Prediction of the Phase Composition and Properties of CoCrFeMnNi Alloy

This paper presents the prediction of the phase composition and properties of a high-entropy CoCrFeMnNi alloy using the Calphad method and neural networks. The study emphasizes the importance of phase composition in determining the properties of materials, separating phases into solid solutions, intermetallic compounds, mixed phases, and amorphous structures. corrosion resistance. Traditional parametric and computational approaches are discussed, the role of rules of thumb and the potential of machine learning methods, in particular neural networks, in predicting mechanical properties such as microhardness, Young’s modulus, yield and strength strengths are emphasized. The research is aimed at creating effective methodologies for designing new alloys with optimal properties, identifying hidden patterns in large data sets, and thereby improving the efficiency of predicting the properties of complex materials.