Crack Classification Research Articles

Pavement Crack Classification and Recognition Algorithm Combined With Tensor Voting and RANSAC

Pavement Crack Classification and Recognition Algorithm Combined With Tensor Voting and RANSAC

The Classification of Asphalt Pavement Crack Images Based on Beamlet Transform

Pavement cracking is a common road infrastructure issue which significantly affects road performance, safety and longevity. This article employed a Beamlet Transform algorithm to detect and classify different types of flexible asphalt concrete pavement cracks. Additionally, a dedicated crack segmentation network was employed for precise segmentation of pavement crack. This approach incorporates advancements that has improve precision in crack classification and segmentation. Based on the results of the beamlet transform, significant improvements in the gray scale representation of crack, enhanced crack detection, reduced noise in crack images and a more precise measurement of cracks length were achieved. Computations were performed to determine the length of linear cracks and the area of block cracks. A total of 1000 pavement images were used for training and testing the accuracy of asphalt pavement crack detection and classification models. The research results showed that block cracking, alligator cracking, transverse cracking, and longitudinal cracking can all be recognized with a remarkable accuracy. Alligator cracks and block cracks achieved detection rates more than 90%, while detection rates for the longitudinal and transverse cracks reached more than 95% accuracy.

A pre-failure narrow concrete cracks dataset for engineering structures damage classification and segmentation

Monitoring of structures’ condition plays a fundamental role in providing safety for users and extending the structures’ lifespan. The monitoring is conducted through on-site inspections by engineers thus this process is time-consuming, labor-intensive and prone to subjective engineering opinions. Detecting damage using machine learning algorithms on images can support engineers’ work, especially for early damages which are difficult to see with the human eye. This article is focused on the concrete crack detection problem in engineering structural elements. Despite the availability of several concrete crack detection datasets, no dataset allows semantic segmentation of cracks narrower than 0.3 mm (the crack width limit for typical engineering structures elements and environmental conditions according to EC 1992-1-1) and the ability for crack classification is limited. The provided open dataset represents only cracks below the crack width limit of 0.3mm, which do not yet indicate concrete elements failure. It is dedicated for early crack classification and segmentation, so that damage protection can be taken at an early stage to prevent structural element damages.

Machine learning-based pavement crack detection, classification, and characterization: a review

The detection, classification, and characterization of pavement cracks are critical for maintaining safe road conditions. However, traditional manual inspection methods are slow, costly, and pose risks to inspectors. To address these issues, this article provides a comprehensive overview of state-of-the-art machine vision and machine learning-based techniques for pavement crack detection, classification, and characterization. The paper explores the process flow of these systems, including both machine learning and traditional methodologies. The paper focuses on popular artificial intelligence (AI) techniques like support vector machines (SVM) and neural networks. It underscores the significance of utilizing image processing methods for feature extraction in order to detect cracks. The paper also discusses significant advancements made through deep learning strategies. The main objectives of this research are to improve efficiency and effectiveness in pavement crack detection, reduce inspection costs, and enhance safety. Additionally, the article presents data gathering approaches, various datasets for developing road crack detection models, and compares different models to demonstrate their advantages and limitations. Finally, the paper identifies open challenges in the field and provides valuable insights for future research and development efforts. Overall, this paper highlights the potential of AI-based techniques to revolutionize pavement maintenance practices and significantly improve road safety.

Crack classification and quantitative evaluation based on dimensionality reduction optimization model of multifeature weak magnetic signal

In this paper, we propose a classification and quantitative method based on the optimization model of dimensionality reduction for detecting crack defects in superalloy turbine disks using multifeature weak magnetic signals. First, the experiment on magnetic weak nondestructive testing was conducted on the defects, resulting in the acquisition of 112 sets of preset magnetic anomaly eigenvalue data. The dimensionality of the multidimensional weak magnetic signal features was then reduced using the principal component analysis method to construct the weak magnetic feature sample library. On this basis, a support vector machine (SVM) model was established to classify and quantitatively evaluate the defects. Genetic algorithm and grid search method were used to optimize the model. Finally, the validity of the optimized SVM model was verified by adding artificial and natural crack defect specimens outside of the sample library. Results show that compared with the original model, the feature dimension reduction and optimization of the two methods enhance the classification accuracy of superalloy surface defects and the quantitative accuracy of defect length, width, and depth. The genetic algorithm significantly improved the classification accuracy, increasing it by 39.33 %. Specifically, the genetic algorithm improved the quantitative accuracy of length and width by 17.9 % and 28.56 % respectively. On the other hand, the grid search method improved the quantitative accuracy of depth the most, with an improvement of 49.83 %. For specimens with natural cracks, the optimized SVM model still demonstrated good classification and quantitative effectiveness in detecting defects, with an accuracy rate of over 85 %.

Investigating average infrared radiation temperature characteristics during shear and tensile cracks in sandstone under different water contents

Shear loading and water contents can accelerate rock deformation and fracturing during loading and mining activities. The prediction of the patterns of cracks in rocks under shear loading is thus crucial for the safe and efficient execution of these activities. Previously, crack patterns were classified using Acoustic Emission (AE). Determination of the type of crack patterns on site is not only cumbersome, but may also lead to inaccurate results due improper execution of the AE procedures. Also, there is no proper experimental study which truly reflects the relationship between Average Infrared Radiation Temperature (AIRT) and crack type. In this study, AE and AIRT were used to examine the crack patterns followed by determination of the effect of sandstone crack formation, under varying water and loading conditions, on AIRT. It was found that the increase in water contents lowers AE and strain, and increases shear stress. A linear decrease in AIRT with loading time followed by a sudden increase at the point of failure was observed in dry rocks contrary to a nonlinear trend in rocks with increasing water content. The absolute rate of AIRT increases shear and decrease in tensile crack. Moreover, Shear cracks dominated pre-set shearing tests, and the ratio of acoustic fracturing to radial cracking varied with the level of water contents and loading method. Furthermore, the employed machine learning models (Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM)) demonstrated accurate classification of shear and tensile cracks with both AIRT and RF data. Based on performance metrics i.e., precision, recall, and F1 score, RF fared better than AIRT with performance metrics (precision = 1, recall = 1, and F1 score = 1). The research offered valuable guidelines for experts to predict cracks and rock failure in rocks, aiding efficient relevant engineering project monitoring and execution.

A Novel Road Crack Detection Technology Based on Deep Dictionary Learning and Encoding Networks

Road crack detection is an important indicator of road detection. In real life, it is very meaningful work to detect road cracks. With the rapid development of science and technology, especially computer science and technology, quite a lot of methods have been applied to crack detection. Traditional detection methods rely on manual identification, which is inefficient and prone to errors. In addition, the commonly used image processing methods are affected by many factors, such as illumination, road stains, etc., so the results are unstable. In the research on pavement crack detection, many research studies mainly focus on the recognition and classification of cracks, lacking the analysis of the specific characteristics of cracks, and the feature values of cracks cannot be measured. Starting from the deep learning method in computer science and technology, this paper proposes a road crack detection technology based on deep learning. It relies on a new deep dictionary learning and encoding network DDLCN, establishes a new activation function MeLU, and adopts a new differentiable calculation method. The technology relies on the traditional Mask-RCNN algorithm and is implemented after improvement. In the comparison of evaluation indicators, the values of recall, precision, and F1-score reflect certain superiority. Experiments show that the proposed method has good implementability and performance in road crack detection and crack feature measurement.

Research on crack classification method and failure precursor index based on RA-AF value of brittle rock

The mechanical and AE information of the whole process of rock damage and fracture are obtained by uniaxial compression test, Brazil splitting test and improved shear test on marble, granite, limestone and sandstone. The internal relationship between the damage and failure mechanism of brittle rock and AE signal is revealed based on these tests. Moreover, in this paper, the improved shear test is used to replace the traditional direct shear test to avoid the interference of the traditional direct shear test on AE signal acquisition. The experimental results show that the rock fracture process has an obvious piecewise variation characteristic and a significant increasing period. A variety of AE signals are screened by coupling the main frequency and its amplitude, and the values of b and CV (r) can be used as the precursor signals of rock critical failure. Based on KDE method and K-means algorithm, the AE data (RA-AF values) collected in Brazil splitting test and improved shear test are coupled to determine the tensile and shear crack boundaries of four kinds of rocks. Based on the determined boundary of AE data between tensile and shear cracks, the corresponding precursor index CV (r) of rock failure is proposed. When the value of CV (r) increases to more than 1, the rock is close to failure or failure has occurred.

Feature extraction and classification of multiple cracks from raw vibrational responses of composite beams using 1D-CNN network

Structures and components need to be constantly monitored to ensure good service life and avoid failures. Structural health monitoring is a wide-ranging concept that tries to ensure the safety of components and structures. Vibration responses of small and large structures contain information about these damages. In the present study, this information is extracted and used to classify the location and severity of cracks. For this purpose, an FE model of Glass Fibre Reinforced Plastic (GFRP) free-free beam is created for beams without any crack and beams with three crack locations and three crack severities. Finite Element (FE) model is validated using modal analysis and is used to generate vibration responses from simulated hammer strikes at different locations on the beam. The vibration data consists of responses of beams that have only one crack present at a time and when two cracks are present. A 1D-CNN network is trained on the generated vibrational responses to classify damage labels assigned for each crack location and crack severity. The network was tested using datasets containing only single crack instances and only dual crack instances. The trained networks were found to be 95% and 93% accurate in determining the damage class respectively. Furthermore, datasets of these two instances combined, containing responses when single cracks and dual cracks are present, were also investigated. These networks had an accuracy of 92%. Hence, in all these instances, the 1D-CNN network classifies the healthy and damaged conditions satisfactorily. There are two advantages of using such a technique. Firstly, this approach simplifies the two-step approach: one for feature extraction and another one for damage prediction into a single step. Secondly, the use of raw vibration data for damage prediction means that real-time damage detection is possible.

Eddy Currents Assessment of Rail Cracks Using Artificial Neural Networks in a Laboratory Setup

Although flaws associated with rolling contact fatigue (RCF) and the corresponding traffic induced damage, which are a cause of failure in railways, have been of great concern in railway system maintenance and safety strategies in many countries for at least two decades, this serious problem has not been yet adequately tackled in the Argentine railway system. The present upgrading activities undertaken in the Argentine railway system (in infrastructure and in rolling stock) are prompting the need for R&D in non-destructive testing techniques and procedures, to satisfy requirements of the new rolling stock and to ensure safe and economic operation of passengers and cargo. RCF damage appears as surface and near surface defects and grows into cracks which in time will propagate along the running surface and through the cross-section. Eddy current testing (ET) is a very efficient in-service inspection method for this task, the near field technique being especially recommended for ferromagnetic components.
 In the present paper, an artificial neural network (ANN) method for automatic classification of flaws with lift-off compensation is presented and tested. The tests consist on the ET evaluation of right angle artificial cracks on a rail calibration coupon; the depth of the cracks studied ranged from 1 to 7 mm. The technique permitted to compensate the weakening of the signals caused by the lift-off effect, allowing signal cracks classification with lift-off variations of up to 5.4 mm.
 The effect of crack skewness on the ET signals is also studied. Because the RCF cracks penetrate the rail at oblique angles, (10° to 30° to the rolling surface), an additional uncertainty component is added to the experiments if calibration is made with a piece having perpendicular cracks. In order to estimate this additional uncertainty on the ANN method presented here, further tests were made with a second calibration piece with cracks at 25° to the surface. Comparison of results showed that the peak to peak amplitudes for both types of cracks are not equivalent at all the tested depths.

A Machine Learning Approach for Simultaneous Classification of Material Types and Cracks

Exterior structures are susceptible to deformation, which can manifest as cracks on the surface. Deformations that occur on surfaces subjected to daily human use can exacerbate rapidly, potentially leading to irreversible structural damage. They have a potential to result in fatalities. Thus, continuous inspection of these deformations is of invaluable importance. In addition, the identification of the materials comprising the structures is essential to facilitate the implementation of appropriate precautionary measures. However, the inspections are hard to maintain with a solely human workforce. More advanced actions can be taken thanks to the developments in technology. Machine Learning methods could be used in this area where human workforce is ineffective. In this regard, an end-to-end Machine Learning approach was proposed in this study. The power of classical feature extraction methods and Artificial Neural Networks were combined to detect cracks and material of the surface simultaneously. The 2D Discrete Wavelet Transform and statistical properties gained from Gray Level Co-Occurrence Matrix were utilized in the feature extraction mechanism, and an ANN structure was designed. The findings of the study indicate that the proposed mechanism achieved an acceptable level of accuracy for recognizing the structural deformations, despite the challenges posed by the complexity of the problem.

Data-driven approach for AI-based crack detection: techniques, challenges, and future scope

This article provides a systematic literature review on the application of artificial intelligence (AI) technology for detecting cracks in civil infrastructure, which is a critical issue affecting the performance and longevity of these structures. Traditional crack detection methods involve manual inspection, which is laborious and time-consuming, especially in urban areas. Therefore, automatic crack detection with AI technology has gained popularity due to its ability to identify degradation of roads in real-time, leading to increased safety and reliability. This review emphasizes two key approaches for crack detection: deep learning and traditional computer vision, with a focus on data-driven aspects that rely primarily on data from training datasets to detect and quantify the severity level of the crack. The article highlights the advantages and drawbacks of each approach and provides an overview of various crack detection models, feature extraction techniques, datasets, potential issues, and future directions. The research concludes that deep learning-based methods used for crack classification, localization and segmentation have shown better performance than traditional computer vision techniques, especially in terms of accuracy. However, deep learning methods require large amounts of training data and computational power, which can be a significant limitation. Additionally, the article identifies a lack of 3D datasets, unsupervised learning algorithms are rarely used to train crack detection model, and datasets having road images with variety of road textures such as asphalt and cement etc. as challenges for future research in this field. A need for 3D and combined texture datasets as challenges for future research in this field.

Image-based Concrete Cracks Identification under Complex Background with Lightweight Convolutional Neural Network

Cracks are important indexes to evaluate the health status of concrete structures. To accurately and automatically identify the cracks of concrete structures, and solve the time-consuming and labor-intensive limits of manual detection methods, this paper proposed an image-based concrete cracks identification method based on a lightweight Convolutional Neural Network, which includes three modules: crack classification, semantic segmentation and quantitative calculation of crack geometric size. Firstly, the S_MobileNet was used to classify cracks, exclude irrelevant regions, and reduce the interference of non-crack images; Secondly, the optimized method SM-UNet based on the U-Net network was employed to segment the detected crack image at the pixel level; Finally, based on the results of crack semantic segmentation, image post-processing technology was used to realize the quantitative calculation of crack geometric size parameters, which provides a basis for crack damage assessment of concrete structures. The experimental results show that this study provides a solution for the automatic detection of crack images and high-precision measurement of crack size, which has an important value in scientific research and engineering application.

Threshold-Based BRISQUE-Assisted Deep Learning for Enhancing Crack Detection in Concrete Structures.

Automated visual inspection has made significant advancements in the detection of cracks on the surfaces of concrete structures. However, low-quality images significantly affect the classification performance of convolutional neural networks (CNNs). Therefore, it is essential to evaluate the suitability of image datasets used in deep learning models, like Visual Geometry Group 16 (VGG16), for accurate crack detection. This study explores the sensitivity of the BRISQUE method to different types of image degradations, such as Gaussian noise and Gaussian blur. By evaluating the performance of the VGG16 model on these degraded datasets with varying levels of noise and blur, a correlation is established between image degradation and BRISQUE scores. The results demonstrate that images with lower BRISQUE scores achieve higher accuracy, F1 score, and Matthew's correlation coefficient (MCC) in crack classification. The study proposes the implementation of a BRISQUE score threshold (BT) to optimise training and testing times, leading to reduced computational costs. These findings have significant implications for enhancing accuracy and reliability in automated visual inspection systems for crack detection and structural health monitoring (SHM).

Hybrid-Input FCN-CNN-SE for Industrial Applications: Classification of Longitudinal Cracks during Continuous Casting

In the presented research, machine learning methods were applied to the prediction of longitudinal cracks in steel slabs during continuous casting. We employ a deep learning approach to process 68 thermocouple signals as a multivariate time series (MTS) along with 32 static features, which encompass both chemical composition and process information. Our deep learning approach integrates two distinct parallel modules, followed by an aggregation block; a Convolutional Neural Network (CNN) processes the thermocouple MTS, while in parallel, the static data undergo processing via a Fully Connected Network (FCN). To enhance the performance of the CNN, we incorporate two Squeeze and Excitation (SE) blocks, which act as an attention mechanism across different channels. By integrating chemical information with MTS in the detection system, we improve the performance of defect detection by 15% relatively.

Extended efficient convolutional neural network for concrete crack detection with illustrated merits

An efficient convolutional neural network (CNN), called EfficientNetV2, was recently developed. The early blocks of EfficientNetV2 have structural characteristics that lead to higher training speeds than state-of-the-art CNNs. Inspired by EfficientNetV2, extended research was conducted in this study to determine whether the early, middle, and late blocks of CNNs should have respective structural characteristics to achieve higher efficiency. Based on comprehensive studies, three tactics were proposed, which underpinned a swift CNN called StairNet. StairNet was subsequently equipped into faster region-based CNN framework, producing Faster R-Stair. The presented StairNet and Faster R-Stair were validated on two datasets, respectively: Dataset1 comprising a pair of open-source datasets and a dataset of images captured in real-world conditions; Dataset2 derived from Dataset1, consisting of more complicated object modes, with the purpose of mimicking the coexistence of multiple cracks under real conditions. Experimental results showed that StairNet outperforms EfficientNetV2, GoogLeNet, VGG16_BN, ResNet34, and MobileNetV3 in efficiency of crack classification and detection. A Faster R-Stair concrete crack-detection software platform was also developed. The software platform and an unmanned aerial vehicle were used to detect concrete road cracks at a university in Nanjing, China. The developed system has a swift detection process, with high speed and excellent results.

Cracks Classification using Acoustic Emission Technique on a Reinforced Concrete Beam

The usage of non-destructive techniques for structure's state assessment is highly desirable because they offer the possibility to monitor continuously and in a non-invasive manner the sign of failures of any structure. Among the several techniques proposed over the years, Acoustic Emission (AE) seems very promising. Such a technique, which applies to various materials, consents to the evaluation of micro-fractures generated during failure by detecting their acoustic emission through sensors located on the surface of the material itself. Concrete beam failure is suitable for such kind of procedure. It has been widely investigated through AE, but despite the many literature contributes, there still is a scarcity of practical applications on real structures, and no consensus on protocols. In this work, an AE technique has been paired with a four-point bending test to try and find a robust and reliable experimental setup for AE application on concrete beams. Results show a proper classification of the occurring cracks, which change according to different zones of the concrete beam and different load values. Axial crack signals exhibit different features concerning shear crack ones. In such a way, the categorization of damages can be performed and crosschecked with the theoretical expectations. All these results suggest that the proposed setup can be used as a possible protocol for practical AE measurements.

Assessment of crack severity of asphalt pavements using deep learning algorithms and geospatial system

Applications of Artificial Intelligence (AI), Deep Learning (DL), and Machine Learning (ML) are becoming common in the field of civil and infrastructure engineering. This paper proposes an innovative asphalt pavement health monitoring framework based on state-of-the-art deep learning algorithms, a convenient data collection strategy, a novel crack width calculation algorithm, and a novel geolocation-based crack visualization method. Furthermore, this paper introduces a 2000-image (1440 × 1440) dataset for crack classification, an 8000 image dataset (360 × 360) dataset and another dataset with manually segmented images. Transfer learning based DL model achieved a validation accuracy of 99%. A novel crack width calculation algorithm is proposed based on the skeletonization and gradient calculation on binary images to quantify the severity of the crack. Locations of the cracked surface positions were identified using geotagged images, and a geospatial mapping method was proposed to visualize the crack locations for health monitoring and maintenance purposes.

Tunnel Lining Crack Recognition Algorithm Integrating SK Attention and Cascade Neural Network

Cracks are one of the main types of tunnel-lining defects. At present, there are no particularly good methods for identifying tunnel-lining cracks. The methods that are used are associated with problems such as poor robustness, low detection efficiency, and inconsistency in defect identification. Vision-based crack identification algorithms that use images of tunnel-lining cracks are also affected by problems such as weak features, irregular shapes, random development, and small proportions. In light of this, we propose in this paper a neural network that integrates U-net and FPN (feature pyramid network) pyramid structure characteristics. Because of its ability to output deep feature information, an SK (selective kernel) attention mechanism was integrated to increase the weight of effective feature regions and improve the detection accuracy of feature maps. An RPN (region proposal network) regional detection network was used for multi-scale regional screening, and non-maximum suppression was used to eliminate repeated anchor frames between different regions. The continuity of cracks was determined using adaptive regional expansion. The region segmentation network was also combined with multi-scale feature maps. Finally, the segmentation results for regions of fine features could be mapped to the whole image to identify cracks, thereby solving the problem that arises when textural features of cracks are weak and cannot be accurately identified. For testing purposes, photos of tunnel-lining crack defects were used. The algorithm described in this paper was able to combine deep and shallow features to identify more abundant crack features, and the recognition accuracy of the crack classification network reached 98.51%. With respect to crack segmentation, the algorithm’s segmentation accuracy reached 94.55%, and its single processing time reached 60.76 ms, indicating more accurate and efficient segmentation performance, compared with FCNs (fully convolutional networks) and classical U-net networks.

Effect of Loading Rate on the Progressive Damage and Crack Classification of Granite Based on Acoustic Emission Technique

Effect of Loading Rate on the Progressive Damage and Crack Classification of Granite Based on Acoustic Emission Technique