Crack Inspection Research Articles

Setting Adaptive Inspection Intervals in Helicopter Components, Based on a Digital Twin

Setting inspection intervals based on an accurate prediction of fatigue crack sizes is essential for sustaining the integrity of aeronautical structures. However, the fatigue crack growth and its prognosis are affected by various uncertainties, which makes the current inspection strategy with fixed intervals challenging in managing the aircraft with diverse damage states in a fleet. In this study, an intelligent crack inspection strategy is proposed based on a digital twin, in which a reduced-order fracture mechanics simulation methodology, a validated fatigue crack growth model, and the historical crack length inspection results are integrated into a dynamic Bayesian network. The proposed strategy uses two connected probabilistic processes, which conduct the diagnosis/prognosis and calculate the inspection intervals, respectively, to adaptively set the inspection intervals according to the updating of the digital twin model. The proposed inspection strategy is demonstrated by the various crack growth histories of a helicopter component and benchmarked against several baselines. The results show that the probability of failure can be kept below the threshold, even though the initial crack size and the crack growth parameters are underestimated in the prior distribution. Further applications on more realistic aircraft structures will be carried out in the future.

Research on Automatic Pavement Crack Recognition Based on the Mask R-CNN Model

Pavement will inevitably be damaged in the process of use; pavement damage detection and assessment are an important part of maintenance management. In order to prevent road diseases, it is necessary to fix the road cracks and implement automatic road crack inspection and monitoring. In this paper, the automatic identification of road cracks is realized by constructing the Mask R-CNN model. The labeled area can be segmented by pixels and positioned at the original data by integrating the image data used for training and the labeled data into a network model. The effect of the training model can be improved by increasing the number of data sets, the pixel of the fracture image, the background of the fracture, and the marking method of the fracture type. The validity and accuracy of the test results were characterized by RPN bounding-box loss, classification loss, mask loss, and total loss.

Wind Turbine Crack Inspection Using a Quadrotor With Image Motion Blur Avoided

The camera-equipped quadrotor is a preferable choice for wind turbine blade (WTB) crack inspection applications with the benefits of high portability and low cost. Unfortunately, the high speed of the quadrotor might cause image motion blur which leads to a crack detection failure. Recent works cope with this by adopting the advanced camera systems or image deblurring techniques, which, however, usually require additional hardware or extra computational load. In this paper, the crack detection failure problem caused by image motion blur is handled by means of quadrotor motion control. First, the desired speed range that can avoid the detection failure caused by the image motion blur is experimentally obtained. Then, a speed regulation controller is developed to regulate the quadrotor flying speed within the obtained range. Experimental studies for crack inspection of a WTB using a camera-equipped quadrotor under wind condition are carried out to validate the effectiveness of the proposed strategy. Compared to the traditional approach without image motion blur avoidance, with the same inspection assignment and wind condition, the proposed method can obtain better quality images with 4.08 higher peak signal-to-noise ratio (PSNR) and 0.1 higher structural similarity index (SSIM) on average, where PSNR and SSIM are two typical image quality assessment metrics. As a result, the crack detection failure problem is avoided and a successful WTB crack inspection is achieved.

Binocular video-based 3D reconstruction and length quantification of cracks in concrete structures

In the past few years, image-based methods for crack inspection have been developed to reduce the cost of the manual crack inspection. However, current image-based methods usually obtain only localized planar crack detection results, while global location and three-dimensional (3D) geometric information of the crack is desired to evaluate the whole structure. In addition, automatic quantification of the actual sizes of all cracks in the global structure is a challenge to overcome. To address these issues, this paper develops an automated 3D reconstruction and length quantification framework for cracks in concrete structures based on binocular videos. In the proposed framework, a crack semantic 3D reconstruction method, combined with binocular visual simultaneous localization and mapping (VSLAM) and a high-performance segmentation network, is first proposed to achieve accurate crack 3D characterization and global localization. A 3D crack quantification method based on point cloud processing is also developed to accurately identify individual cracks on the global structure and quantify their lengths. Field tests are conducted on a concrete bridge to demonstrate the automated inspection framework, which shows high efficiency and practicability. The accuracy of crack detection and quantification of the proposed method is also validated against the results of manual inspection.

Bridge Crack Segmentation Method Based on Parallel Attention Mechanism and Multi-Scale Features Fusion

Regular inspection of bridge cracks is crucial to bridge maintenance and repair. The traditional manual crack detection methods are time-consuming, dangerous and subjective. At the same time, for the existing mainstream vision-based automatic crack detection algorithms, it is challenging to detect fine cracks and balance the detection accuracy and speed. Therefore, this paper proposes a new bridge crack segmentation method based on parallel attention mechanism and multi-scale features fusion on top of the DeeplabV3+ network framework. First, the improved lightweight MobileNet-v2 network and dilated separable convolution are integrated into the original DeeplabV3+ network to improve the original backbone network Xception and atrous spatial pyramid pooling (ASPP) module, respectively, dramatically reducing the number of parameters in the network and accelerates the training and prediction speed of the model. Moreover, we introduce the parallel attention mechanism into the encoding and decoding stages. The attention to the crack regions can be enhanced from the aspects of both channel and spatial parts and significantly suppress the interference of various noises. Finally, we further improve the detection performance of the model for fine cracks by introducing a multi-scale features fusion module. Our research results are validated on the self-made dataset. The experiments show that our method is more accurate than other methods. Its intersection of union (IoU) and F1-score (F1) are increased to 77.96% and 87.57%, respectively. In addition, the number of parameters is only 4.10 M, which is much smaller than the original network; also, the frames per second (FPS) is increased to 15 frames/s. The results prove that the proposed method fits well the requirements of rapid and accurate detection of bridge cracks and is superior to other methods.

Developing a Free and Open-Source Semi-Automated Building Exterior Crack Inspection Software for Construction and Facility Managers

Developing a Free and Open-Source Semi-Automated Building Exterior Crack Inspection Software for Construction and Facility Managers

Analysis for Gesture Input on Crack Inspection Support System

Analysis for Gesture Input on Crack Inspection Support System

Welding defect detection in nuclear power plant spent fuel pool panels based on alternating current field measurement: experimental and finite element analysis

The overlay panels of spent fuel pools of nuclear power plants can easily become corroded and produce micro-crack defects. Surface crack defects tend to expand vertically, horizontally and obliquely, causing damage and fracture to the overlay panels and welds of spent fuel pools. Traditional non-destructive testing (NDT) cannot complete underwater testing in real time. In order to improve the timeliness of crack detection and shorten the inspection period, research on accurate inspection technology for surface cracks in the overlay panels of spent fuel pools is carried out in this paper based on alternating current field measurement (ACFM) and the weld defect detection process for the cladding panels of spent pools is optimised. In this work, different types of artificial defect are assumed and the distortion of the magnetic field characteristic signal caused by the defects is studied. The characteristics of magnetic field signals generated in different defect regions are studied by establishing a defect electromagnetic detection model for numerical calculation. Finally, experimental and numerical results are compared and analysed. The results show that ACFM can be used to quickly and effectively inspect for cracks in the base material, weld and interface of spent fuel pool overlay panels and it has the characteristics of accuracy, high resolution, high sensitivity and low delay. The research results, which have good application value, provide technical support for electromagnetic inspection of latent cracks in field spent fuel pools and early crack warning of underwater structural defects.

The ability of different types of sand to preserve the integrity of calcium sulfoaluminate cement cement mortar during exposure to elevated temperatures

Abstract Due to the depletion of natural sand resources, it is urgent to develop synthetic sand that will replace the natural one in the production of concrete. In this study, we carried out descriptive inspection of mortar working performance, mechanical properties and internal cracking under three different application schemes of fine aggregate, including natural, artificial, and basalt sand. Tests showed that the mortar with river sand had more internal cracking and lowest strength as the temperature rises. The artificial and basalt sand had better resistance and less internal cracking than river sand at high temperature. The compressive strength of basalt sand mortar (BSM) was slightly higher than that of artificial sand mortar (ASM), while the compressive strength value of river sand mortar (RSM) was the lowest at room temperature. However, when heated to 100°C, the RSM had 48% loss of strength, followed by the BSM at 45.4% and ASM at 11.6%. Above 100°C, none of the mortar samples meet the requirement of the calcium sulfoaluminate cement 42.5. The average atomic ratios (Ca/Si, Ca/Al, and Ca/Si) for the ASM and BSM increased with the rise in temperature. XRD showed that above 100°C, the diffraction peaks of Ettringite (AFt) disappeared, the number of CaSO4 diffraction peaks decreased significantly, the intensity decreased, and a diffraction peak of CaCO3 appeared.

Fatigue reliability analysis of bridge crane metal structure considering maintenance

Periodic inspection and maintenance of cracks have great influence on the reliability and safety of metal structures of bridge cranes. However, the influence of maintenance factors on the fatigue reliability of in-service bridge cranes is rarely considered at present. Taking a metal structure of a certain type bridge crane as an example, this paper establishes the limit state equation according to the residual strength of the structure. Considering the reduction of section modulus by fatigue cracks, the influence of periodic inspection and maintenance is quantitatively analyzed. The fatigue reliability of metal structure of bridge crane is analyzed and calculated by using MATLAB program. The results show that the fatigue damage will lead to the continuous decrease of reliability, and the fatigue reliability of metal structure can be restored to a certain extent by considering maintenance, which delays the decrease of reliability.

Automatic Pavement Crack Detection Fusing Attention Mechanism

Pavement cracks can result in the degradation of pavement performance. Due to the lack of timely inspection and reparation for the pavement cracks, with the development of cracks, the safety and service life of the pavement can be decreased. To curb the development of pavement cracks, detecting these cracks accurately plays an important role. In this paper, an automatic pavement crack detection method is proposed. For achieving real-time inspection, the YOLOV5 was selected as the base model. Due to the small size of the pavement cracks, the accuracy of most of the pavement crack deep learning-based methods cannot reach a high degree. To further improve the accuracy of those kind of methods, attention modules were employed. Based on the self-building datasets collected in Linyi city, the performance among various crack detection models was evaluated. The results showed that adding attention modules can effectively enhance the ability of crack detection. The precision of YOLOV5-CoordAtt reaches 95.27%. It was higher than other conventional and deep learning methods. According to the pictures of the results, the proposed methods can detect accurately under various situations.

Three-Stage Pavement Crack Localization and Segmentation Algorithm Based on Digital Image Processing and Deep Learning Techniques.

The image of expressway asphalt pavement crack disease obtained by a three-dimensional line scan laser is easily affected by external factors such as uneven illumination distribution, environmental noise, occlusion shadow, and foreign bodies on the pavement. To locate and extract cracks accurately and efficiently, this article proposes a three-stage asphalt pavement crack location and segmentation method based on traditional digital image processing technology and deep learning methods. In the first stage of this method, the guided filtering and Retinex methods are used to preprocess the asphalt pavement crack image. The processed image removes redundant noise information and improves the brightness. At the information entropy level, it is 63% higher than the unpreprocessed image. In the second stage, the newly proposed YOLO-SAMT target detection model is used to locate the crack diseases in asphalt pavement. The model is 5.42 percentage points higher than the original YOLOv7 model on mAP@0.5, which enhances the recognition and location ability of crack diseases and reduces the calculation amount for the extraction of crack contour in the next stage. In the third stage, the improved k-means clustering algorithm is used to extract cracks. Compared with the traditional k-means clustering algorithm, this method improves the accuracy by 7.34 percentage points, the true rate by 6.57 percentage points, and the false positive rate by 18.32 percentage points to better extract the crack contour. To sum up, the method proposed in this article improves the quality of the pavement disease image, enhances the ability to identify and locate cracks, reduces the amount of calculation, improves the accuracy of crack contour extraction, and provides a new solution for highway crack inspection.

Efficient and Adaptable Patch-Based Crack Detection

Road crack inspection is an important process to maintain the quality of roads for safety issues. The manual road inspection is laborious and time consuming. Thus, an automatic road crack detection is essential to make the inspection process easier and faster. Normally, this crack detection is conducted in real-time with low power computational devices and limited memory. Consequently, many former approaches adopted the patch-based approach to reduce computation for single forward, where the input image is divided into several non-overlapping patches. The generated patches are processed by independent CNN models to capture the crack position. Yet, this approach can lead to disintegrating issues because each patch is processed independently when the CNN fails to detect some patches of the crack. In this study, the improved patch-based crack detector is proposed, and the global patch analyzer is adopted to handle the above issue by considering the relation of each patch processing. Moreover, the proposed model also involves more features such as multiple decoder design and automatic resource mapper to yield superior results than that of the state-of-the-art methods in terms of the speed and accuracy as examined by extensive experiments.

Concrete Crack Quantification Using Voxel-Based Reconstruction and Bayesian Data Fusion

Concrete cracks are one of the most apparent indicators for possible structural deterioration and need to be periodically inspected. However, for current image-based automated crack inspection techniques, accurate and detailed crack quantification and assessment remain a challenging task. Most of these techniques require high-quality input images, which may be difficult to ensure in practice. Besides, simply merging crack detections from multiple images to generate a large crack map may result in an inaccurate outcome for crack severity assessment. In this article, a novel crack quantification framework is proposed to identify complete crack geometric properties utilizing a set of unordered inspection images. To realize this, cracks in images are detected by an instance segmentation convolutional neural network. Subsequently, the crack segmentations from multiple separate images are systematically aggregated through voxel-based reconstruction and Bayesian data fusion. This framework outputs a crack model that can retrieve accurate geometric properties of each crack segment by recognizing the crack's inherent branching patterns. The capability and performance of the proposed crack quantification framework are validated on cracked concrete specimens in a laboratory setting. Also, a field test on a cracked concrete wall was carried out using images captured by a UAV to demonstrate the efficacy of the proposed framework in practical conditions.

Pavement crack measurement based on aerial 3D reconstruction and learning-based segmentation method

Rapid inspection of urban road cracks is vital to maintain traffic smoothness and ensure traffic safety. A rapid pavement crack inspection method uses low-altitude aerial images captured by an unmanned aerial system (UAS) and deep-learning aided 3D reconstruction, and a learning-based object segmentation algorithm is proposed to measure road cracks automatically. The contributions include: (a) An efficient 3D reconstruction method for low-altitude aerial images captured by a UAS is proposed, which applies an instance segmentation network to segment road targets from raw images with complex backgrounds first and then performs structure from motion to reconstruct a large-scale road orthophoto from a large number of aerial images. (b) To detect cracks from the reconstructed large-size road orthophoto, a sliding window algorithm and U-Net model optimized with a transformer structure are used to automatically identify and segment the cracks from the orthophoto at the pixel level. Then, a connected domain feature analysis method is used to measure the road crack length. The proposed method is applied to detection of road cracks in a 1.5 km2 area of a city. The results show that the proposed method can effectively and accurately detect cracks and measure the length of cracks in the 4-km-long road, which proves the practicality of the proposed method.

Towards Robotic Marble Resin Application: Crack Detection on Marble Using Deep Learning

Cracks can occur on different surfaces such as buildings, roads, aircrafts, etc. The manual inspection of cracks is time-consuming and prone to human error. Machine vision has been used for decades to detect defects in materials in production lines. However, the detection or segmentation of cracks on a randomly textured surface, such as marble, has not been sufficiently investigated. This work provides an up-to-date systematic and exhaustive study on marble crack segmentation with color images based on deep learning (DL) techniques. The authors conducted a performance evaluation of 112 DL segmentation models with red–green–blue (RGB) marble slab images using five-fold cross-validation, providing consistent evaluation metrics in terms of Intersection over Union (IoU), precision, recall and F1 score to identify the segmentation challenges related to marble cracks’ physiology. Comparative results reveal the FPN model as the most efficient architecture, scoring 71.35% mean IoU, and SE-ResNet as the most effective feature extraction network family. The results indicate the importance of selecting the appropriate Loss function and backbone network, underline the challenges related to the marble crack segmentation problem, and pose an important step towards the robotic automation of crack segmentation and simultaneous resin application to heal cracks in marble-processing plants.

Novel phase reversal feature for inspection of cracks using multi-frequency alternating current field measurement technique

Aluminum and its alloys have been widely used in aerospace and other industrial fields. Aluminum and its alloy structures are prone to surface and subsurface cracks when they are used in harsh environments. In this paper, a novel phase reversal feature is found to classify and evaluate cracks using the multi-frequency alternating current field measurement (ACFM) technique. The theoretical model of the phase reversal feature is developed. The distorted electromagnetic fields and response signals of surface and subsurface cracks are analyzed by the finite element method. The multi-frequency ACFM testing system is set up. The experiments are carried out to test surface and subsurface cracks. The results show that the response signals of the surface and subsurface cracks have distinct characteristic due to the phase reversal feature using the multi-frequency ACFM technique. The surface and subsurface cracks can be classified by the amplitude reversal phenomenon of the Bz signal caused by the novel phase reversal feature. The buried depth of the subsurface crack can be evaluated accurately by the reversal frequency component.

In Situ Investigation of Hydrogen-Induced Cracking Behavior in Linepipe Steel Under Different Environments

NACE MR0175/ISO 15156 provides the severity of a sour environment defined as a function of pH and H2S partial pressure for sulfide stress cracking. Although hydrogen-induced cracking (HIC) is also a major issue of linepipes exposed to a sour environment, the severity diagram does not necessarily correspond to the HIC susceptibility. Recently, from the viewpoint of fitness-of-purpose, the severity diagrams for HIC have been proposed based on the concept of equal hydrogen concentration. From this concept, HIC susceptibility corresponds well to the steady-state hydrogen permeability obtained from the hydrogen permeation test method. In this study, in order to clarify the relationship between HIC susceptibility and hydrogen diffusion behavior, in situ crack inspection during the HIC test and finite element method analysis of hydrogen diffusion were performed. The in situ inspection technique using phased-array ultrasonic testing which can capture the time dependence of crack distribution, and HIC initiation and propagation behaviors were clearly visualized and investigated. It was found that crack initiation and propagation stabilize as hydrogen concentration reaches a steady-state value throughout the specimen and the result was considered evidence that the HIC susceptibility corresponded with the steady value of hydrogen permeability.

FAECCD-CNet: Fast Automotive Engine Components Crack Detection and Classification Using ConvNet on Images

Crack inspections of automotive engine components are usually conducted manually; this is often tedious, with a high degree of subjectivity and cost. Therefore, establishing a robust and efficient method will improve the accuracy and minimize the subjectivity of the inspection. This paper presents a robust approach towards crack classification, using transfer learning and fine-tuning to train a pre-trained ConvNet model. Two deep convolutional neural network (DCNN) approaches to training a crack classifier—namely, via (1) a Light ConvNet architecture from scratch, and (2) fined-tuned and transfer learning top layers of the ConvNet architectures of AlexNet, InceptionV3, and MobileNet—are investigated. Data augmentation was utilized to minimize over-fitting caused by an imbalanced and inadequate training sample. Data augmentation improved the accuracy index by 4%, 5%, 7%, and 4%, respectively, for the proposed four approaches. The transfer learning and fine-tuning approach achieved better recall and precision scores. The transfer learning approach using the fine-tuned features of MobileNet attained better classification accuracy and is thus proposed for the training of crack classifiers. Moreover, we employed an up-to-date YOLOv5s object detector with transfer learning to detect the crack region. We obtained a mean average precision (mAP) of 91.20% on the validation set, indicating that the model effectively distinguished diverse engine part cracks.

Rail Sample Laboratory Evaluation of Eddy Current Rail Inspection Sustainable System

Increasing the efficiency, frequency, and speed of rail defect detection can reduce maintenance costs and improve the sustainability of railways. The non-contact eddy current (EC) system can be operated along with a railcar for detecting rail flaws. Even if the EC can be utilized for rail defect identification and characterization, current commercial devices are not sufficient for defect classification on rails by providing highly sensitive signals for post-processing. In this study, we established an efficient and expandable eddy current rail inspection system and verified its capability for classification of different defect signals. The integrated hardware and software EC measurement system was firstly applied to detect notched cracks in steel samples with different crack depths and angles. The measured voltage and current analog inputs from the eddy current sensor were acquired and processed with a fast Fourier transformation (FFT) algorithm in the LabVIEW platform. The real-time impedance was then obtained by transferring signals to a normalized impedance plane plot. The processed EC signals showed adequate sensitivity and efficiency with changes of notched crack depths and angles during the sensor movement. A comparative case study on field rail samples was then conducted to examine the feasibility and capability of the established system on different types of actual rail defects. The experimental analysis and case study results demonstrate that the integrated eddy current system could possibly be used for non-destructive rail crack inspection and classification. The enhanced detection capability (especially on subsurface cracks) and real-time post-processing technique could further contribute to improving rail-life sustainability.