Prediction of alloy composition and microhardness by random forest in maraging stainless steels based on a cluster formula

摘要: Fe–Ni–Cr-based super-high-strength maraging stainless steels were generally realized by multiple-element alloying under a given heat treatment processing. A series of alloy compositions designed with uniform cluster formula [Ni16Fe192](Cr32(Ni16–x–y–z–m–nMoxTiyNbzAlmVn)) (at.%) that was developed out unique design tool, cluster-plus-glue-atom model. Alloy rods diameter 6 mm prepared copper-mold suction-cast processing the argon atmosphere. These samples solid-solutioned at 1273 K for 1 h, followed water-quenching, and then aged 783 K 3 h. The effect valence electron concentration, characterized number electrons per unit (VE/uc) 16 atoms, on microhardness these both states investigated. relationship between in firstly established random forest (RF, kind machine learning methods) based experimental results. It found not only any composition within frame formula, but also maximum VE/uc, could be predicted good agreement guidance RF. contributions minor-alloying elements to alloys discussed.