Discovery of New Ti-Based Alloys Aimed at Avoiding/Minimizing Formation of α” and ω-Phase Using CALPHAD and Artificial Intelligence

Abstract

In this work, we studied a Ti-Nb-Zr-Sn system for exploring novel composition and temperatures that will be helpful in maximizing the stability of β phase while minimizing the formation of α” and ω-phase. The Ti-Nb-Zr-Sn system is free of toxic elements. This system was studied under the framework of CALculation of PHAse Diagram (CALPHAD) approach for determining the stability of various phases. These data were analyzed through artificial intelligence (AI) algorithms. Deep learning artificial neural network (DLANN) models were developed for various phases as a function of alloy composition and temperature. Software was written in Python programming language and DLANN models were developed utilizing TensorFlow/Keras libraries. DLANN models were used to predict various phases for new compositions and temperatures and provided a more complete dataset. This dataset was further analyzed through the concept of self-organizing maps (SOM) for determining correlations between phase stability of various phases, chemical composition, and temperature. Through this study, we determined candidate alloy compositions and temperatures that will be helpful in avoiding/minimizing formation of α” and ω-phase in a Ti-Zr-Nb-Sn system. This approach can be utilized in other systems such as ω-free shape memory alloys. DLANN models can even be used on a common Android mobile phone.