Pavement Distress Research Articles

UPDAPS-Flood: a mechanistic-empirical flexible pavement analysis tool to evaluate the effect of flooding events on flexible pavement performance

ABSTRACT Flooding can cause considerable damage to flexible pavements and negatively affects their performance over time. This study aims to evaluate the flooding effects on the flexible pavement performance and the potential resiliency of the pavement network through a mechanistic-empirical (ME) pavement analysis approach. The Unified Pavement Distress Analysis and Prediction System (UPDAPS) programme, which includes ME analysis models, was used to develop the UPDAPS-Flood programme. A total of 7,655 flexible pavement sections were extracted from the Highway Pavement Management System (HPMS) database in three United States regions. Finally, the resiliency of the pavement network to flood events was quantified using the loss of pavement service life based on the international roughness index (IRI). The results showed that flooding has the highest impact on rutting performance, followed by IRI and fatigue cracking. It has been found that a proper drainage system can reduce the flooding impact by a factor of two. The predicted pavement performance was found to be very sensitive to the coefficients of the rutting model, which brings the need for further studies to re-calibrate the rutting prediction model at higher moisture content levels.

Image-based severity analysis of Asphalt pavement bleeding using a metaheuristic-boosted fuzzy classifier

Pavement management systems play a vital role in maintaining transportation infrastructures by evaluating pavement distress to perform maintenance tasks efficiently. Severity analysis is an important step in this process. With an increasing focus on automating the pavement distress inspection, challenges persist, including limited attention to severity analysis of texture-based distresses and lack of applying fuzzy systems in this analysis despite the linguistic and qualitative description of severity levels. Accordingly, this paper presents a methodology leveraging computational intelligence frameworks such as fuzzy logic and metaheuristic optimization to develop a reliable system for severity analysis, particularly focusing on asphalt pavement bleeding. Employing GLSM and statistical feature extraction in conjunction with a fuzzy classifier, optimized with metaheuristic-based algorithms like GA, HBA, GWA, ARA, and SSA, the proposed boosted fuzzy classifier achieves an impressive accuracy of 93% and notable improvements in performance metrics, underscoring its superiority over classic fuzzy classifiers.

The influence of interlayer bonding conditions on the propagation laws of reflective cracks in semi-rigid base pavement based on the DEM and GPR

Reflection cracks represent the predominant internal distress in semi-rigid base asphalt pavements and often accompanied by additional secondary issues that detrimentally affect the pavement structural bearing capacity. The propagation and deterioration of reflective cracks are affected by many factors, for example the interlayer bonding conditions. It is crucial to identify the propagation and deterioration of reflective cracks to prolong the life of pavement structure. The purpose of this article is to explore the influence of interlayer bonding conditions on the propagation laws of reflective cracks. This work employs the discrete element method(DEM) to explore the propagation patterns of reflection cracks accompanied different bonding conditions between the surface layer and base layer subjected to moving load. The results of discrete element simulation reveal a three-phase progression laws when the reflective cracks expand from the base layer to the pavement surface，involving rapid propagation, stable propagation, and failure process. With the interlayer bond strength decreases, expansion of reflective crack is significantly accelerated. Meanwhile, once the critical bond strength threshold is reached, complete debonding will occur between the surface and base layers. The results are ultimately verified through the core sampling from practical engineering using three-dimensional (3D) ground penetrating radar(GPR) detection, along with the radar image recognition of reflective cracks and poor interlayer bonding. The results will serve as a foundation for researching the mechanism and treatment measures for two internal pavement distress, namely reflection cracks and poor interlayer bonding.

PaveSAM – segment anything for pavement distress

Automated pavement monitoring using computer vision can analyse pavement conditions more efficiently and accurately than manual methods. Accurate segmentation is essential for quantifying the severity and extent of pavement defects and consequently, the overall condition index used for prioritising maintenance activities. Deep-learning-based segmentation models are however, often supervised and require pixel-level annotations, which can be costly and time-consuming. While the recent evolution of zero-shot segmentation models can generate pixel-wise labels for unseen classes without any training data, they struggle with irregularities of cracks and textured pavement backgrounds. This research proposes a zero-shot segmentation model, PaveSAM, which can segment pavement distresses using bounding box prompts. By retraining SAM's mask decoder with just 180 images, pavement distress segmentation is revolutionised, enabling efficient distress segmentation using boundingbox prompts, a capability not found in current segmentation models. This drastically reduces labelling costs and establishing the pioneering use of SAM in pavement distress segmentation.

LiDAR-Based Automatic Pavement Distress Detection and Management Using Deep Learning and BIM

LiDAR-Based Automatic Pavement Distress Detection and Management Using Deep Learning and BIM

Polyurethane-Asphaltic Concrete as an Alternative Solution for Road Pavement Distress – A Review

Road traffic accidents are the primary source of injuries and fatalities worldwide, accounting for 20–50 million long term disabilities and 1.25 million deaths annually. Pavement conditions rank as the second most common cause of traffic accidents. The combined effects of environmental factors and traffic loads lead to pavement discomfort. Ensuring proper pavement design and maintenance can assist in lowering accident rates and preventing long-term disability associated with drivers. Physical maintenance procedures like overlays, seal coatings, patching, and filling joints are carried out in practice; nevertheless, they only offer temporary fixes by treating the symptoms rather than the underlying issue. An alternative method for road pavement maintenance is using polyurethane to improve the properties of asphalt due to the excellent properties of polyurethane. This study conducts a systematic review of the polyurethane asphaltic characteristics and performance based on the previous study by researchers. It is found that the pavement maintenance work using polyurethane is able to sustain longer periods and is moisture resistant due to its excellent bonding with the existing pavement material. Keywords: polyurethane, asphalt, pavement, distress, road

Unraveling the optimal strategies for asphalt pavement longevity through preventive maintenance: A case study in South Korea

This study provides a comprehensive evaluation of three pavement surface treatments—Re-Ascon, Micro-surfacing, and Fog-seal—aimed at enhancing the longevity of asphalt concrete pavement. Utilizing visual inspection, bearing capacity measurements, and linear regression modeling, this study rigorously assesses the effectiveness of these strategies in real-world road environments. Notably, Re-Ascon emerges as the least damaged method in visual inspection, offering crucial insights into initial pavement conditions. Visual inspections consistently underscore Re-Ascon's outstanding performance in mitigating pavement distress, particularly in addressing cracking. Quantitative analysis using the Surface Curvature Index (SCI) from Falling Weight Deflectometer (FWD) measurements highlights Re-Ascon's superior elastic modulus (E1) and resistance to deflection compared to alternatives. Re-Ascon's 20 % SCI reduction compared to Fog-seal highlights its superior deflection resistance, supported by logarithmic elastic modulus values. Correlation analysis confirms Re-Ascon's resilience, maintaining low SCI even under higher loads and adverse weather conditions. Geographical variations and method-specific influences are revealed through PCI analysis, emphasizing the vital impact of preventive maintenance. The identified PCI threshold of 60 % guides timely interventions for major maintenance, while service life analysis forecasts approximately 3.0, 2.5, and 1.5 years for Micro-surfacing, Re-Ascon, and Fog-seal methods, respectively. In conclusion, this research furnishes critical insights into preventive maintenance methods, advocating a holistic assessment through visual, structural, and predictive perspectives, and emphasizing the need for ongoing research to advance sustainable strategies.

Pavement raveling inspection using a new image texture-based feature set and artificial intelligence

Enhancing pavement distress inspection is crucial within a pavement management system. Recognizing the advantages of automated pavement condition inspection, considerable efforts have been invested in developing more efficient systems for this purpose. Raveling, a common asphalt pavement distress, significantly impacts both passenger comfort and pavement durability. Given its connection to pavement texture and the limited effectiveness of earlier inspection systems, improving automatic raveling inspection has become a challenging endeavor. This study proposes an image-based system for raveling detection, employing a new image processing-based feature set. This approach generates enhanced inputs for artificial intelligence models, thereby improving the efficiency of raveling inspection while optimizing resource allocation. To accomplish this, an image dataset is created by combining newly collected images with an existing collection. Novel combinations of features are then engineered to extract meaningful texture-based image features. Subsequently, three feature selection algorithms are employed to identify the most pivotal features. Machine Learning (ML) models are then trained for effective raveling detection based on the proposed feature set, and their performance is evaluated across various performance indices. The achieved performance metrics, reaching nearly 96 % on the test datasets, underscore the efficacy of the proposed method in automating the inspection of texture-based pavement distresses.

Automated detection of pavement distress based on enhanced YOLOv8 and synthetic data with textured background modeling

Regular inspections of pavement distress are essential for accident prevention, and deep learning based algorithms have been developed to ensure high accuracy of inspections. However, the lack of available data is a critical challenge for existing algorithms. To address this issue, an elaborate image synthesis strategy is proposed. By combining textured background modeling for real pavement and Unreal Engine-based distress block stitching technique, high-resolution virtual images that are indistinguishable from real images are generated, including five types of pavement distresses. In addition, an enhanced YOLOv8 network utilizing synthetic data is designed in this paper. The enhanced YOLOv8 network is embedded with the Squeeze and Excitation attention module, and the Swin Transformer module, which are designed to distinguish different types of pavement distress accurately and suppress the interference of complex backgrounds (noise, shadow, blur). The results show that the performance of the algorithms trained based on appropriately ratios of synthetic data (2:1 ratio of virtual to real) improves by more than 10% compared with no virtual data. The enhanced YOLOv8 network achieves a Mean Average Precision (MAP) of 94.8% for transverse cracks, longitudinal cracks, cross-cracks, alligator cracks, and potholes, which is better than seven existing object detection models. The proposed image synthesis method can contribute to improving the accuracy and reliability of pavement inspection and alleviate the reliance on large number of distress samples collection.

Automatic Road Pavement Distress Recognition Using Deep Learning Networks from Unmanned Aerial Imagery

Detecting and recognizing distress types on road pavement is crucial for selecting the most appropriate methods to repair, maintain, prevent further damage, and ensure the smooth functioning of daily activities. However, this task presents challenges, such as dealing with crowded backgrounds, the presence of multiple distress types in images, and their small sizes. In this study, the YOLOv8 network, a cutting-edge single-stage model, is employed to recognize seven common pavement distress types, including transverse cracks, longitudinal cracks, alligator cracks, oblique cracks, potholes, repairs, and delamination, using a dataset comprising 5796 terrestrial and unmanned aerial images. The network’s optimized architecture and multiple convolutional layers facilitate the extraction of high-level semantic features, enhancing algorithm accuracy, speed, and robustness. By combining high and low semantic features, the network achieves improved accuracy in addressing challenges and distinguishing between different distress types. The implemented Convolutional Neural Network demonstrates a recognition precision of 77%, accuracy of 81%, mAP of 79%, f1-score of 74%, and recall of 75%, underscoring the model’s effectiveness in recognizing various pavement distress forms in both aerial and terrestrial images. These results highlight the model’s satisfactory performance and its potential for effectively recognizing and categorizing pavement distress for efficient infrastructure maintenance and management.

Review of Lab-Accelerated Aging Techniques of Asphalt Mixes

Bitumen aging contributes to main pavement distress due to the changes in rheological, chemical, and physical characteristics of bitumen. Mainly, aging process can be divided into two categories, the first category namely short-term aging takes place during the heating up of bitumen and aggregate, mixing, transportation, laying down, and compaction. While the second category of aging takes place during the service life of pavement which is denoted as long-term aging. Consequently, researchers’ focus is to simulate bitumen aging in the lab by developing lab-accelerated methods to simulate the process of bitumen aging and studying the rate of change before and after aging. This article reviews these methods and compares the extent of the impact on lab-aged bitumen with old bitumen. The main outcome is, that the duration of exposure to high temperatures, which is the dominant method to accelerate aging process, resulted in inadequate changes in the structure of the bitumen molecule, hence, making it different from old bitumen. For that reason, using oxidants such as hydrogen peroxide showed more reliable results but requires more attention by researchers to achieve a standardized aging process of bitumen.

Automated Multi-Type Pavement Distress Segmentation and Quantification Using Transformer Networks for Pavement Condition Index Prediction

Automated Multi-Type Pavement Distress Segmentation and Quantification Using Transformer Networks for Pavement Condition Index Prediction

YOLOv8-PD: an improved road damage detection algorithm based on YOLOv8n model.

Road damage detection is an crucial task to ensure road safety. To tackle the issues of poor performance on multi-scale pavement distresses and high costs in detection task, this paper presents an improved lightweight road damage detection algorithm based on YOLOv8n, named YOLOv8-PD (pavement distress). Firstly, a BOT module that can extract global information of road damage images is proposed to adapt to the large-span features of crack objects. Secondly, the introduction of the large separable kernel attention (LKSA) mechanism enhances the detection accuracy of the algorithm. Then, a C2fGhost block is constructed in the neck network to strengthen the feature extraction of complex road damages while reducing the computational load. Furthermore, we introduced lightweight shared convolution detection head (LSCD-Head) to improve feature expressiveness and reduce the number of parameters. Finally, extensive experiments on the RDD2022 dataset yield a model with parametric and computational quantities of 2.3M and 6.1 GFLOPs, which are only 74.1% and 74.3% of the baseline, and the mAP reaches an improvement of 1.4 percentage points from the baseline. In addition, experimental results on the RoadDamage dataset show that the mAP increased by 4.2% and this algorithm has good robustness. This method can provide a reference for the automatic detection method of pavement distress.

Automatic Detection of Urban Pavement Distress and Dropped Objects with a Comprehensive Dataset Collected via Smartphone

Automatic Detection of Urban Pavement Distress and Dropped Objects with a Comprehensive Dataset Collected via Smartphone

Structure and mechanism of directional heat induced asphalt pavement with thermal aggregation effect

Efficiently and actively dissipating accumulated heat within asphalt pavement is crucial for reducing pavement distress and improving subgrade stability. This paper proposed a novel inverted “T” shaped heat induced structure (IT-HIS) that facilitates the rapid transfer of heat from the pavement to the subgrade and shoulders. The IT-HIS consists of two components: a vertical gradient thermal conductivity structure utilizing steel slag, and a horizontal oriented carbon fiber heat induced structure. The heat transfer behavior of the IT-HIS was analyzed using a finite element heat transfer model created in ABAQUS, and the results were validated through indoor irradiation experiments. The findings demonstrated that the IT-HIS enhanced heat flow and promoted secondary aggregation in the vertical direction, while facilitated lateral heat dissipation. Compared to the ordinary group (OG), the heat flux of IT-HIS at depths of 5 cm and 6.5 cm increased by 19.8 % and 64.6 %, respectively. The indoor irradiation experiment results indicated that during the heat absorption period, the IT-HIS reduced temperatures at depths of 0 cm, 2 cm, and 5 cm by 1.5 ℃, 1.7 ℃, and 1.1 ℃, respectively. During the heat dissipation period, the IT-HIS reduced temperatures at depths of 0 cm, 5 cm, and 10 cm by 0.9 ℃, 0.7 ℃, and 1.8 ℃, respectively. The IT-HIS enhanced the cooling effect during daytime and inhibited heat upward during nighttime based on the gradient thermal conductivity structure. The proposal and validation of this structure provide a fundamental approach to forming large-scale high-speed microchannel heat dissipation within asphalt pavements, and is expected to provide experimental and theoretical foundations for the development of directional active cooling technologies.

Hybrid Transfer Learning and Support Vector Machine Models for Asphalt Pavement Distress Classification

Pavement condition evaluation plays a crucial role in assisting with the management of the highway infrastructure. However, the current methods used for assessing pavement conditions are costly, time-consuming, and subjective. There is a growing need to automate these assessment tactics and leverage low-cost technologies to enable widespread deployment. This study aims to develop robust and highly accurate models for classifying asphalt pavement distresses using transfer learning (TL) techniques based on pretrained deep learning (DL) networks. This topic has gained considerable attention in the field since 2015 when DL became the mainstream choice for various computer vision tasks. While progress has been made in TL model development, challenges persist in areas of accuracy, repeatability, and training cost. To tackle these challenges, this study proposes hybrid models that combine DL networks with support vector machines (SVMs). Three strategies were evaluated: single DL models using transfer learning (TLDL), hybrid models combining DL and SVM (DL+SVM), and hybrid models combining TLDL and SVM (TLDL+SVM). The performance of each strategy was assessed using statistical metrics based on the confusion matrix. Results consistently showed that the TLDL+SVM strategy outperformed the other approaches in accuracy and F1 scores, regardless of the DL network type. On average, the hybrid models achieved an accuracy of 95%, surpassing the 80% accuracy of the best single model and the 55% accuracy for DL+SVM without TL. The results clearly indicate that employing transfer-learned models as feature extractors, in combination with SVM as the classifier, consistently achieves exceptional performance.

An innovative simplified approach for conductive heat flux in pavement structures

Understanding the conductive heat flux at pavement surfaces and interior layers is crucial for reducing pavement distress, developing cooler pavements, and mitigating urban heat island (UHI) effects. Existing methods often rely on calculating the conductive heat flux as the residual heat flux from net radiation and heat convection, leading to significant measurement uncertainties in practice. This study overcomes this issue by introducing a novel model based on Maclaurin polynomial temperature profiles to more accurately determine the conductive heat flux across pavement surfaces and depths. Validated against designed experiments and existing literature, our model shows that both cubic and quadratic Maclaurin polynomials can approximate pavement temperature profiles properly. Our model facilitates the determination of conductive heat flux at various pavement depths, including the surface. By correlating the temperature gradient with measured conductive heat flux at specific depths, we accurately determine the thermal conductivity of the pavement. The proposed method more accurately estimates conductive heat flux compared to the traditional residual methods. The model proves useful in quantifying conductive heat flux, convection, and convection coefficients at various pavement locations, offering enhanced monitoring of conductive heat flux across urban streets.

Classifying flexible pavement defects using hybrid machine learning approach

The transportation infrastructure sector significantly impacts a country’s gross domestic product (GDP), particularly in developing nations striving to manage and maintain road networks as valuable assets. While asset generation is integral, the more intricate challenge lies in effective maintenance. Pavement monitoring, a crucial component of pavement maintenance and management systems (PMMS), evaluates defect severity, road maintenance prioritization, and maintenance types. To enhance road health monitoring, the present study introduces a hybrid machine learning (ML) method, integrating support vector machine (SVM) and convolutional neural network (CNN). The proposed semi-automated detection system aims to reduce human supervision in traditional surveys, thereby cutting down the cost of pavement distress maintenance The research utilizes data collected by the authors from Ahmedabad city, Gujarat, following Indian road congress (IRC) guidelines for defect selection. Training involves 1,000 images for each crack type, with testing on 100 images. Results indicate that the SVM-CNN model achieves 87% accuracy in training and 91% accuracy in testing for road defect classification, showcasing its efficiency in pavement maintenance and management. The system presents the potential to significantly enhance the efficiency of road maintenance processes, making it a valuable asset for developing nations striving for a more streamlined approach to road network preservation.

Review of Pavement Crack Types and Their Significance

This essay examines the significant importance of pavement distress detection, specifically in the capacity to identify and categorize various forms of cracks, in order to uphold road safety. This study explores the impact of technical breakthroughs on the detection and classification of pavement cracks, leading to notable improvements in road maintenance and accident prevention. The essay additionally explores a range of studies that indicate a connection between pavement conditions and traffic safety, including the association between pavement age and the likelihood of accidents, as well as the influence on the severity of crashes. This analysis serves to illustrate the paramount significance of maintaining pavement integrity in order to ensure traffic safety. The essay foresees future progress in crack detection techniques, highlighting their crucial role in the construction of safer road networks and the improvement of public safety.

An appraisal of statistical and probabilistic models in highway pavements

Accurate performance prediction is crucial for safe and efficient travel on highway pavements. Within pavement engineering, statistical models play a pivotal role in understanding pavement behavior and durability. This comprehensive study critically evaluates a spectrum of statistical models utilized in pavement engineering, encompassing mechanistic-empirical, Weibull distribution, Markov chain, regression, Bayesian networks, Monte Carlo simulation, artificial neural networks, support vector machines, random forest, decision tree, fuzzy logic, time series analysis, stochastic differential equations, copula, hidden semi-Markov, generalized linear, survival analysis, response surface methodology and extreme value theory models. The assessment meticulously examines equations, parameters, data prerequisites, advantages, limitations, and applicability of each model. Detailed discussions delve into the significance of equations and parameters, evaluating model performance in predicting pavement distress, performance assessment, design optimization, and life-cycle cost analysis. Key findings emphasize the critical aspects of accurate input parameters, calibration, validation, data availability, and model complexity. Strengths, limitations, and applicability across various pavement types, materials, and climate conditions are meticulously highlighted for each model. Recommendations are outlined to enhance the effectiveness of statistical models in pavement engineering. These suggestions encompass further research and development, standardized data collection, calibration and validation protocols, model integration, decision-making frameworks, collaborative efforts, and ongoing model evaluation. Implementing these recommendations is anticipated to enhance prediction accuracy and enable informed decision-making throughout highway pavement design, construction, maintenance, and management. This study is anticipated to serve as a valuable resource, providing guidance and insights for researchers, practitioners, and stakeholders engaged in asphalt engineering, facilitating the effective utilization of statistical models in real-world pavement projects.