Abstract: This paper reports the use of integrated computational alloy design, coupled with a rapid printability screening method, to downselect from a total of 70000 datasets in design space to five candidates in the first step, and then from five to one in the second step. The new Ni-base superalloy with compositions of Ni-5.03Al-2.69Co-5.63Cr-0.04Hf-1.91Mo-2.36Re-3.32Ta-0.57Ti-8.46W-0.05C-0.019B exhibits an optimal balance of density (8.82 g/cm²), printability (freezing range of 107 °C), thermal stability (γ′-volume fraction of 50.7 % at 980 °C and low Md‾ value) and creep (rupture time of 612 h at 980 °C/120 MPa). The micro-hardness varies mildly from 417.2 ± 18.5 to 434.7 ± 14.6 HV, suggesting good phase stability. This is substantiated by microstructure observations, which revealed the absence of a topologically close-packed phase. Machine-learning tools of the artificial neural network (ANN), random forest, and support vector regression, respectively, were used to predict creep rupture time. The ANN algorithm achieves the highest accuracy in predicting creep life. By recognising the “black box” nature of the ANN, interpretability analysis was conducted using the local interpretable model-agnostic method. The analysis supports that the ANN model truly learned meaningful functional relationships, and thus is judged as reliable. Feature correlation evaluation outcome emphasises the importance of incorporating microstructure-related input features.

Key words: Alloy design, Ni-base superalloys, Additive manufacturing, Machine learning, Creep