Abstract:Modern military technology demands continuous improvement in the damage efficiency of armor-piercing projectile core materials, driving innovation in high-performance alloy systems. TiZr-based refractory high-entropy alloys (RHEAs, Refractory High-Entropy Alloys), known for their high hardness, compressive strength, and thermal phase stability, have garnered attention due to their potential application in armor-piercing warheads. This study introduces a machine learning (ML)-assisted approach to alloy design, aiming to uncover the complex relationship between composition and performance while improving design efficiency. To address the critical requirement for hardness in armor-piercing applications, a 15-dimensional feature dataset was constructed, incorporating component molar fractions and five key descriptors, based on 157 experimental hardness data points. Eight ML models—including random forest, K-nearest neighbors, and support vector machines—were trained, and XGBoost was identified as the most accurate through hyperparameter tuning via grid search and cross-validation. The SHAP (SHAP，Shapley Additive Explanations) framework was applied to interpret feature contributions. Results indicate that the XGBoost model achieves the highest predictive performance (R2 = 0.73, and the average absolute percentage error is 14.0%). The most influential factors affecting alloy hardness are mixing enthalpy (ΔH_mix), niobium (Nb) content, and atomic size mismatch (δ). Effective hardness control necessitates the synergistic regulation of thermodynamic stability, electronic structure, and geometric dimensions, where inter-feature compensation plays a critical role in optimizing overall performance. This work establishes a novel compositional design paradigm for TiZr-based RHEAs, demonstrating the engineering value of ML in enhancing material development for high-efficiency damage applications.