EXTENDED ABSTRACT: low Young's modulus and high yield strength are needed to meet the required performance of metallic implant materials. The single-objective performance-oriented alloy design theory faces challenges in effectively addressing the inherent conflict between low Young's modulus and high yield strength. In light of the current research landscape regarding low modulus alloys and drawing inspiration from prior studies, this investigation developed a machine learning model for the multi-objective synergistic optimization of modulus and yield strength, successfully enabling simultaneous predictions of Young's modulus and yield strength for the Ti-Zr-Hf-Nb-TaMo-Sn alloy system, with R² values of 0.95 and 0.98, respectively. The critical features influencing the modulus and strength of the alloy were systematically analyzed and identified. Concurrently, a series of complex concentrated alloy (CCAs) with low Young's modulus and high yield strength were successfully developed by this model. These alloys demonstrate a stable single-phase BCC structure with Young's modulus in the range of 40-50 GPa, yield strength of 600-915 MPa, and elastic admissible strain of approximately 1.5%. The multi-objective machine learning model developed in this study enables the synergistic optimization of low Young's modulus and high yield strength in alloys, thereby presenting a novel approach for the design of biomedical alloys.

Figure 1. Schematic illustration of the multi-objective learning process for CCAs’ modulus & strength model

Keywords: low-modulus alloys; machine learning; complex concentrated alloys;