Integrating machine learning and CALPHAD method for exploring low‐modulus near‐β‐Ti alloys
- 11 November 2023
- journal article
- research article
- Published by Wiley in Rare Metals
- Vol. 43 (1) , 309-323
Abstract
Traditional theoretical and empirical calculation methods can guide the design of β‐ and metastable β‐alloys for bio‐titanium. However, it is still difficult to obtain novel near‐β‐Ti alloys with low modulus. This study developed a method that combines machine learning with calculation of phase diagrams (CALPHAD) to facilitate the design of near‐β‐Ti alloys. An elastic modulus database of Ti–Nb–Zr–Mo–Ta–Sn system was constructed first, and then three features (the electron to atom ratio, mean absolute deviation of atom mass, and mean electronegativity) were selected as the key factors of modulus by performing a three‐step feature selection. With these features, a highly accurate model was built for predicting the modulus of near‐β‐Ti alloys. To further ensure the accuracy of modulus prediction, machine learning with the elastic constants calculated was leveraged by CALPHAD database. The root mean square error of the well‐trained model can be as low as 6.75 GPa. Guided by the prediction of machine learning and CALPHAD, three novel near‐β‐Ti alloys with elastic modulus below 50 GPa were successfully designed in this study. The best candidate alloy (Ti–26Nb–4Zr–4Sn–1Mo–Ta) exhibits an ultra‐low modulus (36.6 GPa) after cold rolling with a thickness reduction of 20%. Our method can greatly save time and resources in the development of novel Ti alloys, and experimental verifications have demonstrated the reliability of this method.Keywords
Funding Information
- National Natural Science Foundation of China (52071339)
- National Natural Science Foundation of China (52071339)
- Natural Science Foundation of Hunan Province, China (2020JJ4739)
- Guangxi Key Laboratory of Information Materials (Guilin University of Electronic Technology), China (201009-K)
This publication has 87 references indexed in Scilit:
- Influence of cold rolling and ageing treatment on microstructure and mechanical properties of Ti–30Nb–5Ta–6Zr alloyJournal of the Mechanical Behavior of Biomedical Materials, 2013
- Characterization of a new beta titanium alloy, Ti–12Mo–3Nb, for biomedical applicationsJournal of Alloys and Compounds, 2012
- Effects of cold deformation on microstructure, texture evolution and mechanical properties of Ti–Nb–Ta–Zr–Fe alloy for biomedical applicationsMaterials Science and Engineering: A, 2012
- Development of high Zr-containing Ti-based alloys with low Young's modulus for use in removable implantsMaterials Science and Engineering: C, 2011
- Synthesis and characterisation of a new superelastic Ti–25Ta–25Nb biomedical alloyJournal of the Mechanical Behavior of Biomedical Materials, 2010
- The effect of Zr content on the microstructure, mechanical properties and cell attachment of Ti–35Nb–xZr alloysBiomedical Materials, 2010
- Pseudoelastic behaviour of a β Ti–25Nb–3Zr–3Mo–2Sn alloyMaterials Science and Engineering: A, 2010
- Physical metallurgy of Ti–Ni-based shape memory alloysProgress in Materials Science, 2005
- Beta TiNbSn Alloys with Low Young’s Modulus and High StrengthMATERIALS TRANSACTIONS, 2005
- Absolute electronegativity and absolute hardness of Lewis acids and basesJournal of the American Chemical Society, 1985