Surface Crack Detection Research Articles

Robust surface crack detection with structure line guidance

Robust surface crack detection with structure line guidance

Complex surface cracks detection and identification by laser array spots thermography with PCA-Frangi processing

In this paper, a method for rapid detection and automatic identification of complex surface cracks based on laser array spots thermography with PCA-Frangi processing is developed. With the Laser Array Spots Thermography (LAST), a complex surface crack in a relatively large surface area can be detected rapidly. In addition, a novel approach utilizing the PCA-Frangi algorithm for feature extraction is proposed to enhance the imaging performance of surface cracks with complex morphology. The results show that the proposed method can extract the cracks and eliminate the interference of array spots to crack identification. Furthermore, this method effectively mitigates the impact of thermal inhomogeneity and thermal noise during the heating process. Finally, the crack features are automatically identified. The simulation and experimental results illustrated that the method enables the accurate recognition of complex surface crack characteristics, further enhancing the overall performance of the crack detection with LAST.

Industrial Application of Surface Crack Detection in Sheet Metal Stamping Using Shift-and-Add Speckle Imaging

Industrial Application of Surface Crack Detection in Sheet Metal Stamping Using Shift-and-Add Speckle Imaging

Unsupervised domain adaptation-based crack segmentation using transformer network

Surface cracks are a common structural defect. The intelligent inspection of these defects through computer vision and deep learning is of paramount importance for early maintenance and operation. Despite the remarkable success of supervised learning methods in detecting surface cracks, their performance heavily relies on the availability of extensive labeled datasets. Annotating a single image can be a time-consuming process, prone to human error. Moreover, these methods often struggle to generalize effectively to unseen datasets due to disparities between source and target images. To address this issue, unsupervised domain adaptation comes into play, as it aims to transfer knowledge learned from the labeled source domain to the unlabeled target domain. Consequently, we conducted an evaluation of a recent unsupervised domain adaptation model for semantic segmentation that incorporates masked image consistency into DAFormer, a state-of-the-art model with the ability to adapt to various datasets. To assess the model’s performance, we employed three publicly available crack datasets, each containing background and crack classes. Our study has revealed that : (1) SegFormer, a transformer-based model, outperforms ConvNet-based models without utilizing adaptation knowledge, demonstrating superior generalizability to previously unseen data. (2) The unsupervised domain-adaptation model consistently outperforms the source model, resulting in a significant enhancement in the mean intersection over union of SegFormer’s source-only approach by a remarkable 10% to 22%. With the exception of a single case, the relative performance of unsupervised domain adaptation compared to supervised training with labeled data exceeds 85%, underscoring its promising performance in crack segmentation. Consequently, our adopted method emerges as a viable alternative, particularly in scenarios where labeled data is scarce or prohibitively expensive.

Detection of surface cracks on slanted surfaces and through thick irregular insulation layers using polarimetric microwave imaging

Reliable detection of cracks on slanted metal surfaces and through irregular insulation/coating is critical in many inspection applications. Microwave non-destructive testing (NDT) techniques have proven to be effective for crack detection and characterization. However, the utility of conventional microwave NDT techniques for challenging inspection scenarios which involve cracks on slanted surfaces, or cracks under relatively thick, and possibly, irregular insulation has been limited. In this paper, a polarimetric microwave imaging approach is employed for the detection of cracks in such inspection cases. The detection concept using interrogation with dual polarized wave to suppress the background is presented. It is established herein that the cross-polarization measurement is independent to irregular surfaces, and therefore, it constitutes an effective mean for reliable crack detection even if the background is not uniform or if the metal surface is slanted. This fact is further corroborated by numerical electromagnetic simulations and measurements. The efficacy of the proposed method is demonstrated using imaging results of various samples spanning the abovementioned scenarios.

Reinforced concrete surface cracks length detection and length estimation by using digital image processing approach

Surface cracks are a common failure that occurs in reinforced concrete structures (RC). With the help of new technologies, access to crack properties should be easier and help the inspector to provide better results. However, most inspectors still prefer manual visual inspection approach, which leads to inconsistent results when investigating this flaw. Moreover, cracks with inconsistent shapes and irregularities are a difficult task for crack extraction, and inspectors overlook the details of cracks. Therefore, in this study, crack detection and thin crack appearance enhancement using various digital image processing algorithms (DSP) were proposed to improve the accuracy of crack length estimation. By using certain DSP on the captured crack images on RC, several algorithms were created and coded in MATLAB via the morphological approach to produce good quality of the original crack images. At the end of this study, the appearance of the thin crack was improved and helped to improve the estimate of the total length of the crack in pixels. The maximum percentage error between the estimated crack length was calculated and compared to the actual length and was 7.10 %. The surface crack detection algorithm and the has the potential as a helpful structural health monitoring (SHM) tool for crack inspection.

Crack Detection of Asphalt Concrete Using Combined Fracture Mechanics and Digital Image Correlation

Cracking is a common failure mode in asphalt concrete (AC) pavements. Many tests have been developed to characterize the fracture behavior of AC. Accurate crack detection during testing is crucial to describe AC fracture behavior. This paper proposes a framework to detect surface cracks in AC specimens using two-dimensional digital image correlation (DIC). Two significant drawbacks in previous research in this field were addressed. First, a multiseed incremental reliability-guided DIC was proposed to solve the decorrelation issue due to large deformation and discontinuities. The method was validated using synthetic deformed images. A correctly implemented analysis could accurately measure strains up to 450%, even with significant discontinuities (cracks) present in the deformed image. Second, a robust method was developed to detect cracks based on displacement fields. The proposed method uses critical crack tip opening displacement (δc) to define the onset of cleavage fracture. The proposed method relies on well-developed fracture mechanics theory. The proposed threshold δc has a physical meaning and can be easily determined from DIC measurement. The method was validated using an extended finite-element model. The framework was implemented to measure the crack-propagation rate while conducting the Illinois-flexibility index test on two AC mixes. The calculated rates could distinguish mixes based on their cracking potential. The proposed framework could be applied to characterize AC cracking phenomenon, evaluate its fracture properties, assess asphalt mixture testing protocols, and develop theoretical models.

An alternative Rayleigh wave excitation method using an ultrasonic phased array

Ultrasonic Rayleigh waves have been employed for in-service NDT inspection in a wide range of industries for years. The excitation of Rayleigh waves can be achieved using a variety of methods, with the so-called wedge technique being the most widely used. Recent years have seen considerable research interest in surface crack detection and sizing using Rayleigh waves excited and detected with the wedge technique. However, in this method, Rayleigh waves experience transmission loss at the wedge interfaces. Moreover, the flexibility to generate Rayleigh waves on different waveguides using the same wedge is limited, as the wedge angle depends on the Rayleigh wave wavelength. This work demonstrates a method that provides an alternative Rayleigh wave excitation method. In this, a conventional ultrasonic phased array transducer is used. As there is an appropriate excitation delay between each piezoelectric element of the array transducer, Rayleigh waves can be generated in a wide range of materials using the same phased array transducer. The delay can be estimated based on the elementary pitch of the transducer and the Rayleigh wave velocity of the waveguide. The proposed Rayleigh wave excitation method is demonstrated through both experiments and FE simulations. Furthermore, a finite element model is used to better understand the features of the generated waves and to validate them through their characteristics as Rayleigh wave. A quantitative comparison between the proposed and existing methods is also presented. The directivity and beam divergence of the generated Rayleigh waves are quantified. The results obtained from experiments are in agreement with finite element simulations and demonstrate the possibility of unidirectional and selective excitation of Rayleigh waves through the proposed method. They also highlight the potential for this new excitation method to be used to develop new Rayleigh wave-based inspection methods.

Comparison of hit/miss and ‘â versus a’ POD calculations for short surface cracks using inductive thermography

Inductive thermography is an inspection technique that consists of the heating of a sample or a component by short induced eddy current pulses (duration of 50-100 ms) while an infrared camera records the evolution of the surface temperature. Surface cracks in metals can be excellently detected by this inspection technique. Both the eddy currents and the heat diffusion are disturbed by cracks, therefore becoming visible in the infrared images. The recorded image sequence is processed using the Fourier transform, and the resulting phase image is analysed directly by technicians (human-based detection) or developed defect detection algorithms (computer-based), to localize the defects. For industrial applications, the reliability of an inspection technique is very important. This is why it is necessary to calculate the probability of detection (POD) of the technology considered for each case study. The goal of this investigation is to compare the two standard parametric POD calculation techniques, ‘hit/miss’ and ‘â versus a’, for detecting surface cracks with inductive thermography on the nickel-based austenitic superalloy Inconel 718. First, artificial defects are considered for an ‘â vs a’ POD analysis and results are compared to finite element simulations. Additionally, real cracks on TIG welds, created with a Varestraint test machine, have also been considered and corresponding ‘hit/miss’ POD calculations have been performed. However, it is important to note, that the deeper a crack, the larger obstacle it creates for the eddy current and for the heat flow. Hence not only the defect length, but also its depth affects the signal around it. This implies that the calculated POD depends on both the crack length and depth and that in some cases ‘hit/miss’ POD analysis will not be enough.

Detecting Underwater Concrete Cracks with Machine Learning: A Clear Vision of a Murky Problem

This paper presents the development of an underwater crack detection system for structural integrity assessment of submerged structures, such as offshore oil and gas installations, underwater pipelines, underwater foundations for bridges, dams, etc. Our focus is on the use of machine-learning-based approaches. First, a detailed literature review of the state of the current methods for underwater surface crack detection is presented, highlighting challenges and opportunities. An overview of the image augmentation approach for the creation of underwater optical effects is also presented. Experimental results using a standard network-based machine learning approach, which is used for surface crack detection in onshore environments, are presented. A series of test cases is presented in which existing networks’ performance is improved using augmented images for underwater conditions. The effectiveness and accuracy of the proposed approach in detecting cracks in underwater concrete structures are demonstrated. The proposed approach has the potential to improve the safety and reliability of underwater structures and prevent catastrophic failures.

MobileNetV3-BLS: A broad learning approach for automatic concrete surface crack detection

Concrete surface crack detection is an important means to ensure infrastructure security, including bridges and tunnels. In recent years, computer vision has been widely adopted for concrete surface crack detection, and the intelligent crack detection method based on computer vision has achieved good results with the breakthrough of the deep learning algorithm. However, there are also some challenges, such as complex architecture, high computing burden, and time-consuming training. In this paper, a lightweight broad learning system detection method called MobileNetV3-BLS is proposed. First, the inverted residual structure with the linear bottleneck of MobileNetV3 is introduced as the convolution module of the proposed broad learning system for feature extraction. Then the extracted features are employed to randomly generate both mapping and enhancement nodes in a broad learning system, which are used to train the crack detection model. The proposed MobileNetV3-BLS can improve crack detection accuracy and training speed compared with other classical deep learning networks. On the other hand, the proposed method is a dynamic network of which the weights can be updated quickly to achieve incremental learning by adding new nodes and samples.

Intelligent Detection Method for Concrete Dam Surface Cracks Based on Two-Stage Transfer Learning

The timely identification and detection of surface cracks in concrete dams, an important public safety infrastructure, is of great significance in predicting engineering hazards and ensuring dam safety. Due to their low efficiency and accuracy, manual detection methods are gradually being replaced by computer vision techniques, and deep learning semantic segmentation methods have higher accuracy and robustness than traditional image methods. However, the lack of data images and insufficient detection performance remain challenges in concrete dam surface crack detection scenarios. Therefore, this paper proposes an intelligent detection method for concrete dam surface cracks based on two-stage transfer learning. First, relevant domain knowledge is transferred to the target domain using two-stage transfer learning, cross-domain and intradomain learning, allowing the model to be fully trained with a small dataset. Second, the segmentation capability is enhanced by using residual network 50 (ResNet50) as a UNet model feature extraction network to enhance crack feature information extraction. Finally, multilayer parallel residual attention (MPR) is integrated into its jump connection path to improve the focus on critical information for clearer fracture edge segmentation. The results show that the proposed method achieves optimal mIoU and mPA of 88.3% and 92.7%, respectively, among many advanced semantic segmentation models. Compared with the benchmark UNet model, the proposed method improves mIoU and mPA by 4.6% and 3.2%, respectively, reduces FLOPs by 36.7%, improves inference speed by 48.9%, verifies its better segmentation performance on dam face crack images with a low fine crack miss detection rate and clear crack edge segmentation, and achieves an accuracy of over 85.7% in crack area prediction. In summary, the proposed method has higher efficiency and accuracy in concrete dam face crack detection, with greater robustness, and can provide a better alternative or complementary approach to dam safety inspections than the benchmark UNet model.

Wind turbine blades surface crack-detection algorithm based on improved YOLO-v5 model

The integrity of the blade surface is an essential guarantee for the safe operation of wind turbines. It is crucial to research damage detection of blade surface cracks. Based on the improved YOLOv5 model, D-YOLO-v5 is proposed by improving the loss function, objective classification function, and activation function, extending the application of image processing, artificial intelligence, and pattern recognition to investigate intelligent recognition of cracks on the surface of blades. The blade cracks object detection test was completed by LabelImg image annotation, D-YOLO-v5 training parameters adjustment, test parameters selection, prediction model construction, model training, and model prediction steps. The recognition of cracks under different conditions, such as normal light, dark light, and external interference, is subsequently completed. The values indicated that the object detection model parameters of D-YOLO-v5 were neither over-fitted nor under-fitted. In this case study, the accuracy of the blade surface crack-detection model is 98.62%, the mean average precision value is 49.12%, the recall value is 92.20%, and the recognition speed of a single image is 0.01 s. The simulation concludes that the proposed method can meet the accuracy and real-time requirements of practical engineering.

Surface concrete cracks detection and segmentation using transfer learning and multi-resolution image processing

Surface crack detection must be precise and efficient for the structural health monitoring (SHM) of concrete structures. The traditional techniques of crack detection entail human visual examination. These procedures are labor-intensive, expensive, and inefficient. In order to forestall potentially hazardous circumstances caused by concrete surfaces that have deteriorated, it is vital to have an autonomous concrete crack inspection system. Crack detection and segmentation are the two main components of automatic crack inspection. In this research, deep convolutional neural networks (DCNN) and transfer learning (TL) methods are employed for crack detection in concrete structure images, also multiresolution image analysis based on the wavelet transform is the main process in the crack segmentation. The concrete crack dataset is randomly selected from two prevalent concrete crack datasets for developing the proposed method. The results indicated that DCNN classifier models provide good performance with F1-score ranging from 94.5 to 99.6 percent. In addition, the proposed multiresolution image analysis can segment crack pixels with 95.25 percent for the F1-score and shows acceptable and stable performance regarding various segmentation performance metrics.

Research on the surface crack detection of specimen manufactured by selective laser melting based on local singular value decomposition method

SLM (selective laser melting) is an important additive manufacturing technology. Parts with complex structures can be produced by SLM, so surface cracks and other defects within SLM parts are difficult to be identified by traditional nondestructive testing techniques. In this paper, laser ultrasonic technology is proposed to identify the surface crack of SLM specimen. Because of the anisotropy and residual stress of the specimen, the time signal is strongly interfered with by noise, which makes the identification and location of the crack difficult. To solve this problem, the phase space was reconstructed from the time signal and analyzed by the local singular value decomposition method. According to the result of the experiment, this method can reveal the variation of the phase space and has a good effect on the identification and location of the surface crack whose depth is larger than 1 mm.

Reconfigurable Laser-Stimulated Lock-In Thermography for Surface Micro-Crack Detection.

Surface crack detection and sizing is essential for the manufacturing and maintenance of engines, run parts, and other metal elements of aircrafts. Among various non-destructive detection methods, the fully non-contact and non-intrusive technique based on laser-stimulated lock-in thermography (LLT) has recently attracted a lot of attention from the aerospace industry. We propose and demonstrate a system of reconfigurable LLT for three-dimensional surface crack detection in metal alloys. For large area inspection, the multi-spot LLT can speed up the inspection time by a factor of the number of spots. The minimum resolved size of micro-holes is ~50 µm in diameter limited by the magnification of the camera lens. We also study the crack length ranging from 0.8 to 3.4 mm by varying the modulation frequency of LLT. An empirical parameter related to the thermal diffusion length is found to show the linear dependence with the crack length. With the proper calibration, this parameter can be used to predict the sizing of the surface fatigue cracks. Reconfigurable LLT allows us to quickly locate the crack position and accurately measure its dimensions. This method is also applicable to the non-destructive detection of surface or sub-surface defect in other materials used in various industries.

Surface Crack Detection of Steel Structures in Railroad Industry Based on Multi-Model Training Comparison Technique

A method of steel structure surface crack identification based on artificial intelligence technology is proposed to solve the problem that steel cracks can not be detected and forewarned in time when they appear in the railway industrial environment. The appearance of steel cracks greatly weakens the stability of steel structures, and will seriously endanger the safety of the railway industry if it is not detected and repaired in time. However, the common steel crack detection methods cannot achieve real-time monitoring of steel structures. In order to monitor the surface of steel structure in real-time and explore the recognition effect and model the advantages of common classification neural network models for surface cracks of railway industrial steel, this study evaluates the network model with multiple indicators and parameters under two experimental conditions. In this study, the steel surface cracks in the railway industrial environment are taken as samples, and the steel cracks are identified through the neural network model. For large-volume datasets, the recognition accuracy of the three network models has reached 97%, of which the YOLOv5 model has the best comprehensive recognition ability, and the C-Alex model has the best performance and convergence speed in small-volume datasets. This study explores the application prospects of models under different scenarios, proving that the three models can effectively detect steel surface cracks in real-time, and at the same time, it will pave the way for the development and application of artificial intelligence multi-model fusion technology in the field of the railway industry.

Development of a phased array flexible Rayleigh-wave electromagnetic acoustic transducer for pipe inspection

In this paper, a novel Phased Array fully Flexible Rayleigh-wave EMAT (PAFR-EMAT) suitable for inspection of curved surface based on flexible coil bias field magnet EMAT is proposed. The PAFR-EMAT consists of a flexible racetrack coil generating long pulsed bias magnetic field instead of the conventional permanent magnets, and flexible meander coils triggered in sequence to induce transient eddy current for exciting enhanced Rayleigh wave of MHz frequency. Based on the Lorentz force mechanism, pulsed electromagnetic fields and the generated ultrasonic waves of the proposed new EMAT are studied through numerical simulation at first. Experiments are conducted then to check the practical performance of the PAFR-EMAT for pipe inspection. Results show that the PAFR-EMAT has good performance in Rayleigh wave generation for inspection of the curved surface of metallic pipe and is capable to detect surface crack of small depth.

An Integrated Method for Road Crack Segmentation and Surface Feature Quantification under Complex Backgrounds

In the present study, an integrated framework for automatic detection, segmentation, and measurement of road surface cracks is proposed. First, road images are captured, and crack regions are detected based on the fifth version of the You Only Look Once (YOLOv5) algorithm; then, a modified Residual Unity Networking (Res-UNet) algorithm is proposed for accurate segmentation at the pixel level within the crack regions; finally, a novel crack surface feature quantification algorithm is developed to determine the pixels of crack in width and length, respectively. In addition, a road crack dataset containing complex environmental noise is produced. Different shooting distances, angles, and lighting conditions are considered. Validated through the same dataset and compared with You Only Look at CoefficienTs ++ (YOLACT++) and DeepLabv3+, the proposed method shows higher accuracy for crack segmentation under complex backgrounds. Specifically, the crack damage detection based on the YOLOv5 method achieves a mean average precision of 91%; the modified Res-UNet achieves 87% intersection over union (IoU) when segmenting crack pixels, 6.7% higher than the original Res-UNet; and the developed crack surface feature algorithm has an accuracy of 95% in identifying the crack length and a root mean square error of 2.1 pixels in identifying the crack width, with the accuracy being 3% higher in length measurement than that of the traditional method.

A Review of Detection Technologies for Underwater Cracks on Concrete Dam Surfaces

Cracks seriously endanger the safe and stable operation of dams. It is important to detect surface cracks in a timely and accurate manner to ensure the safety and serviceability of a dam. The above-water crack detection technology of dams has been widely studied, but due to the complex underwater environment, above-water crack detection technology on dam surfaces cannot be directly applied to underwater crack detection. To adapt to the underwater detection environment and improve the efficiency and accuracy of underwater crack detection, many methods have been proposed for underwater crack detection, including sensor detection and image detection. This paper presents a systematic overview of the development and application practices of existing underwater crack detection technologies for concrete dams, focusing on methods that use underwater robots as underwater mobile carriers to acquire images that are combined with digital image processing algorithms to identify, locate, and quantify underwater cracks in dams. This method has been widely used for underwater crack detection on dam surfaces with the advantages of being non-contact, non-destructive, having high efficiency, and wide applicability. Finally, this paper looks further forward to the development trends and research challenges of detection technologies for underwater cracks on concrete dam surfaces, which will help researchers to complete further studies on underwater crack detection.