Dynamic modulus is a key stiffness parameter in the mechanistic–empirical design of asphalt pavements. Traditional laboratory tests are time-consuming and costly, while conventional empirical models fail to characterize the nonlinear viscoelasticity introduced by fibers, and existing machine learning methods suffer from premature hyperparameter convergence and limited interpretability. To address these issues, this study employs an improved black-winged kite algorithm (IBKA) to optimize eXtreme Gradient Boosting (XGBoost) for establishing a dynamic modulus prediction model. Gaussian chaotic mapping, guided pool strategy, and adaptive step size are introduced to enhance global hyperparameter optimization capability. A dataset of 288 samples involving temperature, frequency, strain, and fiber categories is compiled from multi-condition tests. Nested cross-validation and an independent test set are adopted for internal optimization and generalization assessment, with permutation testing (1000 Monte Carlo, p < 0.001) confirming the statistical reliability of the model. The results demonstrate that IBKA–XGBoost delivers excellent accuracy and robustness, achieving an RMSE of 355.1248 MPa and an R2 of 0.9966 in NCV and 373.5450 MPa and 0.9955 on the independent test set. It outperforms BKA–XGBoost, four metaheuristic algorithms, and three conventional tuning strategies across nine evaluation metrics; compared with BKA–XGBoost, RMSE decreases by 23.9% and prediction uncertainty U95 narrows by 23.7%. SHAP and PDP analyses identify temperature as the dominant factor, reveal fiber-type differentiation governed by modulus matching and interfacial compatibility, and confirm asymmetric temperature–frequency interactions consistent with the time–temperature superposition principle. The proposed framework facilitates fiber screening and the intelligent refined design of pavement materials.
To investigate the long-term water stability of graphene-modified permeable asphalt mixtures, in this study, we analysed the effects of single factors and multi-factor coupling. The single-factor water stability was investigated through the free thawing splitting test, standard Cantabro test, and immersion Cantabro test; the experimental indicators were the freeze–thaw cracking ratio (TSR), mass loss rate, and immersion mass loss rate, respectively. The multi-factor water stability was studied through immersion operation tests of mixtures with different degrees of ageing. The dispersion of graphene was examined through Raman mapping, the formation of three-dimensional network structures of graphene and SBS was evaluated via the dynamic shear rheometer test (DSR), and the elemental distribution was quantitatively analysed using energy-dispersive spectroscopy (EDS) and an image pixel algorithm (RGB). The results indicate that an unaged graphene-composite- and SBS-modified permeable asphalt mixture with an optimal graphene content of 0.05% demonstrated a 4.5% improvement in the TSR, alongside reductions in the mass loss rate and water immersion mass loss rate of 25.64% and 23.52%, respectively. Even after prolonged thermal oxygen ageing, its TSR, mass loss rate, and water immersion mass loss rate improved by 5.1%, 23.04%, and 20.70%, respectively. Multi-factor coupling tests confirmed that the water stability met requirements under severe conditions, with better performance at high temperatures. Graphene was uniformly dispersed in the modified asphalt. The appearance of a plateau region at low frequencies in graphene-composite- and SBS-modified asphalt verified the formation of a three-dimensional network structure, and the oxygen content was positively correlated with deepening thermal oxidative ageing.
18 November 2025 in International Journal of Pavement Research and Technology