In order to solve the problems of rutting and early fatigue cracks in emulsified asphalt cold recycled pavement, and the shortage of natural stone resources and new environmental hazards caused by the use of traditional limestone powder filler. In this study, coal gangue powder was added to prepare Emulsified Asphalt Mastic (EAM) to improve the rheological properties and fatigue performance. A series of tests, including frequency scanning, temperature scanning, Multiple Stress Creep Recovery (MSCR), Linear Amplitude Scanning (LAS), and Fourier Transform Infrared spectroscopy (FTIR) were conducted. Through rheology theory, viscoelastic damage theory, the impact of three fillers: Coal Gangue Powder (CGP), Limestone Powder (LP) and Portland Cement (PC), as well as four kinds of Powder-Binder ratios (P/B) (0.6, 0.9, 1.2, 1.5) on the high temperature rheology and medium temperature fatigue performance of EAM was analyzed. The findings reveal that the filler content has a great influence on the proportion of viscoelastic components of EAM in the low frequency domain. The complex shear modulus (G*) and phase angle (δ) of EAM were suitable for Christensen-Anderson-Marasteanu model (CAM) model in the wide frequency domain. Increasing the filler content and Rotating Thin Film Oven Test (RTFOT) aging can improve the high-temperature stability and stress sensitivity of EAM, but it reduced its fatigue resistance. The high temperature performance of EAM containing PC and CGP exhibit superior high-temperature performance compared to LP fillers. Conversely, LP mastic demonstrate superior anti-fatigue performance under actual strain levels in both thin and thick asphalt pavement layers, surpassing the performance of PC mastic and CGP mastic. Therefore, coal gangue powder can be used as a new type of green filler to replace limestone powder. An appropriate amount of incorporation can improve the high temperature stability of the mortar and does not have a huge impact on the fatigue performance. The most suitable range of P/B is identified as 0.6–1.0 when utilizing LP as the filler, 1.2–1.5 when utilizing PC or CGP as the filler.

With the rapid expansion and aging of global road networks, cold recycled mix asphalt (CRMA) has gained significant attention as a sustainable pavement rehabilitation technology. However, the road performance of CRMA is highly sensitive to material composition and curing conditions, making accurate performance prediction challenging. This study develops machine learning (ML) models to predict two critical performance indicators: dynamic stability (DS) for high-temperature stability and indirect tensile strength (ITS) for low-temperature crack resistance. Four ML algorithms, Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Regression (SVR), were trained on a comprehensive dataset of 436 samples. A genetic algorithm (GA) was employed to optimize model hyperparameters, significantly enhancing prediction accuracy and robustness. The SHAP method was further applied to interpret model outputs and identify key influencing factors. Results demonstrate that GA-optimized XGBoost achieved the highest predictive performance for both dynamic stability (DS) and indirect tensile strength (ITS), with R² values of 0.9793 and 0.9694, respectively. Curing temperature, RAP content, and curing time were identified as the most influential factors. This study provides an accurate and interpretable ML-based framework for CRMA performance prediction, facilitating optimized mix design for pavement construction and maintenance.

This paper proposes a novel Signal‐Vehicle Cooperative Control framework (SVCC‐HPPO) based on the improved Hierarchical Proximal Policy Optimisation (H‐PPO) algorithm to jointly optimise traffic signal timing and Connected and Autonomous Vehicle (CAV) trajectories under mixed vehicular environments with both CAVs and Human‐Driven Vehicles (HDVs). A hierarchical hybrid action space is designed to effectively constrain CAV acceleration and signal timing adjustments while explicitly accounting for car‐following dynamics near intersections, enabling flexible exploration within physical limits. The hybrid actor‐critic architecture facilitates simultaneous optimisation of discrete and continuous actions through parallel actors guided by a global critic, balancing optimization effectiveness with training stability. A multi‐objective reward function simultaneously minimises vehicle delay and fuel consumption and maximises ride comfort. The core improvement involves a layered entropy regularisation strategy within the H‐PPO algorithm, which separately manages discrete and continuous entropy to enhance exploration efficiency and stability across hybrid action dimensions. Real‐world intersections evaluation results demonstrate that SVCC‐HPPO significantly outperforms benchmark methods TRANSYT and DRL‐based algorithms, achieving reductions of up to 46.3% in delay, 59.5% in queue length, and 52.9% in fuel consumption, alongside a 177.4% improvement in average speed. Performance gains are further enhanced with shorter optimisation intervals and higher CAV penetration rates.

Waste battery powder (WBP) can effectively enhance the service performance of virgin asphalt with sol–gel structures; however, its toughening mechanism for sol–gel virgin asphalt still lacks rigorous mechanical characterization. Therefore, the objective of this study is to investigate the toughening of WBP-modified asphalt based on the mechanical parameter of cracking area. First, a 12% content of WBP was incorporated into the sol–gel 70# virgin asphalt to prepare WBP-modified asphalt and its fatigue performance was evaluated through linear amplitude, non-damage, and damage time sweep tests. Then, energy–mechanics balance equations were used to establish a cracking area model. Furthermore, the asphalt cracking area was employed to quantify its induced damage and determine the representative rate for the cracking damage process (k_cd). Finally, the activation energy for cracking damage (E_acd) was used to quantify the difficulty of the cracking damage process. The scanning electron microscope test was employed to examine the microstructure of WBP-modified asphalt and the E_acd and microscopic morphology of WBP-modified asphalt were analyzed to reveal the toughening effect of WBP on virgin asphalt. The results showed that WBP-modified asphalt exhibits three nonlinear cracking stages, with a lower cracking rate than virgin asphalt. Its cracking damage generally increases over time, and the damage evolution parameter β serves as k_cd. The micro-grooves and wrinkles of WBP improve bonding to asphalt, increasing the E_acd of sol–gel 70# virgin asphalt from 10.6 to 23.88 kJ·mol⁻¹, thus achieving toughening. In summary, the fatigue damage process of WBP-modified asphalt can be characterized by the kinetic parameters β and E_acd.

Waste sweet potato vine fiber (WSVF) effectively extends asphalt service life by enhancing cracking resistance in gel-like base asphalt matrices, yet its crack-resistant mechanism lacks mechanical characterization. This study proposes an analytical method for evaluating WSVF-modified asphalt’s crack-resistant behavior based on the principle of mechanical energy balance. First, alkali-treated WSVF with a mass fraction of 1% was added into 70# gel-like base asphalt to prepare WSVF-modified asphalt. Lignin fiber (LF)-modified asphalt and 70# gel-like base asphalt were selected as control groups, and three types of time sweep and scanning electron microscopy tests were conducted. Then, the three-dimensional cracking volume model and damage kinetics model were established for analyzing the cracking response behavior, defining the asphalt damage variable and determining the cracking damage activation energy (E_acd). Finally, the E_acd was used to quantify the difficulty of the cracking damage process for the WSVF-modified asphalt. The reinforcement and cracking resistance mechanisms of WSVF in asphalt were analyzed by the E_acd and asphalt microstructure. The results show that the cracking volume response of WSVF-modified asphalt under cyclic loading presents three-stage nonlinear behaviors. The established fatigue damage kinetics model can accurately describe the fatigue damage evolution process of alkali-treated WSVF-modified asphalt. The E_acd values of WSVF-modified asphalt, LF-modified asphalt, and 70# gel-like base asphalt are 10.60 kJ·mol⁻¹, 21.83 kJ·mol⁻¹, and 29.74 kJ·mol⁻¹, respectively. After alkali treatment, the WSVF surface exhibits grooves, demonstrating superior adsorption and storage capacity for asphalt. The WSVF can cross link through the bonding effect of asphalt and form a three-dimensional network framework structure, which can significantly increase the E_acd and provide strengthening and toughening effects on gel-like base asphalt. In summary, E_acd values are used as a mechanical indicator to quantitatively evaluate the fatigue cracking resistance of WSVF-modified asphalt.