Crack Detection Research Articles

Evaluation of the Degree of Degradation of Brake Pad Friction Surfaces Using Image Processing

The improvement of drilling rig systems to ensure a reduction in unproductive time spent on lowering and lifting operations for replacing drilling tools and restoring the performance of drilling equipment units is an important task. At the same time, considerable attention is paid to the reliable and efficient operation of the braking systems of drilling rig winches. In the process of operation, the polymer pads periodically come into contact with the outer cylindrical surface of the metal pulley during braking, work in extreme conditions and wear out intensively, so they need periodic replacement. Tests were carried out on a modernized stand and in industrial conditions for the brakes of drilling winches. A methodology for evaluating the degradation of the brake pad friction surface during its operation is proposed. The assessment of the degradation degree is carried out based on the image of the brake pad surface using image processing techniques. Geometric transformations of the input image were performed to avoid perspective distortions caused by the concave shape of the brake pads and the spatial angle at which the image is acquired to avoid glares. The crack detection step was implemented based on the scale-space theory, followed by contour detection and skeletonization. The ratios of the area and perimeter of segmented and skeletonized cracks to the total area were chosen as integral characteristics of the degradation degree. With the help of scanning electron microscopy, the character of the destruction of the friction surface and the degradation of the polymer material was investigated. Experimental studies were performed, and the application of the proposed method is illustrated.

Real-time detection of surface cracking defects for large-sized stamped parts

This study presents a framework for the real-time detection of surface cracking in large-sized stamped metal parts. The framework aims to address the challenges of low detection efficiency and high error rates associated with manual cracking detection. Within this framework, a novel network, SNF-YOLOv8, is proposed to efficiently detect cracking while ensuring that the detection speed matches the production speed. The network incorporates a convolutional spatial-to-depth module to enhance the detection of small-sized cracking and mitigate surface interference during inspections. Furthermore, a visual self-attention mechanism is introduced to improve feature extraction. A combination of standard convolutional and depth-wise separable convolutional layers in the neck network enhances speed without compromising accuracy. Experimental validation conducted using a dataset from actual production lines, in collaboration with a multi-national corporation, demonstrates that SNF-YOLOv8 achieves an average precision of 85.2% at a detection speed of 164 frames per second. The framework achieves an accuracy rate of 98.8% in detecting large-sized cracking and 96.4% in detecting small-sized cracking, meeting the requirements for high-precision and real-time detection applications.

Automated crack detection of train rivets using fluorescent magnetic particle inspection and instance segmentation

The railway rivet is one of the most important and easily damaged parts of the connection. If rivets develop cracks during the production process, their load-bearing capacity will be reduced, thereby increasing the risk of failure. Fluorescent magnetic particle flaw detection (FMPFD) is a widely used inspection method for train fasteners. Manual inspection is not only time-consuming but also prone to miss detection, therefore intelligent detection system has important application value. However, the fluorescent crack images obtained by FMPFD present challenges for intelligent detection, such as the dense, multi-scaled and uninstantiated cracks. In addition, there is limited research on fluorescent rivet crack detection. This paper adopts instance segmentation to achieve automatic cracks detection of rivets. A decentralized target center and low overlap rate labeling method is proposed, and a Gaussian-weighted correction post-processing method is introduced to improve the recall rate in the areas of dense cracks. An efficient channel spatial attention mechanism for feature extraction is proposed in order to enhance the detection of multi-scale cracks. For uninstantiated cracks, an improvement of crack detection in uninstantiated regions based on multi task feature learning is proposed, thoroughly utilizing the semantic and spatial features of the fluorescent cracks. The experimental results show that the improved methods are better than the baseline and some cutting-edge algorithms, achieving a recall rate and mAP0.5 of 86.4% and 90.3%. In addition, a single coil non-contact train rivet composite magnetization device is built for rivets that can magnetize different shapes of rivets and has universality.

Vison Transformer-Based Automatic Crack Detection on Dam Surface

Dam is an essential structure in hydraulic engineering, and its surface cracks pose significant threats to its integrity, impermeability, and durability. Automated crack detection methods based on computer vision offer substantial advantages over manual approaches with regard to efficiency, objectivity and precision. However, current methods face challenges such as misidentification, discontinuity, and loss of details when analyzing real-world dam crack images. These images often exhibit characteristics such as low contrast, complex backgrounds, and diverse crack morphologies. To address the above challenges, this paper presents a pure Vision Transformer (ViT)-based dam crack segmentation network (DCST-net). The DCST-net utilizes an improved Swin Transformer (SwinT) block as the fundamental block for enhancing the long-range dependencies within a SegNet-like encoder–decoder structure. Additionally, we employ a weighted attention block to facilitate side fusion between the symmetric pair of encoder and decoder in each stage to sharpen the edge of crack. To demonstrate the superior performance of our proposed method, six semantic segmentation models have been trained and tested on both a self-built dam crack dataset and two publicly available datasets. Comparison results indicate that our proposed model outperforms the mainstream methods in terms of visualization and most evaluation metrics, highlighting its potential for practical application in dam safety inspection and maintenance.

Crack detection and damage evaluation of asymmetrical steel-reinforced concrete frame nodes using acoustic emission technology

ABSTRACT Detecting cracks in steel-reinforced concrete (SRC) frame nodes is crucial for ensuring structural safety. This study employs acoustic emission (AE) technology to monitor the growth of concrete structural defects in real time. The aim is to establish a sensitive assessment method based on AE parameters to accurately assess the damage stages of SRC frame nodes by considering the complex crack extension mechanism in SRC structures. An experimental study of the AE characteristics of SRC frame nodes under low-cycle loading was performed. The crack evolution process of SRC frame nodes was monitored and analysed using the AE parameters. The results showed that ringing count is the AE parameter more sensitive to the damage of the SRC frame node. The damage evaluation method was established based on the variation coefficient analysis of the AE parameters. Considering the sudden change in the growth rate of the damage index, the damage evolution process of the SRC frame nodes can be accurately divided into three stages: initial crack compaction, rapid crack expansion, and crack penetration. These stages are consistent with the mechanical properties of SRC frame nodes.

MFAFNet: An innovative crack intelligent segmentation method based on multi-layer feature association fusion network

The regular and timely detection and segmentation of cracks in asphalt pavements is very important for road evaluation. However, certain problems remain to be solved, such as the difficulty of crack detection under interference from zebra stripes and dark light. A novel intelligent crack segmentation method based on a multi-layer feature association fusion network (MFAFNet) is therefore proposed in this study. Firstly, a fusion convolution with a Transformer called a feature coupling encoder (FC-Encoder) is developed in MFAFNet to enhance the model's global feature awareness and ability to capture local details. Secondly, a two-branch feature association module (TFBA-module) is proposed to obtain strong correlation information for global and local features. Next, a hybrid MLP architecture for lightweight feature decoder (H-MLP Decoder) is constructed to achieve feature recombination of the multi-level fusion information. The accuracy of crack segmentation under interference from zebra stripes and dark light is improved through the use of these three modules. Our model is compared with some well-known existing segmentation networks such as U-Net, DeepLabv3+, PSPNet, HRNet and SegFormer, and the segmentation accuracy, F1-score and IoU of the proposed MFAFNet are found to be 94.39 %, 93.26 % and 89.46 %, respectively. In addition, the segmentation efficiency reaches 21.87FPS. Our experimental results show that the proposed MFAFNet yields more effective performance in the field of asphalt pavement crack segmentation than the alternatives.

A lightweight feature attention fusion network for pavement crack segmentation

AbstractThe occurrence of pavement cracks poses a significant potential threat to road safety, thus the rapid and accurate acquisition of pavement crack information is of paramount importance. Deep learning methods have the capability to offer precise and automated crack detection solutions based on crack images. However, the slow detection speed and huge model size in high‐accuracy models are still the main challenges required to be addressed. Therefore, this research presents a lightweight feature attention fusion network for pavement crack segmentation. This structure employs FasterNet as the backbone network, ensuring performance while reducing model inference time and memory overhead. Additionally, the receptive field block is incorporated to simulate human visual perception, enhancing the network's feature extraction capability. Ultimately, our approach employs the feature fusion module (FFM) to effectively combine decoder outputs with encoder's low‐level features using weight vectors. Experimental results on public crack datasets, namely, CFD, CRACK500, and DeepCrack, demonstrate that compared to other semantic segmentation algorithms, the proposed method achieves both accurate and comprehensive pavement crack extraction while ensuring speed.

Effective small crack detection based on tunnel crack characteristics and an anchor-free convolutional neural network

Tunnel cracks are thin and narrow linear targets, and their pixel proportions in images are usually very low, less than 6%; therefore, a method is needed to better detect small crack targets. In this study, a crack detection method based on crack characteristics and an anchor-free framework is investigated. First, the characteristics of cracks are analyzed to obtain the real crack texture, interference noise texture, and targets appearing near each crack as the context information for the model to filter and remove noise. We discuss the crack detection performance of anchor-based and anchor-free algorithms. Then, an optimized anchor-free algorithm is proposed in this paper for crack detection. Based on the advantages of YOLOX-x, we add a semantic enhancement module to better use contextual information. The experimental results show that the anchor-free algorithm performs slightly better than other algorithms in crack detection situations. In addition, the proposed method displays better detection performance for slender and inconspicuous cracks, with an average precision of 0.858.

Comparison of U-Net and Fully Convolutional Networks (FCN) for concrete cracks detection using raw images under various conditions

Crack detection in concrete buildings is crucial for assessing structural health, but it poses challenges due to complex backgrounds, real-time requirements, and high accuracy demands. Deep learning techniques, including U-Net and Fully Convolutional Networks (FCN), have shown promise in crack detection. However, they are sensitive to real-world environmental variations, impacting robustness and accuracy. This paper compares the performance of U-Net and FCN for concrete crack detection on bridges using raw images under various conditions. A dataset of 157 images (100 for training, 57 for testing) was used, and the models were evaluated based on Dice similarity coefficient and Jaccard index. FCN slightly outperformed U-Net in accuracy (94.88% vs. 94.21%), while U-Net had a slight advantage in validation (93.55% vs. 92.99%). These findings provide valuable insights for automated infrastructure maintenance and repair.

Rapid detection of turtle cracks in corn seed based on reflected and transmitted images combined with deep learning method

Cracks in corn seeds greatly affect their storage tolerance and germination ability. These cracks are categorized as single, double, and turtle cracks. The vigor experiment showed that turtle cracks lead to the poorest seed vigor, with significantly lower germination rates after artificial aging. Traditional methods to detect turtle cracks, like lightboxes, staining, and colorimetry, are inefficient or costly. Therefore, a detection method for turtle cracks of corn seeds based on reflected light and transmitted light images combined with deep learning was proposed. The transmitted and reflected light images on embryo and endosperm surfaces of 2000 corn seeds with different crack were collected. A Based on Self-Attention Modul Convolutional Neural Support Vector Networks (SACNSVN) model was proposed to detect the turtle cracks seeds, and compared with the model established by LSTM, CNN, BLR, SVM, and MLP. The effects of embryo surface, endosperm surface, varieties and maturity on turtle crack detection were investigated. The results showed that: (1) The transmitted light image had a significant correlation with 62 and 58 indicators of cracks and turtle cracks, respectively, which better reflected the crack and turtle crack seeds than reflected light image; (2) The accuracy of turtle cracks detection model based on embryo endosperm surface combined dataset were higher than embryo surface, endosperm surface, and embryo endosperm surface mixed dataset; (3) The SACNSVN model provides the optimal accuracy with 82.6%; (4) Variety greatly affects turtle crack detection in corn seeds, while maturity level has a minor impact, and SACNSVN exhibits strong generalization ability. This study provides significant technical support for optimizing the seed processing process and improving the seed quality.

Pixel-level block classification and crack detection from 3D reconstruction models of masonry structures using convolutional neural networks

Inspection and documentation of masonry structures is a time-consuming and expensive process that heavily relies on an engineer's expertise. This paper introduces a computer vision-based method that automates the creation of classified point clouds from 3D reconstruction models obtained through photogrammetry and/or laser scanning. By leveraging Convolutional Neural Networks (CNN) on 3D renders, the proposed methodology can be used to classify structural features (i.e., blocks, mortar, cracks) with greater accuracy and less effort than conventional methods. Moreover, this approach is flexible and can include further classifications by incorporating additional CNN models, allowing broader applications across various materials (i.e., concrete, steel, timber) and defects. Additionally, a precise methodology for accurate crack quantification featuring a manual annotation tool was introduced which was validated using outputs from a full-scale masonry arch bridge test carried out in the laboratory. The results emphasize the robustness of the classification approach and highlight the useful geometric information that can be gained from full-scale masonry structures. The proposed approach has the potential to use image data from UAVs/static cameras and revolutionize the way we document and inspect structures in the future.

Real-time multi-object detection model for cracks and deformations based on deep learning

The paper proposes a deep learning-based multi-object real-time detection model for concrete cracks and structural deformations. The model improves the single-stage object detection framework, You Only Look Once version 7 (YOLOv7), by incorporating convolutional block attention mechanisms and global attention mechanisms into its backbone and neck networks, respectively. It also establishes dual output branches for cracks and deformations within the output module to enable multi-object detection capabilities. Utilizing transfer learning strategies, the model effectively detects concrete cracks and structural deformations with a limited dataset. The results demonstrate that the improved YOLOv7 model significantly improves the detection of non-continuous cracks and reduces noise in complex environments, indicating strong generalization and robustness. The improved model exhibits a 4.53% increase in crack detection accuracy over the original and achieves low peak relative errors for deflection deformation in concrete beams and in-plane deformation in concrete slabs at just 0.22% and 3.05%, respectively.

Autonomous surface crack identification for concrete structures based on the you only look once version 5 algorithm

Failure to repair roads in a timely manner may shorten their life and even cause traffic accidents. Thus, accurate crack detection and reasonable classification are crucial for road safety evaluation. In this study, an improved network model based on the You Only Look Once version 5 algorithm is presented, with three additional modules: The first module improves the data processing speed by replacing the C3 module in the original network with a lightweight network model. The second module was used to lighten network weight by reusing a simple convolution structure to equivalently represent the calculation of a convolution layer as a weighted sum of several small convolution blocks. And the third module is used to improve the detection accuracy by removing the upsampling and performing three-way splicing. The proposed model can detect different types of cracks, and an extensive ablation study is reported based on various combinations of the proposed modules. Based on training on a database of 5484 images, the results show that the improved network proposed in this study can effectively identify pavement cracks. Compared with the original network, mean Average Precision is increased by 5.98%, the inference time is reduced by 4.82%, and the model weight is decreased by 17.36%. Additionally, to comply with engineering practice, comparative experiments were conducted on the pre-rotated dataset. The results showed that compared with You Only Look Once version 8, the improved algorithm improved accuracy, recall, average accuracy, and F1 score by 3.28%, 8.46%, 3.79% and 5.89%, respectively. This study can serve as an important reference for the development of crack detection methods.

MatrixCraCS: Automated tracking of matrix crack development in GFRP laminates undergoing large tensile strains

A novel image processing method for tracking development of matrix cracks in glass-fibre reinforced polymer (GFRP) laminates is presented. Images are acquired in a quasi-static tension test using transillumination white light imaging. These images show changes occurring due to developing damage. The method, called MatrixCraCS, tracks and quantifies matrix cracks while compensating for large specimen deformation and stitching threads, which obscure crack development and seriously impact crack detection. Matrix cracks are tracked via a sequential image difference and morphological filtering is used to detect cracks. MatrixCraCS is verified against synthetic images and shows an error of less than 7% in the quantified length of cracks and 0% detection failures. MatrixCraCS is validated against experimental results for a [±452°902°]S GFRP laminate, where microscopic analysis shows 5.92% error in crack detection. Error relative to manual crack tracking are quantified for detection failures and false positives as 3.3% and 1.57%, respectively. It is found that the method accurately quantifies cracks in GFRP laminates subject to large deformation and is robust against noise.

Enhancing Concrete Crack Image Detection Using MobileNetV2 and Transfer Learning

The safety of civil engineering structures such as bridges and buildings is paramount, necessitating the early detection and repair of cracks to prevent structural failures. Traditional crack detection methods, including manual inspections and basic image processing, are often hampered by slow detection speeds and limited accuracy. This study explores the integration of advanced deep learning techniques, specifically MobileNetV2, enhanced through transfer learning, to improve the efficiency and accuracy of crack detection. The "Concrete Crack Images for Classification" dataset was employed, featuring 40,000 images from real-world scenarios. Our approach leverages the lightweight architecture of MobileNetV2 and the efficiency of transfer learning to create a robust model that not only reduces computational demands but also achieves high accuracy, with a validation accuracy rate of 99.38%. This paper details the model training, the innovative use of MobileNetV2, and comparative analyses with other deep learning models, demonstrating significant improvements over traditional methods. The findings underscore the potential of MobileNetV2 and transfer learning in practical applications, offering a promising avenue for future research in automated crack detection across various engineering fields.

A Review on Crack Detection in Wind Turbine Blade

Abstract: It was observed that there is a need to reduce of maintenance and operational cost of Wind Energy conversion System. The most efficient way of reducing this cost would be to carry out Non-destructive techniques (NDT) and continuously monitor the condition of the system. This allows for early detection of the blade Cracking or damage, minimizing downtime, and maximizing productivity. The importance of condition monitoring and fault diagnosis in WECS (blades) and keeping in mind the need for future research, this paper is intended as a brief status describing different type of faults, methods of detection and future aspects

Underwater dam crack image generation based on unsupervised image-to-image translation

Underwater crack detection is necessary for the safe operation of concrete dams. Current deep-learning-based underwater crack detection methods rely heavily on a large number of crack images; these images are difficult to collect because of complex and dangerous underwater environments. This study proposes a method that can generate underwater dam crack images using above-water dam crack images through an image-to-image translation method. CycleGAN, which is more powerful than other models, was optimized to generate underwater dam crack images by translating existing above-water dam crack images into underwater styles. The generated underwater images were validated using the following major computer vision tasks: classification, object detection, and semantic segmentation. The results demonstrate the potential of these generated images for training and optimizing deep-learning-based crack-detection methods. This method is expected to solve the problem of insufficient data and enhance deep-learning-based detection networks.

PLC BASED RAILWAY ACCIDENT AVOIDANCE SYSTEM

The paper presents a comprehensive framework for enhancing railroad security by integrating technologies such as signalling arrangements, train closure security systems, automatic railroad gate control, intrusion detection, obstacle detection, tunnel control, and automatic blockade systems. These systems utilize sensors and advanced controls to detect and mitigate potential threats, enhancing security measures and reducing the risk of accidents. Programmable Logic Controllers (PLCs) in railroad systems manage several security protocols, including emergency brake, over-speed control, train door control, and fire detection. They also ensure passenger and train safety by monitoring temperature, pressure, and voltage parameters. In the event of any anomalies, the PLC triggers an alert and takes necessary actions to prevent accidents. Key Words: : Automatic Barricade System, Automatic Railway Gate Controlling, Crack Detection System, Obstacle Detection, PLC, Signalling Deployment System, Tunnel Power Saving System.

Concrete Highway Crack Detection Based on Visible Light and Infrared Silicate Spectrum Image Fusion.

Cracks provide the earliest and most immediate visual response to structural deterioration of asphalt pavements. Most of the current methods for crack detection are based on visible light sensors and convolutional neural networks. However, such an approach obviously limits the detection to daytime and good lighting conditions. Therefore, this paper proposes a crack detection technique cross-modal feature alignment of YOLOV5 based on visible and infrared images. The infrared spectrum characteristics of silicate concrete can be an important supplement. The adaptive illumination-aware weight generation module is introduced to compute illumination probability to guide the training of the fusion network. In order to alleviate the problem of weak alignment of the multi-scale feature map, the FA-BIFPN feature pyramid module is proposed. The parallel structure of a dual backbone network takes 40% less time to train than a single backbone network. As determined through validation on FLIR, LLVIP, and VEDAI bimodal datasets, the fused images have more stable performance compared to the visible images. In addition, the detector proposed in this paper surpasses the current advanced YOLOV5 unimodal detector and CFT cross-modal fusion module. In the publicly available bimodal road crack dataset, our method is able to detect cracks of 5 pixels with 98.3% accuracy under weak illumination.

Distilling Knowledge from a Transformer-Based Crack Segmentation Model to a Light-Weighted Symmetry Model with Mixed Loss Function for Portable Crack Detection Equipment

The detection of cracks is extremely important for maintenance of concrete structures. Deep learning-based segmentation models have achieved high accuracy in crack segmentation. However, mainstream crack segmentation models have very high computational complexity, and therefore cannot be used in portable crack detection equipment. To address this problem, a knowledge distilling structure is designed by us. In this structure, a large teacher model named TBUNet is proposed to transfer crack knowledge to a student model with symmetry structure named ULNet. In the TBUNet, stacked transformer modules are used to capture dependency relationships between different crack positions in feature maps and achieve contextual awareness. In the ULNet, only a tiny U-Net with light-weighted parameters is used to maintain very low computational complexity. In addition, a mixed loss function is designed to ensure detail and global features extracted by the teacher model are consistent with those of the student model. Our designed experiments demonstrate that the ULNet can achieve accuracies of 96.2%, 87.6%, and 75.3%, and recall of 97.1%, 88.5%, and 76.2% on the Cracktree200, CRACK500, and MICrack datasets, respectively, which is 4–6% higher than most crack segmentation models. However, the ULNet only has a model size of 1 M, which is suitable for use in portable crack detection equipment.