Dynamic Modulus Prediction of Fiber-Reinforced Asphalt Mixtures Based on XGBoost Optimized by an Improved Black-Winged Kite Algorithm
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.