Cracking In Asphalt Pavements Research Articles

A grid‐based classification and box‐based detection fusion model for asphalt pavement crack

AbstractCrack identification is essential for the preventive maintenance of asphalt pavement. Through periodic inspection, the characteristics of existing and emerging cracks can be obtained, and the pavement condition index can be calculated to assess pavement health. The most common method to estimate the area of cracks in an image is to count the number of grid cells or boxes that cover the cracks in an image. Accurate and efficient crack identification is the premise of crack assessment. However, the current patch‐based classification method is limited by the receptive field and cannot be used to directly classify cracks. Furthermore, the postprocessing algorithm in anchor‐based detection is not explicitly optimized for crack topology. In this paper, a new model, which is the fusion of grid‐based classification and box‐based detection based on You Only Look Once version 5 (YOLO v5) is developed and described for the first time. The accuracy and efficiency of the model are high partly due to the implementation of a shared backbone network, multi‐task learning, and joint training. The non‐maximum suppression (NMS)–area‐reduction suppression (ARS) algorithm is presented to filter redundant, overlapping prediction boxes in the postprocessing stage for the crack topology, and the mapping and matching algorithm is proposed to combine the advantages of both the grid‐based and box‐based models. A double‐labeled dataset containing tens of thousands of asphalt pavement images is assembled, and the proposed method is verified on the test set. The fusion model has superior performance over the individual classification and detection models, and the proposed NMS‐ARS algorithm further improves the detection accuracy. Experimental results demonstrate that the presented method effectively realizes automatic crack identification for asphalt pavement.

EPOXY-RESIN ADHESIVE FOR SEAM FILLING AND POTHOLE REPAIR IN PAVEMENT MAINTENANCE

Aiming at the problems of asphalt pavement crack sealing and pothole repair materials, an epoxy-resin adhesive with high forming strength, good toughness and room-temperature curing was prepared. In addition to being used as a road filling sealant, the adhesive can also be used for preparing a cold patching mixture for pits. The properties of the epoxy-resin adhesive, the construction performance and road performance of the pouring sealant and cold patch were studied. The results showed that the early strength of the epoxy-resin adhesive was fast and high, the curing volume shrinkage was small, the low-temperature characteristics and tensile properties were good, and the toughness was excellent. As a pouring sealant, the epoxy-resin adhesive had excellent low-temperature bending resistance. The cold patching mixture based on the adhesive exhibited strong cohesiveness, good low-temperature crack resistance, and excellent high-temperature stability and water stability. This adhesive expands the application of epoxy resin in repairing cracks and pits of asphalt pavements, and is of great significance in promoting the development of the asphalt pavement maintenance technology.

Automatic pixel-level detection of vertical cracks in asphalt pavement based on GPR investigation and improved mask R-CNN

Non-destructive testing and characterization of internal vertical cracks are critical for road maintenance by ground penetrating radar (GPR). This paper describes a mask region-based convolutional neural network (R-CNN) that automatically detects and segments small cracks in asphalt pavement at the pixel level. Simulation using Gprmax software and field detection were performed to determine the crack features in GPR images of asphalt pavement and the relationship between the width of vertical cracks and their area in GPR images. Results showed that a 0.833 precision, 0.822 F1 score, 0.701 mean intersection-over-union (mIoU) and 4.2 frames per second (FPS) were achieved on 429 GPR images (1024×1024 pixels), and the mean error between the segmented crack width and the true values was 2.33%. The research results represent a further step toward accurately detecting and characterizing internal vertical cracks in asphalt pavement

Geotextile resistance to cyclic and static loading damage when impregnated with asphalt emulsion

Cracks in asphalt pavements are a constant concern in transportation engineering. The simple construction of a new overlayer above the cracked one may result in crack propagation. Over the last decades, geosynthetics has emerged as an interesting anti-reflective crack system. Adopting impregnated geotextiles between the cracked and new overlay may be an attractive solution. However, the installation damage suffered by impregnated geotextiles must be assessed for the design purpose. This study performs laboratory installation damage (cyclic and static loads) over poly(ethylene) terephthalate (PET) and polypropylene (PP) non-woven geotextiles impregnated with rapid setting cationic asphalt emulsion under non-modified (CRS-1) and modified (CRS-1S) conditions. Geotextile specimens were arranged in split test boxes, in which the top layer comprised gravel material (GP) and the bottom layer consisted of gravel (GP), sand (SP) or clayey (CL) soil. The geotextiles were tested (axial tensile and permissivity tests) under the impregnated and non-impregnated conditions before and after the damage procedures. Results show that the modified asphalt emulsion has less adhesion capability, and the geotextile structure has a significant role in the impregnation efficiency. The tensile strength and secant tensile stiffness increased, whereas the elongation at failure and permissivity results decreased after the installation procedures regardless of the impregnation condition. However, the properties of interest were more affected by the installation damage under the impregnated condition than the non-impregnated one. The PET geotextile was more affected under the non-impregnation condition and the PP one under the impregnated condition. The reductions in the elongation at failure may not impair the pavement application of impregnated geotextiles. However, designers must assess if the decrease suffered in tensile strength and the changes in the permissivity results compromise the performance of pavements.

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.

Novel YOLOv3 Model With Structure and Hyperparameter Optimization for Detection of Pavement Concealed Cracks in GPR Images

Accurately identifying and localizing concealed cracks in asphalt pavements through nondestructive ground-penetrating radar (GPR) testing has attracted much attention. However, various realistic factors restrict its detection accuracy. Therefore, this paper proposed a novel YOLOv3 model with a ResNet50vd-deformable convolution (DCN) backbone and a hyperparameter optimization (HPO) method using Bayesian search. First, a 3D-Radar system with multi-channel DXG <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$^{\mathrm {TM}}$ </tex-math></inline-formula> ground-coupled antenna arrays was used to investigate concealed cracks in the asphalt pavement to establish a crack distress dataset with 366 images and 533 cracks. Then, owing to the small GPR image dataset, a simple semi-supervised label distillation (SSLD) method was employed to obtain the pretrained model. Subsequently, Bayesian searching based HPO was performed to find the maximum mean average precision (mAP) and corresponding hyperparameters in 20 searches. Finally, several mainstream detection models were used for comparisons. Experimental results showed that YOLOv3-ResNet50vd-DCN model converged faster and had a smaller loss value (approximately 0.05) in the training process, which illustrates the advantage of model pretraining with the SSLD method. Besides, the proposed model also achieved good detection results, with 92.6% accuracy, 92.3% F1 score, 92.1% mAP, and 0.923 area under the ROC curve (AUC) value, all 3% to 7% higher than that of the other models. After Bayesian searching for HPO, the detection results were further improved to 94.8% accuracy, 96.2% F1 score, 94.6% mAP, and 0.962 AUC value, validating the reliability and superiority of the proposed model and optimization method in detecting pavement concealed cracks of GPR images.

Asphalt Pavement Crack Detection Based on Convolutional Neural Network and Infrared Thermography

Two issues exist in the convolutional neural network (CNN) used for asphalt pavement crack detection: balance between accuracy and complexity, and indistinct edges of cracks and asphalt pavement surface. Infrared thermography (IRT) could use the temperature difference between cracks and pavement surface to better distinguish cracks. This work aims to propose a robust crack detection method based on CNN and IRT. An open benchmark dataset was built for crack detection based on three types of images, including visible images, infrared images, and the fusion of visible and infrared images (in short, fusion image). The dataset also considers different conditions and periods, including single, multi, thin, and thick cracks; clean, rough, light, and dark backgrounds, and three periods in a day. Seven CNN segmentation models are trained and evaluated on this dataset. To keep a balance between accuracy and complexity, evaluation metrics (accuracy, and computational and model complexity) are used to have an overall evaluation of models rather than only the accuracy. The results show that the accuracy and predictions of the visible image and fusion image are almost identical for all models, which are much better than that of the infrared image. When the background is rough or cracks are similar to the background, the fusion image is a better choice for crack detection. Compared with the visible image, all segmentation models have a more stable performance for the fusion image. Among segmentation models, Feature Pyramid Networks (FPN) could be the best model because of its high accuracy and low complexity.

Development of Deterioration Model for Cracks in Asphalt Pavement Using Deep Learning-Based Road Asset Monitoring System

Development of Deterioration Model for Cracks in Asphalt Pavement Using Deep Learning-Based Road Asset Monitoring System

Investigation of transverse crack spacing in an asphalt pavement with a semi-rigid base

Transverse cracking is a serious problem for semi-rigid base asphalt pavement. The shrinkage of the base course and the surface course, as well as reflective cracks, are key factors for transverse cracking in asphalt pavement. Crack spacing can directly reflect the degree of transverse cracking in pavements. Therefore, this study aims to calculate the transverse crack spacing and discuss its affecting factors. To this end, a calculation model of transverse crack spacing for the semi-rigid base asphalt pavement was first established. Then, the transverse crack spacings of different composite structures were calculated, and the influences of the shrinkage coefficient, the structural layer thickness, and the pavement tensile strength on transverse crack spacing were expounded. Finally, the transverse crack spacing of the pavement after the appearance of the reflective was calculated. The results show that the lower lime and fly ash content and skeleton gap gradation can be adopted during the design of the base course. Meanwhile, the lower lime and fly ash content in the macadam base, the skeleton gap gradation and asphalt concrete with a larger particle size in the surface layer can be used during the design of surface layer. In addition, the transverse crack spacing of the semi-rigid base asphalt pavement could be increased by reducing the shrinkage coefficient, increasing the thicknesses of the surface course and the base course, and improving the tensile strength of the pavement. After the appearance of reflective cracks, the transverse crack spacing of the surface layer ranged between 32.8 m and 66.5 m. 15fp-AC25, 15fp-AC20, 15df-AC25, and 17fp-AC25 were found to be the best semi-rigid base asphalt pavement structures to reduce transverse cracking. Finally, transverse cracking in pavement composite structures under different bonding conditions needs to be analyzed in the follow-up work.

Asphalt complex cracks' sensitivity to temperature and crack depth and adjustment of the composite stress intensity factor

This paper is based on the fracture mechanics K-criterion with the composite stress intensity factor solution formula. The influence of temperature and depth in developing complex crack instability and diffusion in asphalt pavements is investigated. The crack composite stress intensity factor and development pattern are analyzed. The finite element modeling analyzes the change in stress intensity factor values at different temperatures and cracks depths. The composite stress intensity factor's temperature effect factor (t*) and crack depth effect factor (d*) are derived, and the calculation formulae are optimized. The study results show that among the complex cracks in asphalt pavements, the type I crack tip stress intensity factor (KⅠ) is the most seriously affected by temperature and crack depth and is also the main controlling factor of crack development. Type II crack tip stress intensity factor (KⅡ) is not significantly influenced by temperature but tends to rise and fall as the crack depth increases. Type III crack tip stress intensity factor (KIII) is smaller than KⅠ and KⅡ. It has less influence on the development of complex cracks in asphalt pavements. t* and d* were introduced to derive the formula for the modified composite stress intensity factor (Keff*). The formula was verified to calculate the composite stress intensity factor at different temperatures and crack depths and to study the cracking pattern of asphalt pavements.

Influence of low-temperature polyurethane solid-solid PCMs particles on the pavement performance of asphalt mixtures

In order to slow down the cooling rate of the mixture and reduce the low temperature cracking of asphalt pavement in large temperature difference areas, low-temperature polyurethane solid-solid phase change materials (LPSPCMs) were prepared by prepolymer method. The researches show that LPSPCMs have good phase change heat storage performance and thermal stability performance, and can be applied to hot mix asphalt mixtures. The LPSPCMs particles were incorporated into the asphalt mixture, and the road performance of the LPSPCMs particulate asphalt mixture was tested and analyzed and found: as LPSPCMs particles change the abrasion resistance and embedded effect between asphalt mixes, with the increase of LPSPCMs particles, the high-temperature performance of asphalt mixes first increased and then decreased. The water stability of asphalt mixtures gradually decreases with the increase of LPSPCMs particles content because relative to limestone aggregates, LPSPCMs particles adhere poorly to asphalt. The thermal stress restrained specimen test (TSRST) showed that the cracking temperature of the asphalt mixture gradually decreased with the increase of LPSPCMs particles contents because of the phase change temperature control effect of LPSPCMs particles indicated that LPSPCMs particles improve the low-temperature performance of asphalt mixtures. On this basis, the correlation between the evaluation index of the phase change temperature adjustment effect and the improvement effect of the low-temperature performance of the mixture was established.

An Efficient Method for Detecting Asphalt Pavement Cracks and Sealed Cracks Based on a Deep Data-Driven Model

Thanks to the development of deep learning, the use of data-driven methods to detect pavement distresses has become an active research field. This research makes four contributions to address the problem of efficiently detecting cracks and sealed cracks in asphalt pavements. First, a dataset of pavement cracks and sealed cracks is created, which consists of 10,400 images obtained by a vehicle equipped with a highway condition monitor, with 202,840 labeled distress instances included in these pavement images. Second, we develop a dense and redundant crack annotation method based on the characteristics of the crack images. Compared with traditional annotation, the method we propose generates more object instances, and the localization is more accurate. Next, to achieve efficient crack detection, a semi-automatic crack annotation method is proposed, which reduces the working time by 80% compared with fully manual annotation. Finally, comparative experiments are conducted on our dataset using 13 currently prevailing object detection algorithms. The results show that dense and redundant annotation is effective; moreover, cracks and sealed cracks can be efficiently and accurately detected using the YOLOv5 series model and YOLOv5s is the most balanced model with an F1-score of 86.79% and an inference time of 14.8ms. The pavement crack and sealed crack dataset created in this study is publicly available.

Investigation on the Feasibility of Different Semicircular Bend Methods for Asphalt Concrete

Cracking of asphalt pavement is mostly caused by the mixed fracture of asphalt concrete. Determining a simple, repeatable, and accurate method is necessary for evaluating the fracture resistance of asphalt concrete. To explore the mixed fracture performance of asphalt concrete and determine the feasibility of different semicircular bend methods, the mixed fracture performances of asphalt concrete at medium and low temperatures were measured. The mixed fracture modes were realized through changing the position of the support and notch or changing the notch angle. After that, the crack propagating characteristics, crack initiation angle, and fracture toughness were analyzed. Results show that temperature has a significant impact on the fracture path, and crack initiation angle at low temperature follows the generalized maximum tangential stress (GMTS) theory. The measured fracture toughness ratios are lower than the theoretical value of GMTS criterion, but the established empirical model has higher accuracy. In the semicircular bend method, changing the positions of the support and notch is stable and repeatable. Therefore, this method may be preferred to evaluate the mixed fracture performance of asphalt concrete in the future.

Rheological, Aging, and Microstructural Properties of Polycarbonate and Polytetrafluoroethylene Modified Bitumen.

Deterioration of asphalt pavements due to massive load of vehicles and climatic variation has demanded the use of pavements construction material with an excellent resilience characteristic, resistance to permanent deformation, and most importantly, a much longer service lifespan. The main structural distresses in pavement construction are permanent deformation at high temperatures and fatigue cracking under repetitive traffic loadings. To comprehensively investigate the performance of bitumen penetration grade (PG) 70 against rutting, fatigue, and high temperature cracking in hot mix asphalt (HMA) pavements, polycarbonate (PC) and polytetrafluoroethylene (PTFE) were used. The investigation of the internal structure, rheological, and physical properties of base and modified bitumen (MB) mixes with different percentages of modifiers (0%, 2.5%, and 5%) by weight were performed via scanning electron microscope (SEM), Fourier transform infrared spectroscopy (FTIR) analysis, X-ray diffraction (XRD) pattern analysis, rolling thin-film oven test (RTFOT), pressurized aging vessel (PAV), dynamic shear rheometer (DSR), rotational viscosity (RV), and bending beam rheometer (BBR). The results of the RV test indicate that modification of neat bitumen with polycarbonate and polytetrafluoroethylene increased the viscosity for polycarbonate-modified bitumen (PCMB), polytetrafluoroethylene-modified bitumen (PTFEMB), and for a blend of PCMB-PTFEMB by 44%, 50%, and 55.75% at 135 °C and 111.10%, 127.80%, and 138.88% at 165 °C, accordingly. BBR test results revealed that modifiers increased the rigidity of neat bitumen by 74.8%, 75.8%, and 74.5% at −16 °C, −22 °C, and −28 °C, respectively.

Cracking behavior of asphalt pavement with a graded gravel layer based on computational granular mechanics

The reflective cracking is still a critical issue to be solved in the semi-rigid base asphalt pavements. In this study, the discrete element method (DEM) is used to study the reflection cracks of semi-rigid base asphalt pavement with a graded gravel interlayer at the meso level. The generation and development of internal meso cracks in asphalt pavements under vehicle loads were simulated and analyzed. The simulation results show that in the semi-rigid base asphalt pavement, the preset cracks extend from the tip to the surface layer and form reflective cracks in the direction of the oblique loading plate. With the increase in surface thickness, the development trend of the cracks slows down, and the total amount of meso cracks in the pavement decreases. The reflective cracking is reduced in the asphalt pavement with a graded crushed stone base, and the distribution position is relatively discrete. Under the same surface thickness, the number of meso cracks decreases with the thickness of the graded crushed stone base. It indicates that the graded gravel can effectively prevent the development of reflective cracking in asphalt pavements.

Machine-filling of cracks in asphalt concrete

In this paper, a machine process to repair cracks in asphalt pavements by filling them with hot bitumen is demonstrated for the first time. We have characterized the quality of these fillings. Furthermore, the paper examines how the filling speed, temperature, bitumen type, crack width, crack irregularity, and the flow of hot bitumen affect the crack filling quality by the machine. In the laboratory we have used a 3D-printer as the machine to fill the cracks due to its simplicity. We have characterized the quality of the repaired cracks in terms of their porosity and shear and tensile strength. We have demonstrated that the bitumen flow, filling speed, and width and depth of cracks determine the quality of the filling and will need to be carefully controlled in a future autonomous crack filling device. The complex interaction between these parameters will need to be underpinned in future research.

Parameter Optimization and Bending Performance Analysis of a Corrugated Steel Plate-UHPC Composite Bridge Deck with PZ Shear Connectors

Composite bridge decks consisting of steel plates and concrete are used to minimize fatigue cracking and damage of asphalt pavement of orthotropic steel bridge decks subjected to wheel loads. This paper presents a methodology to optimize the parameters and mechanical performance of a corrugated steel plate-ultrahigh-performance concrete (UHPC) composite bridge deck with panel zone (PZ) shear connectors using the improved non-dominated sorting genetic algorithm (NSGA-II). A 3-D finite element model is established in ANSYS Workbench software to conduct numerical parameter analysis, and ABAQUS software is used to analyze the optimized model’s mechanical performance. The results show a significant improvement in the mechanical performance of the optimized composite bridge deck, with a 27.66% decrease in the maximum stress in the UHPC layer. The vertical displacement of the optimized composite bridge deck increases sharply when the load reaches 90% of the ultimate load, and a significant change in the strain is caused by the sliding displacement between the UHPC layer and steel plate. The bottom part of the corrugation yields first in the middle span, followed by failures of the ribs. In addition, as the tensile stress increases, damage occurs first in the UHPC layer near the PZ shear connectors in the shear bending area and the bottom in the bending area, expanding significantly to the entire bending and loading areas. The results indicate that the parameter optimization of the corrugated steel plate-UHPC composite bridge deck using NSGA-II improves the structure’s bending performance.

Deep learning and infrared thermography for asphalt pavement crack severity classification

Deep learning, especially convolutional neural network (CNN), is becoming a popular and powerful tool for crack detection. This work aims to apply deep learning and infrared thermography for asphalt pavement crack severity classification. A dataset of asphalt pavement crack was built in this work, including four levels of crack severity, no crack, low-severity crack (i.e., low crack), medium-severity crack (i.e., medium crack), and high-severity crack (i.e., high crack). This dataset had three types of images, the visible image, infrared image, and the fusion of visible and infrared images (i.e., fusion image). Thirteen typical CNN models were trained and evaluated on the aforementioned dataset for deep learning from scratch, while eight pre-trained CNN models trained by ImageNet were also trained and evaluated for transfer learning. This work investigated the effects of image types on the accuracy of deep learning from scratch and transfer learning, as well as the effects of image types on classifying the levels of crack severity. The results show that the CNN models had the highest accuracy on the fusion image for deep learning from scratch, but the highest accuracy on the visible image for transfer learning. The CNN models performed well on both the no crack and low crack but had different performances on the medium crack and high crack for all three types of images, while misclassification occurred mainly on the medium crack and high crack for all three types of images. EfficientNet-B3 had the highest accuracy on all three types of images for both deep learning from scratch and transfer learning.

GPR-based detection of internal cracks in asphalt pavement: A combination method of DeepAugment data and object detection

The lack of data and poor quality of ground penetrating radar (GPR) images have limited the development of the object detection for internal cracks in asphalt pavement. To address this issue, this paper proposed a ‘DeepAugment’ data augmentation strategy combined with object detection models. First, the characteristic of internal cracks was determined with numerical simulation and GPR field test, which was in accordance with the coring results. Subsequently, the proposed DeepAugment method was used to enhance the crack features. Object detection results showed that the recognition accuracy and confidence level of internal crack detection improved by using the object detection model to test the enhanced GPR images, which was more noticeable in the YOLOv3 model. The proposed method is found to be of significance for accurately identifying internal cracks in GPR images, and the recognition accuracy after data enhancement can meet the needs of road maintenance engineering.

Factors affecting low-temperature cracking of asphalt pavements: analysis of field observations using the ordered logistic model

ABSTRACT Accurate identification of factors that primarily affect the number of low-temperature cracks is crucial for selection of road materials and planning of pavement maintenance. Field investigations of low-temperature cracks were performed in the years 2014 and 2020 on the same 68 road sections being in service in typical traffic conditions. The collected data were statistically analysed using the ordered logistic regression model. Comparison of the odds ratios which were calculated on the basis of the model enabled ordering of the selected factors from those having the greatest effect on low-temperature cracking of pavements to those with the least influence: (1) pavement age, (2) type of asphalt concrete, (3) modification of bitumen, (4) climatic zone (on the basis of low performance grade temperature). The odds of a section belonging to the group of cracked sections decreased by half when a polymer-modified bitumen was used in its binder course and asphalt base. Regardless of the considered factors, the odds of a pavement section being classified into the group of heavily cracked sections are comparable. It means that some external factors, including quality of paving works and bitumen chemistry, may prove the most crucial.