Multiobjective Optimization‐Driven Design of Novel Zn Alloys Exhibiting Synergistic Enhancement of Strength and Ductility via NSGA‐III

With excellent castability and dimensional stability, Zn alloys are widely used in the automotive and electronic industries. However, the inherent trade‐off between strength and ductility remains a key bottleneck limiting their application in high‐performance fields. In this study, a multidimensional dataset covering hardness (HD), ultimate tensile strength (UTS), and elongation (EL) of Zn alloys was established. Through feature engineering, six key elemental features—Al, Cu, Si, Ti, Mg, and Zn—were accurately identified. Three XGBoost machine learning (ML) models with prediction accuracy ( R 2 ) values exceeding 0.9 were established. By integrating the nondominated sorting genetic algorithm III (NSGA‐III), a novel high‐strength and high‐ductility Zn alloy was successfully designed. Compared with conventional Zn alloys, this alloy achieves a groundbreaking balance in three mechanical properties (155 HV, 354 MPa, and 2%), resulting in a significant improvement in overall performance. This study breaks through the traditional trial‐and‐error paradigm by establishing a novel materials development workflow integrating data‐driven modeling, performance prediction, optimization design, and experimental validation, enabling rapid and efficient discovery of Zn alloys with superior strength and ductility. It provides a new research paradigm for the synergistic optimization of structural material properties.