Roughness Index Research Articles

Research and comparison of pavement performance prediction based on neural networks and fusion transformer architecture

<abstract> <p>The decision-making process for pavement maintenance from a scientific perspective is based on accurate predictions of pavement performance. To improve the rationality of pavement performance indicators, comprehensive consideration of various influencing factors is necessary. To this end, four typical pavement performance indicators (i.e., Rutting Depth, International Roughness Index, Longitudinal Cracking, and Alligator Cracking) were predicted using the Long Term Pavement Performance (LTPP) database. Two types of data, i.e., local input variables and global input variables, were selected, and S-ANN and L-ANN models were constructed using a fully connected neural network. A comparative analysis of the predictive outcomes reveals the superior optimization of the L-ANN model. Subsequently, by incorporating structures such as self-attention mechanism, a novel predictive approach based on the Transformer architecture was proposed. The objective is to devise a more accurate predictive methodology for pavement performance indices, with the goal of guiding pavement maintenance and management efforts. Experimental results indicate that, through comparative analysis of three quantitative evaluation metrics (root mean square error, mean absolute error, coefficient of determination), along with visual scatter plots, the predictive model employing the fused Transformer architecture demonstrates higher robustness and accuracy within the domain of pavement performance prediction when compared to the L-ANN model. This outcome substantiates the efficacy and superiority of the model in terms of predictive performance, establishing it as a reliable tool for accurately reflecting the evolution of asphalt pavement performance. Furthermore, it furnishes a theoretical reference for determining optimal preventive maintenance timing for pavements.</p> </abstract>

Pavement maintenance strategy for Provincial roads in Tarakan City, North Kalimantan

Tarakan City has several road segments on provincial roads that have experienced significant damage in the form of sinkholes and substantial potholes on the road surface. These deteriorations are primarily attributed to the impact of traffic, excessive traffic loads, subgrade soil conditions that fall short of requirements, and the use of pavement materials that do not meet the specified standards. To devise effective road repair plans, the collection of field data is crucial. Two distinct methods are employed for data collection to assess pavement conditions: the International Roughness Index (IRI) and the Surface Distress Index (SDI). The IRI method measures road roughness using the Rough meter III instrument, while the SDI method focuses on parameters like crack area, crack width, pothole count, and wheel path rut depth. The surveyed road sections encompass Amal Lama, Gunung Selatan, Aji Iskandar, Bhayangkara, Aki Pingka, and the Ring Road of Tarakan City. Research findings reveal the surface damage level of roads in Tarakan City using the SDI and IRI methods, with the following breakdown: roads in good condition account for 42.86%, those in moderate condition make up 51.90%, slightly damaged roads constitute 4.8%, and heavily damaged roads represent 0.44%. Additionally, the study has determined the percentage of each type of maintenance required: Routine Maintenance at 94.77%, Periodic Maintenance at 4.8%, and Reconstruction at 0.44%.

Machine Learning-Based Prediction of International Roughness Index for Continuous Reinforced Concrete Pavements

Machine Learning-Based Prediction of International Roughness Index for Continuous Reinforced Concrete Pavements

Impact of Sasobit on Asphalt Binder’s Performance under UAE Local Conditions

Asphalt pavements are the backbone of the transportation system. In light of the rising costs of energy and materials and the growing emphasis on sustainable infrastructure, there has been a push to enhance the performance of asphalt pavements. One of the primary methods for achieving this goal is the incorporation of warm mix additives into the asphalt binder. This study investigated the impact of Sasobit on the asphalt binder by adding 2% and 4% of Sasobit, by weight, to the asphalt binder. The following tests were conducted: penetration, softening point, rotational viscosity, and high-temperature performance. The results demonstrated that the addition of Sasobit at 2% and 4% concentrations resulted in a 25% and 30% reduction in penetration, respectively, accompanied by a 26% and 71% increase in the asphalt binder's softening point, as well as a 17°C and 36°C rise in the softening point, respectively. Additionally, the viscosity at 135°C and 165°C and the mix and compaction temperatures decreased by 30% and 25%, respectively. Utilizing the outcomes mentioned above, AASHTOWare simulations were conducted to assess the impact of local climate conditions and gradation. The simulations demonstrated that adding Sasobit resulted in enhanced service life, as evidenced by the International Roughness Index, permanent deformation, and bottom-up fatigue. The simulations and test results collectively indicate that Sasobit's incorporation could be advantageous for local asphalt pavements. The authors recommend further testing the effect of Sasobit on the performance of asphalt mixes in rutting, fatigue, and moisture damage.

Predicting the International Roughness Index of JPCP and CRCP Rigid Pavement: A Random Forest (RF) Model Hybridized with Modified Beetle Antennae Search (MBAS) for Higher Accuracy

Predicting the International Roughness Index of JPCP and CRCP Rigid Pavement: A Random Forest (RF) Model Hybridized with Modified Beetle Antennae Search (MBAS) for Higher Accuracy

Research progress of ultrasound in accurate evaluation of cartilage injury in osteoarthritis.

Osteoarthritis (OA) is a prevalent cause of joint algesia, loss of function, and disability in adults, with cartilage injury being its core pathological manifestation. Since cartilage damage is non-renewable, the treatment outcome in the middle and late stages of OA is unsatisfactory, which can be minimized by changing lifestyle and other treatment modalities if diagnosed and managed in the early stages, indicating the importance of early diagnosis and monitoring of cartilage injury. Ultrasound technology has been used for timely diagnosis and even cartilage injury treatment, which is convenient and safe for the patient owing to no radiation exposure. Studies have demonstrated the effectiveness of ultrasound and its various quantitative ultrasound parameters, like ultrasound roughness index (URI), reflection coefficient (R), apparent integrated backscatter (AIB), thickness, and ultrasound elastography, in the early and accurate assessment of OA cartilage pathological changes, including surface and internal tissue, hardness, and thickness. Although many challenges are faced in the clinical application of this technology in diagnosis, ultrasound and ultrasound-assisted techniques offer a lot of promise for detecting early cartilage damage in OA. In this review, we have discussed the evaluation of ultrasonic cartilage quantitative parameters for early pathological cartilage changes.

Pavement Sections’ Reliability Based on Deterioration Model Using Artificial Neural Network (ANN)

Pavement distresses, such as cracks and ruts, reduce pavements’ effectiveness and serviceability and can lead to failure. This underlines the importance of predicting pavements’ deterioration in pavement management systems (PMSs) for effective maintenance and rehabilitation (M&R) strategies. Consequently, it is essential to understand the concept of service life, which represents how long a pavement will remain in service based on how reliable it is. This study introduces a pavement deterioration model using data from the Long-Term Pavement Performance program for the international roughness index (IRI) and other factors. Different machine learning methods were utilized in developing the model to incorporate eight factors that significantly affect pavement roughness; these methods are: linear regression, regression tree, Gaussian Process Regression (GPR), Support Vector Machine (SVM), Ensemble Trees, and Artificial Neural Network (ANN). For comparison, the models’ performances were evaluated using Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and R squared (R2). The weights and biases of the best model and the Federal Highway Administration (FHWA) recommended IRI ranges were utilized to create the limit state function. A reliability analysis using Monte Carlo Simulation (MCS) was determined to calculate the sections’ probability of failure. This study concluded that pavement sections in the US and Canada are reliable and that the mean yearly Kilo Equivalent Single Axle Load (KESAL) significantly contributes to pavement failure. Keywords: Pavement deterioration, IRI, Machine learning, Neural network, Pavement reliability, Probability of failure.

Traffic Noise Prediction for Delhi-NCR using Multiple RegressionModelling Approach

Traffic noise prediction models are crucial for designing highways to implement preventive measures against traffic noise pollution by analyzing future trends. This study aims to identify the traffic, road geometrical, and environmental parameters that escalate traffic noise pollution, enabling rectification of influencing factors and enhancement of strategies to reduce this pollution. A traffic noise prediction model was developed for the highways of Delhi-NCR using the Multiple Regression approach, incorporating various traffic, geometric, and environmental parameters. Statistical analysis was conducted, and the model was formulated based on data collected from 31 sampling stations on two major Delhi highways. Significant variables identified include the number of lanes, average building height, international roughness index, temperature, wind speed, and humidity. The model’s validity is affirmed by a coefficient of determination R2 = 0.75, indicating a good fit.

Modelling the effects of flexible pavement distresses in the long-term pavement performance database on performance

Evaluating flexible pavement performance is mandatory for managing transport infrastructure. This study focuses on modeling the relationships between international roughness index (IRI) and a total of 10 types of pavement distress, including alligator, block, wheel path length, wheel path longitudinal, non-wheel path longitudinal, transverse crackings, patches, bleeding, raveling areas, and pumping. The data recorded under the Long-Term Pavement Performance was used to develop the models. Data sets covering General Pavement Studies from seven states of the United States were used in modeling. The study used modeling approaches, including nonlinear regression analysis, multivariate adaptive regression splines, and artificial neural networks (ANN), in which IRI was the dependent variable and pavement distress was the independent variable. In the developed models, 0.516, 0.623, and 0.684 regression coefficients values were obtained for nonlinear regression analysis, multivariate adaptive regression splines, and artificial neural networks approaches, respectively. The analysis results have determined that the artificial neural networks technique performs more successfully than the other techniques. The statistical error analyses of the root mean square error, Nash-Sutcliffe coefficient of efficiency, mean absolute error, and normalized root mean square error also showed that the same modeling approach performs more successfully. With these data generated from a universally used database, it has been determined once again that ANN is the most efficient mathematical approach in modeling the relationships between surface distresses and IRI.

ХАРАКТЕРИСТИКИ ПОВЕРХНІ ПОКРИТТЯ ДОРОЖНЬОГО ОДЯГУ СТАНДАРТНІ МЕТОДИ ВИМІРЮВАННЯ

Abstract. The texture of a road pavement surface and its skid resistance which concerns its ability to resist the vehicle wheel skidding have been accepted worldwide as the road safety criterion. These characteristics are interconnected in that the texture affects the skid resistance. The goal of the paper is to carry out the comparative analysis of valid road safety and performance parameters and its dependence on the road pavement surface texture and the comparative analysis of international and regional standard methods of road surface texture and skid resistance measurements covering methods acceptable for the road network survey. The main principles of the road pavement surface texture categorization were analyzed with its ranging as micro-, macro- and megatexture where the microtexture parameters sufficiently influence adhesion between pavement and tire especially in wet conditions. It was stated also that the macro- and megatexture parameters govern the rolling resistance and dynamic effect where the last is attributable to the comparable dimensions of the megatexture wavelength and the tire footprint and also affects the increase in loading that may be equal to the additive ESALs up to 40 %. The high-range wavelength roughness exceeding λ = 500 mm should be viewed as the road surface unevenness, as the feature negatively governing the vehicle road-holding ability. Also the contemporary high-performance techniques and methods for the road pavement surface skid resistance determination were reviewed and it was shown that these method and the according equipment should be divided as performing the longitudinal friction measurements or the side-way force measurements to be carried out under conditions that allow the investigators to distinguish the contribution made by the road pavement surface characteristics to the friction force. The possibilities of the usage of the results of the mathematical analysis of the road surface profile survey were analyzed separately and it was shown that the power spectral density can be accepted as a valid parameter for non-direct estimation of the road surface texture through international roughness index IRI. Keywords: road pavement, surface texture, profilometer, skid resistance, slid angle, friction coefficient, international roughness index.

Road Maintenance Management Based on Geographic Information System (GIS)

This research implements GIS in transportation, specifically road maintenance. The system is built by utilizing 2D/3D models from aerial photographs using UAV as a base map. Attribute data such as the type and dimensions of road damage can be obtained by interpreting high-resolution 2D/3D models, which display each road damage, making it easier to measure the dimensions of road damage. The assessment of road conditions is done using the PCI method, which indicates that 51% of the roads fall under the category of people with low incomes to severely damaged category. These roads are prioritized on a map based on their area and cost of maintenance. The projection calculation of the amount of damage is analyzed with one do-nothing scenario, where the roads have not been maintained for ten years. The progression of the damage is observed each year, and the reactive maintenance cost is calculated from 2023 to 2032. The cost and duration are analyzed using three do-something scenarios: optimistic, moderate, and pessimistic. The research results show that the moderate scenario has the lowest cost among the other scenarios and is the most effective scenario, as it produces road conditions with an International Roughness Index (IRI) value of less than 6. This research can assist the government in making informed decisions regarding road maintenance.

Investigation of Medium-Term Performance of Porous Asphalt and Its Impacts on Tire/Pavement Noise

To assess the medium-term performance of porous asphalt pavement during service and its influence on tire/pavement noise level, a seven-year continuous observation and data analysis study was conducted. Key performance indicators were measured and calculated by using automated pavement technology testing equipment. The noise levels were tested by using the on-board sound intensity (OBSI) method on three types of porous asphalt pavements (PUC-10, PAC-13, and PUC-10 + PAC-13) and one dense thin layer course (DTC) for comparison. The findings indicated that the Damage Rate (DR) and Surface Friction Coefficient (SFC) of porous asphalt pavements diminished greatly over time, while the International Roughness Index (IRI) and Rut Depth (RD) remained relatively stable. The two-layer porous asphalt pavement showed the largest noise reduction over the medium-term. Compared to DTC, the OBSI noise levels of these structures were lower by 2.09 dB, 1.53 dB, and 2.88 dB, respectively. The OBSI was found to be closely correlated with the SFC, IRI, test speed, lane, and pavement type. The RD had a notable effect on the OBSI in PUC-10 pavements. In PUC-10 + PAC-13 pavements, a significant linear relationship was observed between the OBSI and SFC. This is mainly because of the polishing of the coarse aggregates, which leads to micro-texture reduction, high frequency noise increase, and SFC decrease. This study makes a valuable contribution to understanding the laws of porous asphalt pavement performance changes and the relationship between tire/pavement noise and pavement characteristics.

Fast calibration for vibration-based pavement roughness measurement based on model updating of vehicle dynamics

ABSTRACT The vibration-based pavement roughness measurement method has garnered significant attention in recent years due to the development of low-cost sensors. The vehicle calibration process is necessary before field measurement due to the effect of changeable vehicle dynamics, restricting the large-scale implementation of pavement roughness measurement. This paper proposes a novel calibration method for vibration-based pavement roughness measurement. It can quickly calibrate vehicle dynamic parameters through a few controlled impact tests. The model updating technique is employed to estimate vehicle dynamic parameters, resulting in the development of a full-car numerical model that accurately simulates the vibration of the test vehicle. A road-vehicle coupled simulation system is introduced, incorporating randomly generated road profiles and the calibrated full-car model. This system can simulate vibration responses under various conditions. A linear relationship between IRI (International Roughness Index) and vehicle vibration indices (e.g., RMS – Root Mean Square of vertical acceleration) is estimated based on simulated results. The efficiency and accuracy of the calibration method are validated on actual roads in Shanghai, China. The average IRI difference between the ground truth and test data reached 0.5 m/km in a 100 m road section, demonstrating the reliability and practicality of this fast calibration method.

Estimating local pavement performance and remaining service interval using neural networks-based models and automation tool

This study introduces an integrated approach to enhance county pavement management, emphasising operational efficiency in determining the Remaining Service Interval (RSI) for rigid and flexible pavements. It establishes a robust methodology for systematically processing raw county road data through dynamic segmentation and summarisation to create a structured pavement database. It also incorporates innovative approaches and input configurations in employing Artificial Neural Networks (ANNs) to predict current and future county pavement performance indicators, including International Roughness Index (IRI), rutting, transverse, and longitudinal cracks, even with limited data. Evaluation of the ANN models on independent county road databases exhibited high prediction accuracies (0.86 < R 2 < 0.99), varying with specific performance indicators. The study results in an automation tool for expediting road performance estimation over multiple years. This tool seamlessly integrates the ANN models, empowering county engineers to make data-driven decisions and optimise resource allocation for effective pavement management, achieving significant cost savings.

Mechanical properties and fracture surface roughness of thermally damaged granite under dynamic splitting

AbstractIn order to understand the mechanical properties and the fracture surface roughness characteristics of thermally damaged granite under dynamic splitting, dynamic Brazilian splitting tests were conducted on granite samples after thermal treatment at 25, 200, 400, and 600°C. Results show that the dynamic peak splitting strength of thermally damaged granite samples increases with increasing strain rate, showing obvious strain‐rate sensitivity. With increasing temperature, thermally induced cracks in granite transform from intergranular cracks to intragranular cracks, and to a transgranular crack network. Thermally induced damages reduce the dynamic peak splitting strength and the maximum absorbed energy while increasing the peak radial strain. The fracture mode of the thermally damaged granite under dynamic loads is mode II splitting failure. By using the axial roughness index , the distribution ranges of the wedge‐shaped failure zones and the tensile failure zones in the fracture surfaces under dynamic Brazilian splitting can be effectively identified. The radial roughness index is sensitive to the strain rate and temperature. It shows a linear correlation with the peak splitting strength and the maximum absorbed energy and a linear negative correlation with the peak radial strain. can be used to quantitatively estimate the dynamic parameters based on the models proposed.

Carbon emissions quantification and different models comparison throughout the life cycle of asphalt pavements

Establishing a comprehensive and systematic method for quantifying carbon emissions (CEs) of asphalt pavement is challenging due to the multifaceted and diverse nature of the involved processes. Utilizing a life cycle assessment framework, this study introduces a practical model system for capturing CEs across the entire lifespan of asphalt pavement. A pivotal aspect of our approach involves calculating activity levels. Material quantities are ascertained based on mixture proportions and specific pavement information. We employ Ridge Regression and the quota method to approximate the energy consumption of construction machinery. A comparative analysis is performed between two CE computation models that use energy consumption and operational time as activity levels, respectively. Additional vehicle fuel consumption is translated based on shifts in the International Roughness Index, as predicted by the Mechanistic-Empirical Pavement Design Guide. CEs from traffic disruptions are calculated collaboratively through VISSIM simulations and MOVES emission modeling. Our findings reveal that material production, mixture preparation, and maintenance duration are the principal factors contributing to CEs throughout the asphalt pavement lifecycle. Notably, emission estimates for machinery in the construction phase can vary by as much as 8.3 times across different models. The study suggests that incorporating the use of recyclable materials and designing more durable pavement structures can offer effective avenues for CE mitigation.

Machine Learning for Prediction of the International Roughness Index on Flexible Pavements: A Review, Challenges, and Future Directions

Timely maintenance of road pavements is crucial to ensure optimal performance. The accurate prediction of trends in pavement defects enables more efficient allocation of funds, leading to a safer, higher-quality road network. This article systematically reviews machine learning (ML) models for predicting the international roughness index (IRI), specifically focusing on flexible pavements, offering a comprehensive synthesis of the state-of-the-art. The study’s objective was to assess the effectiveness of various ML techniques in predicting IRI for flexible pavements. Among the evaluated ML models, tree ensembles and boosted trees are identified as the most effective, particularly in managing data related to traffic, pavement structure, and climatic conditions, which are essential for training these models. Our analysis reveals that traffic data are present in 89% of the studies, while pavement structure and climatic factors are featured in 78%. However, maintenance and rehabilitation history appears less frequently, included in 33% of the studies. This research underscores the need for high-quality, standardized datasets, and highlights the importance of model interpretability and computational efficiency. Addressing data consistency, model interpretability, and replicability across studies are crucial for leveraging ML’s full potential in fine-tuning IRI predictions. Future research directions include developing more interpretable, computationally efficient, and less complex models to maximize the impact of this research field in road infrastructure management.

Analysis of the correlation between the pavement structure combinations and pavement performance using experimental sections

The new generation of pavement technology with the goal of longevity is an important supporting technology that can promote the achievement of sustainable development of high-speed roadways. To further investigate the evolution trend of long-life pavement performance, this paper paved experimental sections to explore the correlations between pavement structure combinations and pavement performances. This paper presented four experimental sections with different pavement structures, asphalt concrete layer thicknesses, and pavement materials. Then, this paper analyzed the effects of the seasonal factors, pavement structure, and lanes on the deflection value and rut depth from three dimensions by the Pearson correlation coefficient (PCC). Finally, this paper used the analysis of variance (ANOVA) to analyze the relationships between the layer thickness of various materials in the pavement structure and the pavement performances, including the deflection value, international roughness index (IRI), texture depth (TD), British Pendulum Number (BPN), sideway force coefficient (SFC), rut depth, and disease area. The results showed that the seasonal factors significantly affected the deflection values of pavement structures with PCCs of 0.61, 0.72, 0.53, and 0.78. The high temperatures increased the average deflection values by 22.85%, 72.88%, 77.61%, and 88.13%, respectively. Under the influence of high temperature in summer and traffic loads, the increased ranges of average rut depth were −0.2%, 4.89%, 9.56%, and 7.31%, respectively. The results of ANOVA showed that the pavement structure type and thickness of each structural layer significantly affected the deflection value, and there also was a strong correlation between the pavement structure type, thickness, BPN, and SFC with p-values less than 0.05. Increasing the thickness of the asphalt surface was beneficial for reducing the area of defects, while laying the semi-rigid base layer was beneficial for maintaining the deflection value and rut depth at a lower level.

Accident Severity Analysis On the North-South Expressway Using Binomial Logistic Regression

Accidents on Malaysian expressways must be monitored on a regular basis since severe accidents occur on expressways due to higher posted speeds than on other roadways. This study aims to analyse accident severities based on pavement conditions using binomial logistic regression. Data on accident severities and pavement conditions were gathered from the Malaysian Highway Authority (MHA) and the The Royal Malaysian Police (PDRM) respectively. Three binomial logistic regression models were constructed based on four accident severity categories of death, serious injury, minor injury and damage. The accident severity was grouped into different classifications in which Model 1, Model 2 and Model 3 were developed. To assess the model's predictive capabilities, predicted accident severity levels were distinguished with actual accident severity levels. Based on the results, Model 1 and Model 2 except Model 3 have significant pavement conditions and are viable for accident severity predictions whereby both models exhibited high prediction accuracy, has good fit and good in differentiating between two classifications. The model's classifier is better at classifying accident severity classes with more samples than categorizing accident severity classes with fewer data. The odds ratio of both Model 1 and Model 2 revealed that International Roughness Index (IRI) has greater influence in predicting accident severity compared to rut depth (RD) and mean texture depth (MTD) particularly on predicting death. This study suggested that a comparable study be conducted on other road classifications.

Soil denudation in the northwestern Negev (Israel) following the Late Byzantine – Early Islamic period

During the 5th and 6th centuries, the economic hinterland of the city of Gaza encompassed a network of settlements that supplied the city with agricultural produce. Water was collected in underground cisterns from rooftops and courtyards. While almost nothing remained of the above-ground structures since the settlements collapsed, soil erosion exposed these cisterns, which now serve as well-preserved indicators of the location and levels of the houses - that supplied the water. The study examines to what extent the land abandonment in the late Byzantine - early Islamic period resulted in denudation and soil property changes. We hypothesize that the abandonment of settlements and agriculture intensified soil erosion and amplified gully development. Approximately 140 cisterns were mapped in the study area, mainly north of the ephemeral Nahal Gerar stream. The height of the cisterns above the ground was used to calculate the denudation rate (DR) since abandonment. Findings indicate that over relatively flat terrains (1–5 %), cisterns protrude 0.5–1.2 m above the surface. Considering abandonment in the 6th or 11th century, DR was calculated as 0.35–0.85 mm/yr or 0.5–1.2 mm/yr, respectively. Over steeper slopes (10–12 %), along river banks and incised gullies, extensive bank erosion occurred, leading to the exposure of cisterns up to 2.5 m; DR = 1.8 to 2.5 mm/yr, depending on the abandonment time. The settlements' distribution and the surface topography directly correlate: in settled areas, Terrain Roughness Index (TRI) values are higher compared to other areas with the same lithology and rainfall amount. Following abandonment, decaying houses resulted in the complete disintegration of mud bricks, increasing the proportion of fine soil fractions. Cisterns acted as sedimentation basins, trapping surface-derived sediments and debris, including degraded brick material. This process influenced the mechanical composition of soils, affecting soil erosion and land degradation.