Machine learning prediction of elastic properties and glass-forming ability of bulk metallic glasses
- PDF / 2,191,399 Bytes
- 10 Pages / 612 x 792 pts (letter) Page_size
- 78 Downloads / 286 Views
rtificial Intelligence Research Letter
Machine learning prediction of elastic properties and glass-forming ability of bulk metallic glasses Jie Xiong , Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hong Kong, China Tong-Yi Zhang, Materials Genome Institute, Shanghai University, Shanghai, China San-Qiang Shi, Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hong Kong, China Address all correspondence to Tong-Yi Zhang at [email protected] (Received 4 January 2019; accepted 25 March 2019)
Abstract There is a genuine need to shorten the development period for new materials with desired properties. In this work, machine learning (ML) was conducted on a dataset of the elastic moduli of 219 bulk-metallic glasses (BMGs) and another dataset of the critical casting diameters (Dmax) of 442 BMGs. The resulting ML model predicted the moduli and Dmax of BMGs in good agreement with most experimentally measured values, and the model even identified some errors reported in the literature. This work indicates the great potential of ML in design of advanced materials with target properties.
Introduction Bulk-metallic glasses (BMGs), as promising materials with unique structural features and outstanding mechanical, physical, and chemical properties, have been extensively studied for potential applications in various fields since they were first discovered in 1960 by Duwez and co-workers.[1] However, the relationship between the mechanical properties and chemical composition of BMGs remains unclear due to the poor understanding of the underlying physics. No successful analytic model is currently available to design a new BMG with targeted properties. As a result, the discovery and optimization of potential materials for application relies on the timeconsuming traditional paradigms of materials science and engineering.[2] Along with the fast development of artificial intelligence, the paradigm of machine learning (ML) and materials informatics, which unifies the knowledge learned from experiments, theory, computations, and simulations, is rapidly becoming popular in materials science.[2–7] Integrating artificial intelligence with materials science and engineering will accelerate the design and discovery of advanced materials. Several research groups have used ML to study metallic glasses. For example, Sun and co-workers used support vector machine to study the glass-forming ability (GFA) of binary metallic alloys with random compositions.[5] Ward and Ren applied an ML approach to metallic glasses containing three or more elements.[6,7] The findings of these studies suggest that ML has great potential to aid in discovery of new metallic glasses with good GFA. In this work, we used ML to study BMGs with the aim to predict their elastic moduli (bulk modulus K and shear
576 ▪
modulus G) and GFA. A four-step procedure was followed: (1) data collection: two sets of experimental data on metal– metal BMGs were collected from the literature, one set containing the elastic moduli of 219 BMGs and t
Data Loading...
