This study systematically compares the predictive performance of single machine learning (ML) models (KNN, Bayesian ridge regression, decision tree) and ensemble learning methods (bagging, boosting, stacking) for quantifying the rheological properties of mineral powder-modified asphalt, specifically the complex shear modulus (G*) and the phase angle (δ). We used two emulsifiers and three mineral powders for fabricating modified emulsified asphalt and conducting rheological property tests, respectively. Dynamic shear rheometer (DSR) test data were preprocessed using the local outlier factor (LOF) algorithm, followed by K-fold cross-validation (K = 5) and Bayesian optimization to tune model hyperparameters. This framework uniquely employs cross-validated predictions from base models as input features for the meta-learner, reducing information leakage and enhancing generalization. Traditional single ML models struggle to characterize accurately as a result, and an innovative stacking model was developed, integrating predictions from four heterogeneous base learners—KNN, decision tree (DT), random forest (RF), and XGBoost—with a Bayesian ridge regression meta-learner. Results demonstrate that ensemble models outperform single models significantly, with the stacking model achieving the highest accuracy (R² = 0.9727 for G* and R² = 0.9990 for δ). Shapley additive explanations (SHAP) analysis reveals temperature and mineral powder type as key factors, addressing the “black box” limitation of ML in materials science. This study validates the stacking model as a robust framework for optimizing asphalt mixture design, offering insights into material selection and pavement performance improvement.

Rubber powder asphalt has been widely studied due to its favorable temperature sensitivity and fatigue resistance. However, because rubber powder does not easily swell in asphalt, it leads to poor storage stability and high viscosity, limiting its large-scale application. In this study, modified asphalt was prepared using desulfurized rubber powder (DRP) and styrene-butadiene-styrene (SBS) modifiers, aiming to identify the optimal formulation for enhanced performance. It was hypothesized that the combined use of DRP and SBS would produce synergistic effects, improving the overall mechanical and rheological properties of the asphalt. To test this, the effects of this composite modification were evaluated using Marshall tests (penetration, softening point, ductility, elastic recovery, and Brookfield viscosity) and Superpave tests (shear modulus, high-performance grade, rutting factor, fatigue factor, and creep and recovery). Additionally, moisture susceptibility, high-temperature stability, low-temperature cracking resistance, and fatigue resistance at the mixture level were assessed. Performance was evaluated according to the Chinese standard JT/T 798-2019 for rubberized asphalt using reclaimed tire rubber. Results show that DRP-modified asphalt demonstrates excellent temperature sensitivity, rutting resistance, deformation resistance, and fatigue performance. However, an excessive amount of DRP increases Brookfield viscosity, which negatively affects the workability of the asphalt binder. The addition of SBS further improves the softening point, ductility, and deformation recovery of the binder. Considering cost-effectiveness and overall performance, the optimal formulation was determined to be 25% DRP and 1% SBS. At this dosage, all performance indicators met the required standards. The rotational viscosity at 180 °C was approximately 35% lower than that of conventional rubber powder–modified asphalt, while the high-temperature rutting factor and fatigue resistance at medium-to-low temperatures outperformed those of SBS-modified asphalt. The mixture test results reveal that the gradation has an impact on the performance of the obtained mixture, but overall, the DRP-SBS composite-modified asphalt mixture has significant advantages in terms of performance and cost-effectiveness.

To facilitate the high-value utilization of reclaimed asphalt pavement (RAP), this study investigated the efficacy of fine separation technology as a pre-treatment method. This technology significantly reduced the variability of RAP, controlling the coefficients of variation for asphalt content and aggregate gradation within 5% and 10%, respectively, and minimized false particle content (agglomerates of fines and aged asphalt). Response Surface Methodology (RSM) was employed to optimize the mix design for ultra-high-RAP- content mixtures (50–70%). A predictive regression model was developed to determine the Optimal Binder Content (OBC) based on RAP and rejuvenator dosage. The road performance of the resulting mixtures was comprehensively evaluated. Results showed that the technology markedly enhanced the overall performance of recycled asphalt mixtures. While high-temperature rutting resistance improved with increasing RAP content, low-temperature performance declined. The mixture with 70% RAP failed to meet low-temperature cracking requirements. Consequently, an optimal RAP content of 60% is recommended. Furthermore, the generalized sigmoidal model effectively constructed dynamic modulus master curves, accurately predicting the viscoelastic behavior of these ultra-high-RAP mixtures. This study demonstrates that fine separation is a critical pre-processing step for reliably producing high-quality, sustainable asphalt mixtures with RAP content far exceeding conventional limits.

The utilization of oil-rich reclaimed asphalt pavement fine aggregate (O-RAP), characterized by its high asphalt content, which has inherent compatibility with the high asphalt demand of stress-absorbing layer (SAL) mixtures, enables significant recycling rates, thereby promoting resource efficiency and a promising pathway for sustainable infrastructure development. This study provides a comprehensive evaluation of the rheological properties of recycled asphalt binder through dynamic shear rheometer and bending beam rheometer tests. Furthermore, the pavement performance of SAL mixtures was systematically assessed via fatigue testing, moisture susceptibility evaluation, rutting resistance analysis, and overlay testing. The results indicate that increasing the O-RAP content enhances the complex shear modulus while reducing the phase angle, suggesting improved stiffness but reduced flexibility of the binder. In SAL mixtures, higher O-RAP content was associated with decreased fatigue life, moisture stability, and low-temperature cracking resistance, yet it contributed to improved resistance to reflective cracking and high-temperature rutting. Pearson correlation analysis further revealed that the fatigue life of the binder exhibits a strong positive correlation with creep rate and significant negative correlations with creep stiffness modulus, high-temperature stability, and reflective cracking resistance. These findings underscore the viability of high-content O-RAP incorporation in SAL mixtures as a technically sound and environmentally sustainable strategy for low-carbon pavement construction, offering significant reductions in virgin material consumption and associated carbon emissions.

To evaluate the feasibility of a virtual overlay tester (OT), a modeling approach was proposed based on the discrete element method (DEM). Simulations were conducted on three types of asphalt mixtures across three different thickness conditions. Through the analysis of the load/displacement curves, crack propagation paths, force chains, and contact force characteristics, it was observed that the peak loads decrease with increasing thicknesses, indicating a notable size effect. The complexity of the crack path was positively correlated with the particle size along the path and the fractal dimension. Coarse aggregates can inhibit crack propagation to some extent. Prior to reaching the peak load, compressive force chains in asphalt concrete-13 (AC13) and large stone porous asphalt mixture-30 (LSPM30) exhibited a symmetrical and divergent distribution along the crack, while tensile force chains formed an arch-like pattern. After the peak load, compressive force chains were symmetrically distributed in an arch shape along the crack. In stone mastic asphalt-13 (SMA13), compressive forces were transmitted along coarse aggregates, forming several continuous vertical paths. The proportion of strong compressive force chains to total compressive force chains across the three gradations ranged from 0.74 to 0.83, while the corresponding proportion for tensile force chains ranged from 0.72 to 0.78.

The purpose of this study is to solve the problem of the harmless treatment of dredged silt and soil extraction during road construction in lake areas. The silt in the project area is used as the research material to evaluate its engineering applicability as an improved filling material for the roadbed of the lake’s surrounding road. Through indoor pretreatment and a series of mechanical performance tests, including compaction tests, unconfined compressive strength tests (UCS), bearing ratio tests (CBR), triaxial compression tests (CU consolidated undrained), and consolidation tests, we obtained key mechanical parameters of modified sludge soil, such as maximum dry density, optimal moisture content, unconfined compressive strength, bearing ratio, shear strength, and compression characteristics. The research results show that with the increase in modifier dosage, the optimal moisture content of modified sludge soil increases, the maximum dry density decreases, and its compressive strength and shear strength significantly improve. The CBR value also meets the technical requirements of each layer of the roadbed. Specifically, after 7 days of curing, the compaction degree of 10% modified sludge soil can exceed 96%, the unconfined compressive strength reaches 0.819 MPa, the CBR value reaches 17.5, the cohesion measured by triaxial tests is 78 kPa, the internal friction angle is 27°, and it exhibits low compressibility. These findings provide new solutions for environmentally friendly treatment, resource utilization, and road engineering in river and lake sediments.