that combines superpixel segmentation algorithm simple linear iterative clustering (SLIC) with CAM for more accurate semantic segmentation of cracks. In addition, this paper uses Bayesian optimization algorithm to obtain the optimal parameter combination that maximizes the performance of the model. The test results show that the algorithm only requires image-level labeling, which can effectively reduce the labor and material consumption brought by pixel-level labeling while ensuring accuracy.