Pavement Damage Research Articles

Innovative method for pavement multiple damages segmentation and measurement by the Road-Seg-CapsNet of feature fusion

Deep learning algorithms have achieved promising results in the field of pavement damage segmentation. Since the texture features of map crack damage are complex, existing segmentation methods may experience the problem of edge information loss for the damaged area. In this study, we therefore propose Road-Seg-CapsNet, a feature fusion model combined with StyleGAN, to segment multiple complex forms of damage to asphalt pavements. Firstly, a data enhancement algorithm based on StyleGAN is developed to amplify the dataset. Next, padding convolution is used in the convolution layer of Road-Seg-CapsNet to retain more image edge information, which effectively solves the problem of information loss at the edges of areas of damage with map cracks. The feature map in the upsampling layer is fused with the features of the convolutional layer to improve the segmentation accuracy of the model. An optimised dynamic routing algorithm is then applied, which reduces the model parameters and improves the efficiency of model training. Our experimental results show that the segmentation mAP of the proposed model can reach 0.942. To verify the superiority of the proposed method, a comparative experiment with FCN, Mask R-CNN and optimised Mask R-CNN is carried out. Based on the segmentation results, a quantification and measurement experiment is carried out, and the minimum accuracy for the damaged areas is found to be 0.903.

Drone usage for pavement damage identification

Abstract: The timely use of appropriate renovation measures can effectively extend the life of road surfaces. For this purpose, it is necessary to carry out a detailed identification of damage, and then on its basis to assess the condition of road surfaces. Due to the development of advanced measurement techniques and computer applications, damage to pavements can be monitored faster and more accurately. This article presents a method of identifying damage to the pavement of a large area of the square with the use of a drone. The applicated method allowed to visualize and differentiate various surface defects faster and more preciously. The method also enabled determine causes and genesis of damage more greatly. Keywords: Drone; Pavement damage; DJI SPARK, Damage Identification

Prediction of interlayer shear strength of double-layer asphalt using novel hybrid artificial intelligence models of ANFIS and metaheuristic optimizations

The pavement damages such as slipping, rutting, top-down cracking of flexible pavement are very common during the operation process. These damages are mainly caused by interlayer shear stress acting between the asphalt layers during traffic movement. This is one of the main reasons for reduced pavement service life and increased maintenance costs. Therefore, the Interlayer Shear Strength (ISS) parameter needs to be evaluated and accurately predicted. Generally, ISS of double–layer asphalt concrete is measured directly in the field or on the samples in the laboratory, which involves much time and cost. Therefore, in this study, we have estimated ISS of asphalt pavement based on three input parameters: temperature, normal pressure and aggregate diameter using novel hybrid machine learning models namely Culture Algorithm based Adaptive Neuro Fuzzy Inference System (ANFIS-CA), Differential Evolution based Adaptive Neuro Fuzzy Inference System (ANFIS-DE) and Invasive Weed Optimization based Adaptive Neuro Fuzzy Inference System (ANFIS-IWO). Estimated shear strength was compared with the direct measured shear strength for the validation of model’s performance. In this study results of 180 double-layer asphalt samples which were fabricated by three different mixtures of Dmax 12.5, Dmax 19 and Dmax 25 and tested by shear device in the laboratory with five levels of normal pressure (0, 0.14, 0.2, 0.4, 0.6 MPa) at three temperature levels (25, 40 and 60 °C) were considered. Standard statistical measures namely Mean Absolute Error (MAE), Root-Mean-Square Error (RMSE), and Correlation Coefficient (R) were used to assess the models’ prediction capabilities. The results exhibit that all the suggested models have high accuracy of prediction, but performance of ANFIS-IWO (MSE = 0.02, MAE = 0.024, RMSE = 0.047, and R = 0.953) is slightly better than ANFIS-CA (MSE = 0.04, MAE = 0.031, RMSE = 0.047, and R = 0.966) and ANFIS-DE (MSE = 0.03, MAE = 0.034, RMSE = 0.057, and R = 0.953). Therefore, all the proposed models are suitable and powerful potential tools for the accurate prediction of the ISS for the proper consideration of pre-construction and post-construction pavement asphalt mixture design but the ANFIS-IWO model is the best.

A road pricing model involving social costs and infrastructure financing policies

This research develops a non-linear continuous optimisation model to estimate tolls for multi-class and multi-period traffic considering integral social costs such as congestion externalities, pavement damage, environmental emissions, operational travel costs, and user travel time cost, in addition to maintenance and construction of road infrastructure costs. The approach uses social welfare principles, formulating a function to calculate the social welfare of a multi-class flow that moves in multiple periods based on a stochastic discrete choice model and considering infrastructure financing constraints. A case study was conducted applying the model to a road in the Colombian Caribbean region and estimated the value of tolls using the particle swarm optimisation heuristic. Results showed that infrastructure policies considering partial financing resulted in higher social welfare values. Scenarios requiring toll revenue to be higher than infrastructure cost can shrink demand and cause distributive issues.

Comparison of the response of an instrumented pavement section under individual and platoon truck loading

ABSTRACT Truck platooning is a recent solution proposed to optimise road transportation. Platooning can help improve transport efficiency and road safety, reduce traffic congestion, fuel consumption and greenhouse gases emissions. Considering that truck platoon configurations are new, studying their impact on pavement response and damage is crucial. In this context, this study presents the results obtained in a full-scale experiment designed to evaluate the structural responses of a test track subjected to the pass of trucks under two configurations: individual and platoon. The pavement was instrumented to measure the transverse and longitudinal strains at the bottom of the asphalt layers of the pavement structure. Strains were measured under two test configurations, individual trucks and platoons, for four vehicle speeds: 40 , 60 , 70 , and 80 km/h. In order to consider the weather influence, two test campaigns were performed, one during the winter and the other during the summer. The study's main conclusion is that by managing inter-truck distances, truck speeds, lateral deviation (wandering), time, and periods of circulation, it is possible to minimise the impact of platooning trucks on the pavement's structure responses.

Analysis on factors affecting the cooling effect of optical shielding in pavement coatings

Inspired by transparent heat-shielding research, three tungsten bronze nanoparticles (i.e., nano-cesium tungsten bronze (Cs0.3WO3), nano-sodium tungsten bronze (Na0.28WO3) and nano-potassium tungsten bronze (K0.26WO3)) with excellent near-infrared light absorption properties were applied for the first time to prepare pavement coatings so as to alleviate the temperature-related damage of pavement and urban heat island effect. X-ray diffraction (XRD), scanning electron microscopy (SEM), ultraviolet–visible–near infrared spectrometer (UV/VIS/NIR), self-made indoor simulated solar radiation apparatus were employed in this research to study the application of nano tungsten bronze into pavement, as well as its benefit. It was found that the solar reflectivity of the coating is between 3.22% and 6.29%, which is very close to that of asphalt binder, which is 5.24%. The coating made of Cs0.3WO3 nanoparticles reduced the temperature most significantly among all specimens, and the combination of theoretical optimal cooling effect was determined. The correlation between the temperature rising value of the specimen coated with the most effective coating and that of the control specimen was established, which provided a basis for predicting the cooling value of the coating.

A review on the utilization of waste material in asphalt pavements.

Recycling of waste and disposal has become a vital environmental issue that creates serious concern worldwide. The use of waste material in pavement structure is one of the essential initiative for the future towards sustainable environment. This study imparts a review on waste materials such as plastic waste, crumb rubber, glass fibre, steel slag, crushed concrete and Low Density Polyethylene (LDPE) and their use in asphalt pavements. The waste materials act as modifiers and have the capability to upgrade the performance of pavement and provide green technology with eco-friendly environment. Utilization of waste material as an asphalt binder enhanced the engineering properties of asphalt pavements. It may be regarded as a smart strategy for sustainable development as it is cost-effective, economical, efficiency and productivity. Moreover, it approached to minimize the pollution. Further, many researchers have investigated the outcomes of asphalt pavement with waste and observed that it achieved the properties and performance of asphalt mixtures while reducing pavement damage, failure and deformation.

The Effect of Pavement Damage on Number of Accidents and on Traffic Congestion on Roads Using Multivariate Analysis of Variance

Traffic road accidents are a concern for every elected government since it affects the socio and economic well-being of a country. Kenya has experienced high number of road accidents claiming more than three thousands lives every year. The cause of traffic road accidents is usually blamed on the drivers, pedestrians, lack of adequate enforcement of traffic laws, quality of roads among other reasons. The government has tried to address this road carnage by coming up with road safety measures and improvement of road infrastructure. In this paper Multivariate Analysis of Variance (MANOVA) has been used to study the effect of pavement damage on number of accidents and on time spent on roads. By considering two dependent variables (the number of accidents and traffic congestion on roads) and two factors (damage on pavement and type of vehicle), a 2×3 design with 4 replications, for a total of 24 observation vectors has been developed. Significance tests involving the individual dependent variables have been carried out. Using the sampled data from Nairobi, it has been determined that type of vehicle has a significant effect on the number of accidents and traffic congestion on roads. It is also determined that damage of pavements does not have significant effect on the number of accidents and traffic congestion on roads.

Analysis of Tire‐Pavement Contact Morphology Characteristics during the Virtual Track Train Maneuvering

The tire‐pavement contact morphology during the virtual track train maneuvering has an essential function in assessing vehicle performance and pavement damage. The longitudinal tread tire and viscoelastic asphalt pavement were developed based on the finite element method. Then, the tire‐pavement contact model was developed according to the Euler–Lagrange algorithm and validated. Contact area and stress distribution under uniform, braking, and cornering conditions are explored with the dynamic tire force of the virtual track train as the external load. Also, the effect factors were analyzed. The results indicate that vertical stress distribution is symmetrical along the length and width directions, and contact area is rectangular under uniform condition. Vertical and longitudinal stresses have similar distributions under braking condition, with a wide front and a narrow back along the length direction. Under cornering condition, the closer to the inside of the cornering, the larger the contact area. Vertical stress is similar to the lateral stress distribution, and the larger stress value is concentrated on the inner side of each tread. Load, tire pressure, slip rate, and slip angle have significant effects on contact morphology, while velocity has little effect. Contact area increases with the increase of load and slip rate and decreases with the increase of tire pressure and slip angle. Vertical stress increases gradually with the increase of load. Higher tire pressure makes stress distribution more concentrated. The increase in slip rate increases vertical and longitudinal stresses and gradually moves in the running direction. Vertical and lateral stresses increase with the slip angle and are mainly distributed on the inside of the turn. This research can be used to evaluate and analyze the response and damage of the virtual track train to asphalt pavement under uniform, braking, and cornering conditions. It can be used as a reference for the design and paving of asphalt pavement.

New Approach to Determine Standard Deviation and Precision Estimates for ASTM D4867/D4867M and AASHTO T283

Abstract Moisture damage in asphalt pavements can be attributed to the incompatibility of the asphalt binder, aggregate, or the interaction of the asphalt binder and aggregate. Moisture damage can accelerate pavement distresses such as cracking and rutting. The most widely used test methods by state highway agencies are AASHTO T283-14, Standard Method of Test for Resistance of Compacted Asphalt Mixtures to Moisture-Induced Damage, and ASTM D4867/D4867M-09, Standard Test Method for Effect of Moisture on Asphalt Concrete Paving Mixtures. Some state highway agencies evaluate moisture resistance during production to ensure a quality asphalt mixture. Currently AASHTO T283-14 and ASTM D4867/D4867M-09 do not provide a method to calculate the standard deviation of the tensile strength ratio (TSR), nor does it provide precision estimates for the TSR. The objective of this paper is to show how one can calculate the variance (or standard deviation) of a variable when the value of interest (i.e., TSR) is calculated from two other random variables. The standard deviation of a random variable that is a quotient of two other variables can be calculated easily as long as the individual variables are random, independent, and the standard deviations are small relative to the mean. The novelty of this approach is in a statistics-based method for determining the standard deviation of the TSR based on using an approximation for the ratio variance using ASTM D4460-97, Standard Practice for Calculating Precision Limits Where Values Are Calculated from Other Test Methods. This new approach to calculate the standard deviation of the TSR will be used to develop a precision statement for AASHTO T283-14 and ASTM D4867/D4867M-09 following ASTM E691-19e1, Standard Practice for Conducting an Interlaboratory Study to Determine the Precision of a Test Method (Superseded).

Transfer learning based deep convolutional neural network model for pavement crack detection from images

The road is a path that supports to connect different places. It plays a crucial role in our day-today life. Improper maintenance, overloading, climate conditions, and some other elements create distress on the roads. The common distresses are Potholes, cracking, and rutting. Manually detecting the distresses means human inspection is a messy and long time-consuming process. In recent past accidents on road is on the increase due to improper maintenance of road. Efficient methods of detecting pavement damages using image processing, machine learning and deep learning techniques have been a trending research topic. Image processing algorithms mainly include edge detection, region growing methods, and threshold segmentation operations for processing the pavement images and extracting crack information from the images. Machine learning methods of pavement crack detection adapts neural networks, supervised and unsupervised learning algorithms with pavement crack image as input. With Deep learning techniques, it has been possible to detect pavement cracks with greater accuracy. In this paper, we review the deep learning methods of pavement crack detection and propose a novel method to detect pavement cracks using Deep Learning with transfer learning. We also analyzed the performance of the proposed model for different network architectures namely, Google net, Alexnet and Resent and inferred that Google net gives better performance in detecting pavement cracks.

Developing a Maintenance Model for Pavements Vulnerable to Climate Change in South Eastern Nigeria

The South East region of Nigeria faces widespread flood during rainy seasons as a result of inadequate drainage channels, poor drainage management and most often the absence of drainage. The increase in rainfall can be attributed to climate change. Climate change has become one of the most common sources of road pavement failure in the region which leads to rapid need of maintenance as a result of flooding and this problem is becoming worse yearly. Most roads in the region suffer submergence because of flooding. In this research work, a predictive model will be developed to control maintenance of road infrastructural systems in the South-East in terms of fatigue. This work is limited to pavement behavior with respect only to fatigue life using the mechanical/elastic properties as the input parameter using additives in the established failure conditions considering Federal roads in the South East as case studies. It is also important to note that the research has a well-defined assumption within the scope to expectancy is 20 years. The loads causing pavement failure are ≥80 KN single axle. Passenger cars will not be included in the passenger. The performance of flexible pavement in real life is synonymous with performance of hot mix asphalt concrete (HMA) in the laboratory. The fatigue life of a pavement is the number of load repetitions ≥80 KN single axle load and finally, traffic loads and moisture are the only contributors to pavement damage.

Deep Learning-Based Thermal Image Analysis for Pavement Defect Detection and Classification Considering Complex Pavement Conditions

Automatic damage detection using deep learning warrants an extensive data source that captures complex pavement conditions. This paper proposes a thermal-RGB fusion image-based pavement damage detection model, wherein the fused RGB-thermal image is formed through multi-source sensor information to achieve fast and accurate defect detection including complex pavement conditions. The proposed method uses pre-trained EfficientNet B4 as the backbone architecture and generates an argument dataset (containing non-uniform illumination, camera noise, and scales of thermal images too) to achieve high pavement damage detection accuracy. This paper tests separately the performance of different input data (RGB, thermal, MSX, and fused image) to test the influence of input data and network on the detection results. The results proved that the fused image’s damage detection accuracy can be as high as 98.34% and by using the dataset after augmentation, the detection model deems to be more stable to achieve 98.35% precision, 98.34% recall, and 98.34% F1-score.

Performance of Concrete Pavement Incorporating Portland Limestone Cement in Cold Weather

The City of Winnipeg (COW) and the University of Manitoba (UM), Canada, have partnered since 2015 to conduct research on the use of portland limestone cement (PLC), comprising up to 15% limestone filler, in transportation infrastructure such as pavements and bridges. Laboratory tests have substantiated the equivalent or superior resistance of concrete made from PLC, relative to that made from general use (GU) cement (Type I) to durability exposures including acids, sulfate salts and chloride-based deicing salts. Subsequently, a field trial was done in 2018, which involved casting two concrete pavement sections made from PLC and GU cement in Winnipeg, Manitoba, Canada. The current paper reports on the construction and long-term (three years/winter seasons) properties of these pavement sections including fresh properties, strength, absorption and chloride ions penetrability, as well as microstructural features. Cores were taken from mid-slabs and at joints, which are the most vulnerable locations to damage in concrete pavements. The field trial results showed that concrete pavement sections made with PLC had equivalent or superior performance compared with those made of GU in terms of fresh, hardened and durability properties. Thus, it presents a viable option for sustainable construction of concrete flatwork in cold regions.

Dynamic response analysis of vehicle and asphalt pavement coupled system with the excitation of road surface unevenness

This study aims to solve the dynamic responses of the vehicle and asphalt pavement coupled system while considering road surface unevenness and deformation. First, an advanced solving procedure is proposed by decoupling the vehicle-pavement coupled system into two subsystems (i.e., quarter vehicle model with two degrees of freedom, and viscoelastic multilayered asphalt pavement) and solving them independently until the surface deformation has converged through an iterative scheme. During the solving procedure, the finite difference method and integral transform techniques are respectively conducted to compute the dynamic responses of vehicle and pavement. Then, the solutions for the dynamic responses of the pavement are verified through finite element simulation, which highlights the accuracy and efficiency of the proposed solution. The convergence study for the iterative procedure of vehicle-pavement coupled system is conducted, and the coupling effect on pavement and vehicle displacements is investigated. Finally, the effects of the vehicle and pavement parameters (i.e., suspension stiffness and damping, tire stiffness and damping, road surface unevenness, and pavement temperature and vehicle speed related to the viscoelasticity of asphalt material) on the pavement dynamic responses and damages are discussed comprehensively. These numerical investigations could prove that the solutions for the dynamic responses of the vehicle-pavement coupled system has the potential to guide road-friendly vehicle design and pavement service life evaluation.

Backcalculation of damage density of in‐service asphalt pavements using artificial intelligence‐based finite element model updating

AbstractFatigue damage is a common distress significantly affecting asphalt pavements in the performance, economy, and safety aspects. Accordingly, this paper aims to propose a methodology to backcalculate a continuum damage mechanics (CDM)‐based damage density of in‐service asphalt pavements from field nondestructive testing (NDT). An artificial intelligence (AI)‐based finite element (FE) model updating was applied with the falling weight deflectometer (FWD) test results for the calibrations of the damage density and supporting layer moduli. The development of the damage density with pavement service time was categorized and fitted with proposed analytical models. The damage density was compared with field observations on the fatigue cracking performance of asphalt pavements. It was found that the damage density had close relations with the material type, structural configuration, and fatigue cracking area of the pavement. This study shows a promising application of the damage density in the evaluation and prediction of the fatigue damage of asphalt pavements, which will lead to a timely and cost‐effective pavement maintenance and rehabilitation.

Climate Change Challenges for Flexible Pavement in Canada: An Overview

This paper provides an outlook on the effects of climate change and the severity and frequency of extreme weather events on the performance of flexible pavements across North America. Now more than ever, the climate is changing at a rapid pace, which will alter long-term environmental loading parameters and extreme weather events. Such alterations will pose implications for the design, maintenance, and rehabilitation of flexible pavements, especially in terms of their serviceability, safety, and functionality. In northern Canada, roads are founded on various terrain types, including thaw-sensitive ice-rich permafrost underlying terrains. Such roads have experienced signs of embankment and pavement damage, which are usually induced by the degradation of the underlying permafrost due to climate change. Therefore, the development and implementation of new permafrost thaw mitigation techniques for vulnerable roads are essential and will be discussed in this paper. Resilient flexible roads should be designed to withstand the conditions that are likely to occur during their design life, taking into account the impact of the climate change on pavement performance in response to daily and seasonal changes in heat, precipitation, freeze–thaw cycles, and extreme weather events.

Effect of MIST Conditioning on Moisture-Induced Damage of RAP Mixes Using Elastic Moduli and Stress–Strain Behavior

Moisture-induced damage of asphalt pavements constitutes a primary distress. To quantify the extent of moisture-induced damage efficiently, a moisture-induced stress tester (MIST) was developed. This study adopts varying stress cycles of MIST to condition the asphalt mixes without and with reclaimed asphalt pavement (RAP) to ascertain their moisture-induced damage resistivity. Hence, the control mix (0% RAP) and mixes containing 10%, 20%, 30%, and 40% RAP by weight were prepared and conditioned using 0, 1,000, 2,000, 3,500, 5,000, and 10,000 stress cycles of MIST. Thereafter, an indirect tensile (IDT) strength test was conducted on the prepared mixes. Using analytical approaches, the biaxial state of stress was defined to compute the static (ES,H) and average modulus (ES,A). Increasing stress cycles of MIST decreased the stiffness of control and RAP mixes. The compressive stress–strain curve (SSC) was plotted and utilized to compute the linearity and toughness index (TI) of control and RAP mixes. Increasing stress cycles of MIST were observed to increase the ductility of control and RAP mixes, whereas prepeak linearity was observed to reduce it. The TI increased with the increase in stress cycles of MIST. New moisture damage ratios (MDRs) were computed by utilizing ES,H and ES,A and compared with the commonly adopted tensile strength ratio (TSR). Based on such MDRs, it was concluded that RAP improves the moisture-induced damage resistivity of asphalt mixes. Statistical analysis indicated that both ES,H and ES,A have the potential to be good indicators of moisture-induced damage of control and RAP mixes.

PENGARUH BEBAN LALU LINTAS TERHADAP KERUSAKAN LENTUR DI JALAN TOL BERDASARKAN METODE PAVEMENT CONDITION INDEX (Studi Kasus Ruas Lingkar Luar Jakarta (JORR) W2 Utara Jalur A dan B)

Jorr toll road function as a network of roads that serves to break down the traffic that currently accumulates in the city of Jakarta, so that this toll road will facilitate the flow of traffic from bogor / Jagorawi towards Tangerang / Merak, and vice versa. With the perfect JORR, it will be one of the alternatives to Soekarno-Hatta International Airport. Jakarta W2 Utara Outer Ring Road is often crowded with traffic during certain hours. So in the field there are many locations of pavement damage where as large in the lane of heavy-laden and overloaded vehicles. Differences in traffic load can cause different levels of road damage between lanes. The extent of road damage can be evaluated by using the PCI method. The purpose of this study is to evaluate the effect of traffic load on flexible damage based on PCI method with the level and type of damage in each lane can be identified.

Comparison of PCI (Pavement Condition Index) and SDI (Surface Disstres Index) in Identification of Urban Road Damage

The S. Parman road section is an access to two universities as well as access to the north of Jakarta using flexible pavement. Various heavy and light vehicles pass through these roads, causing road damage. Evaluation of the condition of road damage is very necessary to monitor the level of road damage that occurs on a road segment. This study aims to determine the level of damage that occurs, as well as determine the appropriate type of road damage handling. The method used in assessing the condition of road pavement damage is the PCI (Pavement Condition Index) and SDI (Suface Distress Index) method, which conducts a visual survey by viewing and analyzing the damage based on the type, level of damage and quantity of damage to be used as a basis for carrying out maintenance and repair activities. repair. How to analyze it by dividing the road into a sample of 100m. The results of the research on the condition of the Letjen S. Parman road (Grogol direction Slipi) with the PCI method obtained the overall average PCI value of the Letjen S. Parman road section is Perfect (Exellent) as much as 78.5%, Very Good (Very Good) as much as 16 .6%, and Good (Good) as much as 4.9% and the results of the research on the condition of the road section of Letjen S. Parman (Grogol direction of Slipi) with the SDI method, the overall SDI value of the road section of Letjen S. Parman is 65 for the score the highest score at stationing 3+900-3+800 and 0 for the lowest score at stationing 3+400-3+300.