Crack Detection Research Articles

Study on Fractal Damage of Concrete Cracks Based on U-Net

The damage degree of a reinforced concrete structure is closely related to the generation and expansion of cracks. However, the traditional damage assessment methods of reinforced concrete structures have defects, including low efficiency of crack detection, low accuracy of crack extraction, and dependence on the experience of inspectors to evaluate the damage of structures. Because of the above problems, this paper proposes a damage assessment method for concrete members combining the U-Net convolutional neural network and crack fractal features. Firstly, the collected test crack images are input into U-Net for segmenting and extracting the output cracks. The damage to the concrete structure is then classified into four empirical levels according to the damage index (DI). Subsequently, a linear regression equation is constructed between the fractal dimension (D) of the cracks and the damage index (DI) of the reinforced concrete members. The damage assessment is then performed by predicting the damage index using linear regression. The method was subsequently employed to predict the damage level of a reinforced concrete shear wall–beam combination specimen, which was then compared with the actual damage level. The results demonstrate that the damage assessment method for concrete members proposed in this study is capable of effectively identifying the damage degree of the concrete members, indicating that the method is both robust and generalizable.

Circumferential Crack Detection in Ultra-High-Pressure Tubular Reactors with Pulsed Eddy Current Testing.

Ultra-high-pressure tubular reactors are crucial pieces of equipment for polyethylene production. Long-term operation under high temperature, high pressure, and other extremely harsh conditions can lead to various defects, with circumferential cracks posing a major safety risk. Detecting cracks is challenging, particularly when they are under a protective layer of a certain thickness. This study designed a pulsed eddy current differential probe to detect circumferential cracks in ultra-high-pressure tubular reactors, with the lift-off distance acting as a protective layer. Detection models for traditional cylindrical and semi-circular excitation differential probes were established using finite element simulations. Corresponding experiments under different lift-off conditions were carried out, and the model's accuracy was verified by the consistency between the simulation results and experimental data. The distribution of the eddy current field under different conditions and the disturbances caused by cracks at various positions to the detection signal were then calculated in the simulations. The simulation results showed that the cracks significantly disturbed the eddy current field of the semi-circular excitation differential probe compared with that of the traditional cylindrical probe. The designed differential probe effectively detected circumferential cracks of specific lengths and depths using the difference in the voltage signals. The experimental results were in agreement with the simulation results, showing that the designed probe could effectively detect 20 mm-long circumferential cracks at a lift-off of 60 mm. The experimental results also show that the probe's detection coverage area in the axial direction varied with the lift-off height. The probe design and findings are valuable for detecting cracks in ultra-high-pressure tubular reactors with protective layers.

Numerical study of phase space analysis for the development of subsurface crack detection method using pulsed eddy current

Root-deck cracks, a prominent form of subsurface damage observed in orthotropic steel decks (OSDs), pose significant challenges to maintaining structural integrity. Early detection of these cracks is crucial to prevent further deterioration. This paper introduces novel and robust techniques for processing response signals obtained from the Pulsed Eddy Current Technique (PECT) using phase space analysis. The proposed methods aim to improve sensitivity and noise handling capabilities by employing an appropriate damage index derived from comprehensive phase space analysis, enabling effective detection of subsurface cracks in OSDs. A numerical study demonstrates the effectiveness of the proposed methods in detecting crack length change as small as 1 mm from the bottom of a 12 mm steel plate, with the Change in Phase Space Topology (CPST) identified as a suitable damage index. Furthermore, the newly proposed signal processing techniques allow for a more comprehensive interpretation of response signals for subsurface damage detection, encapsulating the extent of damage within a single value, even in the presence of small crack lengths near the bottom of the steel plate and noise. As a result, the proposed methods overcome the limitations of conventional approaches and offer promising prospects for enhanced subsurface crack detection in OSDs.

A Novel YOLOv10-DECA Model for Real-Time Detection of Concrete Cracks

The You Only Look Once (YOLO) series algorithms have been widely adopted in concrete crack detection, with attention mechanisms frequently being incorporated to enhance recognition accuracy and efficiency. However, existing research is confronted by two primary challenges: the suboptimal performance of attention mechanism modules and the lack of explanation regarding how these mechanisms influence the model’s decision-making process to improve accuracy. To address these issues, a novel Dynamic Efficient Channel Attention (DECA) module is proposed in this study, which is designed to enhance the performance of the YOLOv10 model in concrete crack detection, and the effectiveness of this module is visually demonstrated through the application of interpretable analysis algorithms. In this paper, a concrete dataset with a complex background is used. Experimental results indicate that the DECA module significantly improves the model’s accuracy in crack localization and the detection of discontinuous cracks, outperforming the existing Efficient Channel Attention (ECA). When compared to the similarly sized YOLOv10n model, the proposed YOLOv10-DECA model demonstrates improvements of 4.40%, 3.06%, 4.48%, and 5.56% in precision, recall, mAP50, and mAP50-95 metrics, respectively. Moreover, even when compared with the larger YOLOv10s model, these performance indicators are increased by 2.00%, 0.04%, 2.27%, and 1.12%, respectively. In terms of speed evaluation, owing to the lightweight design of the DECA module, the YOLOv10-DECA model achieves an inference speed of 78 frames per second, which is 2.5 times faster than YOLOv10s, thereby fully meeting the requirements for real-time detection. These results demonstrate that an optimized balance between accuracy and speed in concrete crack detection tasks has been achieved by the YOLOv10-DECA model. Consequently, this study provides valuable insights for future research and applications in this field.

Virtual reality visualisation of automatic crack detection for bridge inspection from 3D digital twin generated by UAV photogrammetry

This research develops a UAV photogrammetry methodology to generate 3D digital twins (DT) of the Elvanlı Bridge in Mersin, Turkey. These DTs are then analyzed using advanced image processing algorithms for automatic crack detection. The identified cracks were incorporated into the 3D model, creating a DT to damage-augmented digital twins (DADT). Subsequently, the DADT was rendered in virtual reality, offering an interactive alternative solution with remote access to on-site structural visual inspections in a digital environment. This approach has increased the objectivity and efficiency of inspections in the digital environment. The results demonstrate the potential of this integrated approach to enhance the accuracy and reliability of bridge inspections, reduce operational costs, and provide a comprehensive platform for structural health monitoring through non-invasive methods. The study transformative impact of combining emerging technologies such as UAV photogrammetry and VR in civil engineering, paving the way for more systematic and precise infrastructure assessments.

Internal inspection method for crack defects in ferromagnetic pipelines under remanent magnetization

Magnetic flux leakage (MFL) testing is effective in detecting corrosion in ferromagnetic pipelines. However, the MFL generated at the crack is highly weak and is easily drowned in the strong background magnetic field and difficult to detect. Therefore, this paper creatively proposes a remanent magnetic flux leakage (RMFL) detection method. This method utilizes the hysteresis state of the pipeline after MFL detection and identifies crack defects by collecting the remanent magnetic flux density near the inner wall surface of the pipeline. The remanent magnetic field distribution near the pipeline surface is examined at different crack sizes, magnetization speeds, and lift-off values via theoretical analysis, finite element simulation, and experimental verification. In addition, experiments have demonstrated that in terms of crack detection capability, RMFL is superior to MFL. Therefore, adding a RMFL measurement module to the conventional MFL detector has important practical value. It can realize the targeted collaborative application of these two technologies, namely the synchronous detection of corrosion and crack defects, which greatly improves the detection coverage and detection efficiency.

Application of Surface Ultrasonic Waves for Detection of Contact Fatigue Cracks in the Rail Surface

The integrity and durability of rails plays a key role in train safety. However, the interaction of the rail head surface with the wheels of the rolling stock leads to high damage to these areas. The surface of the rail head is subject to the greatest damage, in which fatigue cracks develop on the surface with subsequent development. Timely detection of fatigue cracks in the rolling surface is possible using the ultrasonic technique using surface waves. To do this, the work investigated the sensitivity of a surface ultrasonic wave to obstacles in the surface of rails in the form of extended grooves, notches of finite length and known depth, as well as real cracks. The studies were carried out using the pulse-echo method at frequencies of 1.25, 1.8, 2.5, 4 MHz. Research has shown that surface waves are sensitive to surface fatigue cracks. The amplitude of the reflected pulses depends on the wavelength and the depth of crack propagation. The influence of the distance to fatigue cracks and the orientation angle of the transducer relative to the rail axis on the sensitivity of the surface wave to these defects was also studied. The results obtained allow us to conclude that the use of surface ultrasonic waves makes it possible to detect fatigue cracks in the crack surface. Thus, the use of the pulse-echo technique and surface wave converters makes it possible to detect contact fatigue cracks in the rail head, which can be used to eliminate them in a timely manner. The determination of their depth by amplitude is influenced by many factors, which are difficult to take into account in real conditions.

Pavement Distress Detection Based on the Staged Deep Learning Classifier Approach

Pavement crack detection is a critical task that is essential to ensure the safety of roads and highways. Accurate detection and classification of pavement cracks can help transportation agencies to identify potential maintenance needs and plan appropriate interventions. In this project, we propose a staged deep learning classifier approach for pavement crack detection to provide accurate and comprehensive information about the pavement condition. In this proposed pavement crack detection model, there are four main phases: pre-processing, feature extraction, feature selection, and crack detection. Firstly, raw images are pre-processed through median filtering and histogram equalization for noise removal and contrast enhancement. Next, features such as the improved local binary pattern, gray-level co-occurrence matrix, and gray-level run length matrix are extracted from the pre-processed images. The optimal features are selected using a hybrid optimization model, the tuna customized honey badger optimization algorithm, which combines the honey badger algorithm and tuna swarm optimization. This new hybrid optimization model will enhance the search strategy for solving optimization problems. The loss function of an augmented convolutional neural network (A-CNN) is modified to compute the root mean square error instead of the entropy-based loss function. The final detected outcomes (presence or absence of cracks) are acquired from the A-CNN.

Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNet

With the progress of social life, the aging of building facilities has become an inevitable phenomenon. The efficiency of manual crack detection is limited, so it is necessary to explore intelligent detection technology. This article proposes a novel crack detection method TF-MobileNet. We took into account the effect of lightweight and crack feature extraction, so we developed a novel crack feature extraction backbone network, which combined Transformer and MobileNetV3. Then we improved the feature fusion network by using the multi-headed attention mechanism of the Bottleneck Transformer, which enables the feature fusion effect to be improved. Then, we integrated SENet and SimAM attention mechanisms into the networks used for feature extraction and feature fusion, thereby further improving the crack detection performance. Finally, we deployed our model in edge devices (NVIDIA Jeston Nano). The findings indicate that our proposed model has achieved 90.8% mAP on the dataset and worked well on the edge device side, which meet the requirements of automatic crack detection. Our model enables real-time monitoring of pavement using edge devices. This approach allows for timely maintenance and repair of the pavement. In the future, we can train the model to recognize more pavement distress features, addressing road safety issues effectively.

Crack SAM: enhancing crack detection utilizing foundation models and Detectron2 architecture

Accurate crack detection is crucial for maintaining pavement integrity, yet manual inspections remain labor-intensive and prone to errors, underscoring the need for automated solutions. This study proposes a novel crack segmentation approach utilizing advanced visual models, specifically Detectron2 and the Segment Anything Model (SAM), applied to the CFD and Crack500 datasets, which exhibit intricate and diverse crack patterns. Detectron2 was tested with four configurations—mask_rcnn_R_50_FPN_3x, mask_rcnn_R_101_FPN_3x, faster_rcnn_R_50_FPN_3x, and faster_rcnn_R_101_FPN_3x—while SAM was compared using Focal Loss, DiceCELoss, and DiceFocalLoss. SAM with DiceFocalLoss outperformed Detectron2, achieving mean IoU scores of 0.69 and 0.59 on the CFD and Crack500 datasets, respectively. The integration of Detectron2 with faster_rcnn_R_101_FPN_3x and SAM using DiceFocalLoss involves generating bounding boxes with Detectron2, which serve as prompts for SAM to produce segmentation masks. This approach achieves mIoU scores of 0.83 for CFD dataset and 0.75 for Crack500 dataset. These results highlight the potential of combining foundation models with Detectron2 for advancing crack detection technologies, offering valuable insights for enhancing highway maintenance systems.

Nonlinear Crack-Wave Modulations in Shear Horizontal Wave Propagation for Fatigue Crack Detection

The nonlinear interaction of shear horizontal waves with fatigue cracks is investigated for structural damage detection. The focus is on the non-classical modulation effect in the presence of damage. The major principle of the method is explained theoretically and supported by a semi-analytical solution. The method is tested experimentally in aluminium beams with fatigue cracks. A combination of high-frequency ultrasonic and low-frequency vibration shear excitations are introduced to monitored beam components using low-profile piezoceramic shear actuators. Nonlinear vibro-acoustic responses are gathered using laser vibrometry. Vibration excitation frequencies are selected using experimental and numerical modal analysis. A series of vibro-acoustic experiments is performed for fatigue crack detection. The results show that the non-classical nonlinear vibro-acoustic effect – based on shear horizontal wave propagation – can be used for crack detection. In addition, the method also allows for damage localisation.

Predicting actual crack size through crack signal obtained by advanced Flexible Eddy Current Sensor using ResNet integrated with CBAM and Huber loss function

This study presents an advanced FEC sensor, engineered by arranging coils in a co-directional current configuration. Moreover, boasting a compact design, the FEC sensor showcases significantly enhanced spatial resolution, enabling robust detection of small cracks even at low excitation frequencies and mitigating issues of overlapping in adjacent crack detection. Results indicate successful crack detection through voltage and phase measurements, albeit with phase signals demonstrating variation at specific excitation frequencies, complicating the determination of actual crack sizes. Consequently, a novel model is proposed to forecast actual crack sizes, leveraging experimental data from the FEC sensor system. This model integrates a Residual Neural Network (ResNet) architecture with a Convolutional Block Attention Module (CBAM) and utilizes the Huber loss function to minimize errors during model training. Comparative analysis underscores the superior performance of the proposed model in predicting crack length and depth compared to the standalone ResNet, particularly when utilizing the Huber loss function with a δ value of 1.0. Evaluation metrics, encompassing Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE), illustrate an average accuracy surpassing 95 % for crack size predictions. Consequently, the proposed model demonstrates remarkable performance, significantly reducing the time required to ascertain actual crack sizes by leveraging voltage and phase measurements.

Visual detection of road cracks based on improved U-Net and morphological operations

Visual detection of road cracks based on improved U-Net and morphological operations

Computer vision-based cascade detection of peeling and cracking in masonry house walls

Self-built masonry structures are commonly used as houses in rural areas of the central plains of China. These structures pose significant safety risks due to the low level of self-building and non-standard designs. The primary type of damage to the walls of masonry houses is cracks, while the decorative layers of the walls may also experience peeling or cracking. The shapes, sizes, and surface characteristics of these damages are complex and unique to each type. To achieve fast identification of surface damage on masonry house walls, this paper proposes a cascade detection model that combines a multilevel cascade classifier with a parallel sub-segmentation network. The VGG16 neural network is used as the backbone for a multi-level series classifier. The model is trained by using a damage image set of the wall decorative layers in rural masonry houses. The classification of background and damage, as well as the classification of cracks and peels, are sequentially completed. Then, the parallel sub-segmentation model uses EfficientNet-B7 as the encoder and combines it with the U-Net framework skeleton to perform pixel-level segmentation of peeling and cracks. Finally, the output of parallel sub-segmentation networks is superimposed and fused to generate a complete image containing segmentation information of peeling and cracks. The cascade form network structure adopted in this model significantly reduces the training difficulty and enhances the model accuracy. Compared with Segformer and Deeplabv3+ network, the average IoU of the proposed method for on-site masonry wall images can be increased by 0.29 and 0.08, respectively.

Evaluation of asphalt anti-cracking performance of SBS polymer with SCB method and deep learning

In recent years, there have been unprecedented developments in artificial intelligence. Object detection, voice recognition, face recognition etc. are some of the artificial intelligence applications. In this study, an auxiliary method for the automatic detection of cracks, one of the main deterioration problems on highways, is proposed. The crack formation of hot mix asphalts is investigated with an image processing method modeled with Attention SegNet architecture. Styrene-butadiene-styrene (SBS), the most widely used additive in bitumen modification, was used at 2 %, 3 %, and 4 % ratios to modify 50/70 bitumen. Semi-circular asphalt specimens obtained with SBS modified bitumen were subjected to a semicircular bending (SCB) test and fracture performance was investigated. The effects of different temperature, notch size and additive on crack detection performance are evaluated. In the experimental study, maximum load, fracture energy, fracture toughness (KIC) values were obtained at low temperature, and resistance values against crack propagation were obtained by applying the J-integral method at intermediate temperature. The results demonstrated that with the addition of SBS, the fracture strength and maximum load values increased at each temperature value, with the 4 % SBS mixture offering the highest performance. Moreover, the image segmentation performed with SegNet provided high accuracy and precision values for cracks. It was observed that the accuracy values of the image processing methods decreased at low temperature, while at high temperature, higher accuracy values were obtained as the cracking rate.

Multi-Scale Semantic Map Distillation for Lightweight Pavement Crack Detection

Multi-Scale Semantic Map Distillation for Lightweight Pavement Crack Detection

The design of two-dimensional elastic diffusers

The ability to design surfaces with specific scattering properties has widespread applicability. In this article, we leverage a stochastic method for designing randomly rough, two-dimensional surfaces with a prescribed mean angular intensity distribution. Analytical and numerical techniques are implemented for a linearly elastic medium-vacuum interface, to generate band-limited diffusers with square and elliptical domains of scattering. Longitudinal incidence is assumed, and the theory allows for bulk wave mode conversions. Multivalued, discontinuous surfaces are formulated, and it is shown that the theoretical model may be satisfied independently of the facet shape utilised, with square and hexagonal discretizations given as examples. In the context of elastic wave scattering, the surfaces presented in this article may have applications in the calibration of scatterometers for wave manipulation as well as for crack detection using ultrasound.

The Effect of Erosive Media on the Mechanical Properties of CAD/CAM Composite Materials.

This study aimed to investigate the effect of acidic media storage (gastric acid and Coca-Cola) on the mechanical properties of CAD/CAM materials. Three types of materials were tested: a polymer-infiltrated ceramic network (PICN) (Vita Enamic (En), VITA Zahnfabrik, Germany), a resin composite block (RCB) (Cerasmart (Cs), GC Corp, Japan), and a conventional resin-based composite (Gradia direct (Gr), GC Corp, Japan), which was used as a control. Beam-shaped specimens of each material, with dimensions of 16 mm × 4 mm × 1.5 mm, were prepared (90 in total). The specimens were divided into subgroups (10 each) and stored for 96 h in either gastric acid, Coca-Cola, or distilled water. Flexural strength and elastic modulus were evaluated using a three-point flexural strength test with acoustic emission (AE) monitoring. Vickers microhardness was measured before and after storage in gastric acid and Coca-Cola. Data were statistically analysed using two-way and one-way ANOVA, the Tukey's post hoc, and independent t-test at a significance level of 0.05. The results showed that Cs and En maintained their flexural strength and elastic modulus after acidic media exposure, while Gr experienced a significant decrease in flexural strength following gastric acid storage (p < 0.01). Initial crack detection was not possible using the AE system, impacting the determination of flexural strength. Exposure to acidic media decreased all materials' microhardness, with Gr showing the most notable reduction (p < 0.0001). Gastric acid had a greater impact on the microhardness of all tested materials compared to Coca-Cola (p < 0.0001). In conclusion, storage in erosive media did not notably affect the flexural strength or elastic modulus of CAD/CAM composites but it did affect hardness. CAD/CAM composite blocks demonstrated superior mechanical properties compared to the conventional composite.

UP-CrackNet: Unsupervised Pixel-Wise Road Crack Detection via Adversarial Image Restoration

UP-CrackNet: Unsupervised Pixel-Wise Road Crack Detection via Adversarial Image Restoration

MECFNet: Reconstruct Sharp Image for UAV-Based Crack Detection

MECFNet: Reconstruct Sharp Image for UAV-Based Crack Detection