Long-Term Pavement Performance Research Articles

Research on Multi-Parameter Error Model of Backcalculated Modulus Using Abaqus Finite Element Batch Modeling Based on Python Language

The error in modulus backcalculation is a crucial component in validating the rationality and reliability of results for engineering applications. The objective of this study is to identify the theoretical limitations associated with backcalculated modulus errors under typical parameter uncertainties and to determine the primary factors contributing to these errors. Firstly, using the actual measurements or data from the Long-Term Pavement Performance (LTPP) project, the statistical distributions of errors for typical parameters in the modulus backcalculation model were determined. Subsequently, a factor level table for orthogonal experimental design was developed, leading to the construction of 81 orthogonal design experimental schemes and their corresponding theoretical pavement structure models based on the actual error distributions. The deflection responses of 81 theoretical pavement structure models were then computed using an ABAQUS finite element batch analysis method devised in Python. Furthermore, a multi-parameter error model for modulus was established using multiple linear regression and variance analysis. Finally, the theoretical limitations of modulus errors under actual errors were analyzed. The results show that the errors of thickness, load amplitude and load frequency follow a normal distribution, while the distribution of backcalculated modulus errors follows an approximate mixed Gaussian distribution. When the errors of multiple parameters are combined randomly, the modulus errors range from −100% to 595%, and the probability of the modulus errors being less than 15% is highest in the asphalt surface layer, followed by the subgrade, and then the base and subbase layers. Within the same error range, the modulus error is random. However, with different error ranges, the overall level of modulus error increases in proportion to the size of those ranges. Compared to factors such as thickness, load amplitude, and load frequency, the errors in deflections have a highly contribution rate on the modulus errors exceeding 99%.

Subgrade performance assessment for rigid runway using long-term pavement performance database

Maintaining desired subgrade performance is an effective way to reduce runway pavement deterioration. Due to lack of extensive field test data, life-cycle performance of runway subgrade has not been fully understood. In order to quantitatively estimate subgrade condition, a novel method of evaluating subgrade performance was developed and validated using the 726 sets of Heavy Weight Deflectometer (HWD) test data of ten runway sections. Statistical analysis demonstrates that the structural behaviour of rigid runway subgrade follows normal distribution in different service stages and can be efficiently evaluated by the subgrade performance index (ψ). The results of factor analysis show that Accumulated Air Traffic Volume (ATV) during service life is the major cause of spatial variations in subgrade condition. In the designed service period of runway, it validates that sea-reclaimed subgrade results in faster degradation in the initial stage of service life while thicker pavement exhibits better capability in protecting the subgrade soil in long-term view. Besides, the differences in applied loads and pavement thickness give rise to the subgrade performance variation in longitudinal direction. Meanwhile, the comparison between the main and the less trafficked test lines in transversal direction reveals that the aircraft impacts play a positive role in resisting the natural fatigue process. By the suggested method, subgrade performance of HWD test points can be categorized into 4 levels from “Excellent”, “Good”, “Fair” to “Poor” based on ψ value. It is helpful for airport agency to make scientific decisions on Maintenance and Rehabilitation (M&R) treatment by calculating the effective area of envelope (β) using the ratio of subgrade performance (η).

Long-term performance of porous asphalt pavement incorporating recycled plastics

Recycling plastic in asphalt pavement holds potential for environmental and economic benefits. However, its performance after prolonged exposure to heat, oxygen, sunlight, and moisture remains uncertain, casting doubt on its viability. In this study, various types of recycled plastics were incorporated into porous asphalt mixtures and exposed to long-term aging conditions. A total of 360 specimens were tested to evaluate several key properties: moisture susceptibility and rutting resistance; abrasion resistance; and indirect tensile strength and fatigue resistance. The results indicate that porous mixtures with 5 % plastic generally exhibit superior long-term performance compared to non-plastic porous mixtures, except for cracking resistance. Excessive addition of plastic (15 %) in asphalt pavement can lead to significant degradation of long-term performance. A trial section incorporating plastic in porous asphalt pavement exhibited satisfactory performance after a year of construction. These insights are pivotal in shaping policy and directing resources toward sustainable road construction practices.

Machine learning-based models for thermal cracking prediction of flexible pavements

Prediction of transverse cracking is crucial for pavement practitioners and decision-makers to prognosticate the cracking development and allocate maintenance budgets. This research investigates thermal crack predictions, using four various machine learning techniques: the support vector regression (SVR), the regression artificial neural network (RNN), the Gaussian process regression (GPR) and the least-square boost ensemble method (LSBoost). Predictions were based on 214 pavement sections with 1262 data points from the Long-Term Pavement Performance (LTPP) database. The models are developed using 20 variables representing age, binder, mix, aggregate and climate properties. The LSBoost ML algorithm exhibited the best performance, with a coefficient of determination (R2) of 0.926 for training and 0.727 for testing. Sensitivity analysis revealed that pavement age is the predominant factor in transverse crack prediction followed by the freezing index (FI). Overall, climatic parameters played an important role in transverse crack predictions compared to the mix and binder properties.

A Comparative Study of Pavement Roughness Prediction Models under Different Climatic Conditions

Predicting the International Roughness Index (IRI) is crucial for maintaining road quality and ensuring the safety and comfort of road users. Accurate IRI predictions help in the timely identification of road sections that require maintenance, thus preventing further deterioration and reducing overall maintenance costs. This study aims to develop robust predictive models for the IRI using advanced machine learning techniques across different climatic conditions. Data were sourced from the Ministry of Energy and Infrastructure in the UAE for localized conditions coupled with the Long-Term Pavement Performance (LTPP) database for comparison and validation purposes. This study evaluates several machine learning models, including regression trees, support vector machines (SVMs), ensemble trees, Gaussian process regression (GPR), artificial neural networks (ANNs), and kernel-based methods. Among the models tested, GPR, particularly with rational quadratic specifications, consistently demonstrated superior performance with the lowest Root Mean Square Error (RMSE) and highest R-squared values across all datasets. Sensitivity analysis identified age, total pavement thickness, precipitation, temperature, and Annual Average Daily Truck Traffic (AADTT) as key factors influencing the IRI. The results indicate that pavement age and higher traffic loads significantly increase roughness, while thicker pavements contribute to smoother surfaces. Climatic factors such as temperature and precipitation showed varying impacts depending on the regional conditions. The developed models provide a powerful tool for predicting pavement roughness, enabling more accurate maintenance planning and resource allocation. The findings highlight the necessity of tailoring pavement management practices to specific environmental and traffic conditions to enhance road quality and longevity. This research offers a comprehensive framework for understanding and predicting pavement performance, with implications for infrastructure management both locally and worldwide.

Microwave self-healing characteristics of the internal voids in steel slag asphalt mixture subjected to salt-freeze-thaw cycles

Microwave heating technology can be used to repair freeze-thaw (F-T) cycle damage and cracks caused by the use of snow melting salts and de-icers in winter. This study utilized three different gradations of asphalt mixtures: AC-13, SMA-13, and OGFC-13, and enhanced their microwave absorption performance with steel slag (SS). The heating uniformity was evaluated through surface and internal temperature tests. Additionally, the mechanisms of damage and healing of the asphalt mixtures under salt freeze-thaw (S-F-T) damage conditions were explored using S-F-T cycles test and X-ray computed tomography scans (CT). The results showed that OGFC-13 exhibits a significantly higher rate of temperature increase compared to the other two types due to its stronger wave absorption capacity. The thermal hysteresis caused by steel slag leads to uneven spatial temperature distribution. The study recommends an optimal microwave heating time of 40 s for SS asphalt mixtures, which has minimal impact on the mixture structure, by defining an evaluation method for the uniformity index and local overheat ratio. After undergoing S-F-T cycles, the porosity of all three asphalt mixtures increased, particularly at the top and bottom of the specimens. Among them, OGFC-13 exhibited the poorest durability under S-F-T conditions, with the S-F-T cycles having a significant impact on medium-sized voids (0.15–0.6 mm). After microwave heating, AC-13 and SMA-13 showed good repair effects, with porosity levels returning to their initial states. For large voids (>2.36 mm) in OGFC, microwave heating may not effectively reduce the number of voids. Additionally, the healing rate of mixture specimens at certain mid-height ranges is higher due to elevated surface temperatures in these areas, making it especially effective in repairing F-T damage. This study shows that microwave heating of SS asphalt mixtures can improve the durability of pavement in cold regions. However, implementation challenges include the need for specialized equipment and potential uneven heating. Future research should explore optimizing microwave heating techniques to minimize local overheating and investigate the long-term performance of microwave-repaired asphalt pavements under various environmental conditions.

Buckling prediction based on joint opening and safe temperature estimation in jointed plain concrete pavements

Concrete pavement buckling is a significant distress that disrupts traffic flow and results in costly repairs, issues that are increasingly exacerbated by global warming. Addressing these issues, this study develops a systematic framework for assessing jointed plain concrete pavement (JPCP) by integrating temperature and moisture gradients, pavement structures, and material properties into mechanical-based models for predicting buckling potential. Specifically, a two-stage analysis is developed to analyze buckling development based on the slab deformation and the slab-base interface, including joint closure assessment and upheaval buckling prediction. Through the established model, parametric studies are conducted to quantitatively identify key factors influencing buckling. Moreover, the developed models are applied to pavement sections in various climate regions and validated through comparative analysis with field data from the Long-Term Pavement Performance (LTPP) database to confirm model accuracy. Additionally, a case study using pavement buckling data from Wisconsin between 2014 and 2020 demonstrates the model's practical application. As the results, it is found that temperature increase, the percentage of incompressible materials, and the coefficient of thermal expansion are critical for joint opening changes, while the coefficient of thermal expansion, elastic modulus, and slab thickness are crucial to post-buckling performance. Regression equations are provided to estimate safe temperature increases as a recommended buckling temperature limit. Furthermore, the predicted joint opening shows reasonable alignment with joint gauge measurement in the field recordings from the LTPP database. Finally, the predicted buckling events are reasonably compared with field recordings for a Wisconsin pavement section from 2014 to 2020. In summary, by considering pavement structural parameters, material properties, and weather conditions, this comprehensive model provides a reasonable tool for predicting and mitigating JPCP buckling in different climate conditions.

Development of superpave asphalt binder specifications to meet climate conditions in the UAE

ABSTRACT Asphalt binder's performance is highly sensitive to temperature fluctuations and climatic conditions. The selection of an inappropriate asphalt binder leads to considerable damage and impacts roads' longevity. The current selection practice of asphalt binder in the United Arab Emirates (UAE) is mainly according to the penetration grading system, which does not consider local temperature conditions. The Superpave Performance Grade (PG) system considers extreme pavement temperatures to define appropriate asphalt binder PG. This study aimed at developing the Superpave asphalt binder PG map for the UAE. The Strategic Highway Research Program (SHRP) and Long-Term Pavement Performance Program (LTPP) Superpave models were used to calculate the pavement temperatures employing air temperature records collected from 20 weather stations across the UAE. The result of the Superpave PG map highlights three distinct asphalt binder grades at 98% reliability: PG 76-10, PG 70-10, and PG 64-10. The PG 76 -10 asphalt binder is the most prevalent PG, covering more than 85% of the UAE map. However, the current construction practice utilizes penetration grades 40/50 and 60/70, through both asphalt binders are equivalent to PG 64-xx. This necessitates the use of different modifier technologies to achieve the Superpave requirements of PG 76-10 and PG 70-10.

Imporved model for pavement performance prediction based on recurrent neural network using LTPP database

Accurate pavement performance prediction plays a critical role in formulating maintenance and repair strategies for transportation departments, enabling the achievement of better pavement performance with limited financial resources. However, due to the intricate influence of numerous factors on pavement performance deterioration, improving the accuracy of pavement performance prediction poses a challenge for conventional models. Therefore, the aim of this study is to establish a machine learning-based model pavement performance prediction model. First, this study considers five factors that affect pavement performance, including pavement initial performance indicators, traffic loads, weather, pavement structure, and maintenance measures, and identifies 15 specific indicators that affect pavement performance based on these five factors. Then, based on the Long-Term Pavement Performance (LTPP) database, the study screens and summarizes these indicators, obtaining 2464 high-quality pavement performance data for Pavement Conditions Index (PCI) prediction and 3238 high-quality pavement performance data for IRI prediction. Finally, three distinct prediction models are established, namely, the Fully Connected Neural Network (FCNN) model, the Long Short-Term Memory (LSTM) model, and the combined LSTM-Attention model. The study shows that the LSTM-Attention model performs significantly better than the FCNN and LSTM models, with an R2 coefficient of determination of 0.81 for PCI and 0.79 for IRI. The innovation of this paper is that the authors have introduced the Attention mechanism on the basic of LSTM model, which makes the fitting accuracy of the prediction model further improved.

Multi-Step Relaxation Characterization and Viscoelastic Modeling to Predict the Long-Term Behavior of Bitumen-Free Road Pavements Based on Polymeric Resin and Thixotropic Filler.

Asphalt pavements are fundamental to modern transportation infrastructure, requiring elasticity, firmness, and longevity. However, traditional asphalt, based on bitumen, faces several limitations. To improve pavement performance, polymer resins are being used to substitute bitumen and improve requirements. Therefore, a deep understanding of the material behavior is required. This study presents the analysis of the relaxation behavior of a poly(methyl methacrylate)-based pavement and the influence of mineral fillers. An approach using a linear elastic-viscoelastic material model was selected based on evidence and validated across the linear and nonlinear deformation range. The results reveal no influence of the mineral fillers on the relaxation behavior. The presented modification of the linear elastic and viscoelastic modeling reveals accurate results to predict long-term pavement performance. This approach offers a practical method for forecasting asphalt behavior. Further research is needed to incorporate deformation behavior into the model.

Global Warming and Its Effect on Binder Performance Grading in the USA: Highlighting Sustainability Challenges

The mounting impacts of climate change on infrastructure demand proactive adaptation strategies to ensure long-term resilience. This study investigates the effects of predicted future global warming on asphalt binder performance grade (PG) selection in the United States using a time series method. Leveraging Long-Term Pavement Performance (LTPP) data and Superpave protocol model, the research forecasts temperature changes for the period up to 2060 and calculates the corresponding PG values for different states. The results reveal significant temperature increases across the majority of states, necessitating adjustments in PG selection to accommodate changing climate conditions. The findings indicate significant increases in average 7-day maximum temperatures across the United States by 2060, with 38 out of 50 states likely to experience rising trends. Oregon, Utah, and Idaho are anticipated to face the largest temperature increases. Concurrently, the low air temperature has risen in 33 states, with notable increases in Maine, North Carolina, and Virginia. The widening gap predicted between required high and low PG poses challenges, as some necessary binders cannot be produced or substituted with other grades. The study highlights the challenge of meeting future PG requirements with available binders, emphasizing the need to consider energy consumption and CO2 emissions when using modifiers to achieve the desired PG properties.

A probabilistic investigation of long-term field performance of warm mix asphalt pavements

Warm-mix asphalt (WMA) has been gaining popularity in sustainable road engineering due to its reduced environmental impacts. However, uncertainties remain regarding its long-term pavement performance compared to hot mix asphalt (HMA). Especially, the critical factors influencing the field performance of WMA are yet to be determined. Hence, this study analyzes the long-term field performance of pavement overlaid with WMA, using data from the Specific Pavement Studies 10 (SPS-10) of the long-term pavement performance (LTPP) program. The evaluation includes 58 field sections from nine projects across the United States, encompassing two WMA types (foaming processing and chemical additive) and their corresponding HMA control sections. Performance indicators such as alligator cracking, longitudinal cracking in the wheel path, transverse cracking, rutting, and roughness (measured by the international roughness index, IRI) were considered. Per-state and per-climate region Bayesian multilevel models were built to account for site- and region-level heterogeneity. The study results demonstrated that pavement with WMA performed equally well to the HMA counterparts under similar conditions, indicating that their potential for widespread application in meeting both performance standards and environmental conservation requirements. Also, WMA technologies did not differ in pavement performance, and thus the field performance of WMA was not a dominant factor in deciding WMA technology types. Furthermore, Bayesian multilevel models proved highly effective in performance data varying across construction sites and regions.

Performance of optimized composition of epoxy resin adhesive used in High Friction Surface Treatment

The High Friction Surface Treatment (HFST) paving technique is widely employed in engineering practices globally, serving to enhance the long-term anti-skid performance of pavements. However, there still exist significant gaps in research regarding the modified and optimized composition and corresponding content of the polymer binding materials used in HFST, as well as the performance of the pavements laid with modified and optimized blended aggregates during service. To address these issues, this research first modified and optimized the composition ratio of traditional epoxy resin materials. Subsequently, a toughened, high-flow epoxy bonding system suitable for the maintenance of concrete pavements was prepared. Additionally, the study explored the bonding performance of this system with both the cement base surface and aggregates. The results established that the optimal ratio range for the modified epoxy adhesive system is E51 epoxy resin to curing agent to toughening agent to diluent in the proportions of 100: 30–35: 20–30: 5. The experimental group used a high-flow epoxy resin adhesive ratio of E51 epoxy resin: curing agent: toughener: diluent = 100:30:20:5. For control group 1, the ratio of epoxy resin adhesive was E51 epoxy resin: curing agent = 100:30, and for control group 2, the ratio was E44 epoxy resin: curing agent = 1:1. Compared with control groups 1 and 2, the modified epoxy system with the cement base demonstrated a 149 % increase in average pull-off strength and an 18 % increase in average shear strength. Similarly, in comparison with control groups 1 and 2, the modified epoxy system with aggregates exhibited a 174 % increase in average pull-off strength and a 541 % increase in average shear strength. Based on the pull-off and shear test results, it was ultimately determined that the dosage of modified epoxy binder for HFST mixtures should be controlled at 1.0–1.2 kg/m2, and the dosage of aggregate should be controlled at 3.3–4.3 kg/m2. These findings provide valuable insights into optimizing HFST pavement compositions for improved performance and longevity.

Comparative study of moisture and stress dependent unbound material modulus for flexile pavement response modeling

Moisture can significantly impact the resilient modulus of pavement base and subgrade. Although various resilient modulus models exist, their accuracy in predicting pavement responses have not been examined and verified. This study aims to compare the accuracy of pavement response modeling using different resilient modulus, considering moisture and stress dependent unbound material modulus. Comprehensive pavement information including pavement structure, viscoelastic property of asphalt concrete, unbound material properties, moisture gradient, water table, temperature gradient and FWD deflections were collected from Long-Term Pavement Performance (LTPP) program. Based on collected data, finite element models were developed to predict pavement deflections under FWD load and pavement responses under traffic loading, respectively. The results show that the moisture-suction-stress dependent (MSS) model has the best prediction accuracy as compared to field measurements, followed by the Witczak model, while the generalized constitutive model displayed the largest deviation. Under traffic loading, the critical pavement responses predicted from Witczak and generalized constitutive model can have a significant deviation from those predicted from MSS model. The generalized constitutive model was found to constantly overestimate the responses, and the deviation of Witczak model depends on other factors such as pavement structure. Using results from MSS as the baseline, these deviations were found to result in up to 50% errors in service life of selected pavements in this study. These findings highlight the importance of taking matric suction into account for accurate modeling of flexible pavement responses.

Bayesian dynamic modelling for probabilistic prediction of pavement condition

Significant funds have been allocated to maintain road networks each year in developed countries. Performance prediction is crucial for pavement management systems to adjust working plans and budget allocation. As a Bayesian nonparametric method, Gaussian process regression (GPR) is powerful in predicting nonlinear time series and quantifying uncertainty. However, it remains computationally intensive and fails to adapt to the time-varying characteristics. To address such issues, a dynamic GPR model is proposed for probabilistic prediction of the International Roughness Index (IRI) for flexible pavements. A moving window strategy is developed to substantially shrink the size of training data, which effectively alleviates computational cost and thus leads to a dynamic GPR. A genetic algorithm is then adopted to determine the optimal window size by considering the trade-off between computational efficiency and accuracy. A dataset acquired from Long-Term Pavement Performance (LTPP) is used to demonstrate the feasibility of the dynamic GPR. Its performance is compared to traditional GPR as well as dynamic and static Bayesian linear regression (BLR) models. The comparison results indicate that the proposed dynamic GPR can increase the accuracy by 0.86, 1.52, and 2.27 times for dynamic BLR, static GPR, and static BLR, respectively. It exhibits the best results in terms of accuracy and uncertainty metrics due to its nonlinear modelling and time-varying ability.

Performance prediction for network-level flexible pavements using an optimised ANN approach

ABSTRACT Considering that the road network shares traffic flow as a system, this study aimed to predict the network-level flexible pavement performance, using an optimised artificial neural network (ANN) approach to predict the pavement performance of each individual road, and the Ford-Fulkerson algorithm to determine the weight coefficients of roads. ANNs were developed to predict distress conditions, functional conditions and structural performance using the inputs of the pavement age and structural, traffic and climatic conditions. ANNs were trained with Long-Term Pavement Performance (LTPP) program data, and almost all the coefficient of determination values between ANN outputs and measured results are larger than 0.9. This ANN approach was optimised by establishing grey models to provide predictive short-term performance data for training ANNs, and employing Kalman Filter to modify the long-term performance prediction. Applications in typical LTPP sections validated the effectiveness of the optimisation method. This study used the reduction in road network capacity due to the assumed unavailability of a certain road to quantify its role (weight coefficient), which was calculated using the Ford-Fulkerson algorithm. This network-level performance prediction approach was applied in a 25-expressways network in Shanghai, which validated the good generalisation capabilities of ANNs and feasibility of the Ford-Fulkerson algorithm.

Development of a Machine Learning (ML)-Based Computational Model to Estimate the Engineering Properties of Portland Cement Concrete (PCC)

Portland cement concrete (PCC) is the construction material most used worldwide. Hence, its proper characterization is fundamental for the daily-basis engineering practice. Nonetheless, the experimental measurements of the PCC’s engineering properties (i.e., Poisson’s Ratio -v-, Elastic Modulus -E-, Compressive Strength -ComS-, and Tensile Strength -TenS-) consume considerable amounts of time and financial resources. Therefore, the development of high-precision indirect methods is fundamental. Accordingly, this research proposes a computational model based on deep neural networks (DNNs) to simultaneously predict the v, E, ComS, and TenS. For this purpose, the Long-Term Pavement Performance database was employed as the data source. In this regard, the mix design parameters of the PCC are adopted as input variables. The performance of the DNN model was evaluated with 1:1 lines, goodness-of-fit parameters, Shapley additive explanations assessments, and running time analysis. The results demonstrated that the proposed DNN model exhibited an exactitude higher than 99.8%, with forecasting errors close to zero (0). Consequently, the machine learning-based computational model designed in this investigation is a helpful tool for estimating the PCC’s engineering properties when laboratory tests are not attainable. Thus, the main novelty of this study is creating a robust model to determine the v, E, ComS, and TenS by solely considering the mix design parameters. Likewise, the central contribution to the state-of-the-art achieved by the present research effort is the public launch of the developed computational tool through an open-access GitHub repository, which can be utilized by engineers, designers, agencies, and other stakeholders.

Integrating Tensometer Measurements, Elastic Half-Space Modeling, and Long-Term Pavement Performance Data into a Mechanistic–Empirical Pavement Performance Model

Pavement performance models (PPMs) are utilized to predict pavement network conditions which is an essential part of any sustainable pavement management system (PMS). The reliability of a PMS and its outputs is proportional to the reliability of the PPM used. This article describes a mechanistic–empirical pavement performance model based on pavement response parameters—strains calculated in the pavement layers measured by tensometers embedded in the pavement surface and verified by calculations in the elastic half-space model and supplemented by empirical data from long-term pavement performance monitoring and accelerated pavement testing. Hence, the herein described PPM combines pavement serviceability evaluation, pavement bearing capacity, and the physico-mechanistic properties of paving materials. The analytical methods which were used to ascertain the physico-mechanistic characteristics, the material fatigue degradation model, and the surface degradation, unevenness in particular, are described. A comparison of the empirical PPM created in the last century used by the national road administrator to this day and the newly created PPM is presented. The comparison shows the difference in the calculated socio-economic benefits and subsequent cost–benefit analysis results. The comparison shows that the use of the old PPM may have produced false economic evaluation results that have led to poor decision making, partially explaining the unsustainable trend of road network management in our country.

Preventive Maintenance Decision-Making Optimization Method for Airport Runway Composite Pavements

Long-term preventive maintenance planning using finite annual budgets is vital for maintaining the service performance of airport runway composite pavements. Using the pavement condition index (PCI) to quantify composite pavement performance, this study investigated the PCI deterioration tendencies of middle runways, terminal runways, and taxiways and developed prediction models related to structural thickness and air traffic. Performance jump (PJ) and deterioration rate reduction (DRR) were used to measure maintenance benefits. Based on 112 composite pavement sections in the Long-term Pavement Performance Program, this study analyzed the influences of five typical preventive maintenance technologies on PJ, DRR, and PCI deterioration rates. The logarithmic regression relationship between PJ and PCI was obtained. For sections treated with crack sealing and crack filling, the DRR was nearly 0. For sections treated with fog seal, thin HMA overlay, and hot-mix recycled AC, the DRR was 0.2, 0.7, and 0.8, respectively. To solve the multi-objective maintenance problem, this study proposed a decision-making optimization method based on dynamic programming, and the solution algorithm was optimized, which was applied in a five-year maintenance plan. Considering different PCI deterioration tendencies of airport regions, as well as PJ, DRR, and costs of maintenance technologies, the preventive maintenance decision-making optimization method meets performance and financial requirements sufficiently.

Ensemble Learning Approach for Developing Performance Models of Flexible Pavement

This research utilizes the Long-Term Pavement Performance database, focusing on devel-oping a predictive model for flexible pavement performance in the Southern United States. Analyzing 367 pavement sections, this study investigates crucial factors influencing asphaltic concrete (AC) pavement deterioration, such as structural and material components, air voids, compaction density, temperature at laydown, traffic load, precipitation, and freeze–thaw cycles. The objective of this study is to develop a predictive machine learning model for AC pavement wheel path cracking (WpCrAr) and the age at which cracking initiates (WpCrAr) as performance indicators. This study thoroughly investigated three ensemble machine learning models, including random forest, extremely randomized trees (ETR), and extreme gradient boosting (XGBoost). It was observed that XGBoost, optimized using Bayesian methods, emerged as the most effective among the evaluated models, demonstrating good predictive accuracy, with an R2 of 0.79 for WpCrAr and 0.92 for AgeCrack and mean absolute errors of 1.07 and 0.74, respectively. The most important features influencing crack initiation and progression were identified, including equivalent single axle load (ESAL), pavement age, number of layers, precipitation, and freeze–thaw cycles. This paper also showed the impact of pavement material combinations for base and subgrade layers on the delay of crack initiation.