Expanding Materials Selection Via Transfer Learning for High-Temperature Oxide Selection
- PDF / 2,454,892 Bytes
- 13 Pages / 593.972 x 792 pts Page_size
- 51 Downloads / 168 Views
https://doi.org/10.1007/s11837-020-04411-1 Ó 2020 The Minerals, Metals & Materials Society
AUGMENTING PHYSICS-BASED MODELS IN ICME WITH MACHINE LEARNING AND UNCERTAINTY QUANTIFICATION
Expanding Materials Selection Via Transfer Learning for High-Temperature Oxide Selection ZACHARY D. MCCLURE
1
and ALEJANDRO STRACHAN1,2
1.—School of Materials Engineering and Birck Nanotechnology Center, University, West Lafayette, IN 47907, USA. 2.—e-mail: [email protected]
Purdue
Materials with higher operating temperatures than today’s state of the art can improve system performance in several applications and enable new technologies. Under most scenarios, a protective oxide scale with high melting temperatures and thermodynamic stability as well as low ionic diffusivity is required. Thus, the design of high-temperature systems would benefit from knowledge of these properties and related ones for a large number of oxides. While some properties of interest are available for many oxides (e.g., elastic constants exist for > 1000 oxides), the melting temperature is known for a relatively small subset. The determination of melting temperatures is time consuming and costly, both experimentally and computationally; thus, we use data science tools to develop predictive models from the existing data. Since the relatively small number of available melting temperature values precludes the use of standard tools, we use a multi-step approach based on transfer learning where surrogate data from first principles calculations are leveraged to develop models using small datasets. We use these models to predict the desired properties for nearly 11,000 oxides and quantify uncertainties in the space.
INTRODUCTION Materials capable of operating at high temperatures are critical for applications ranging from aerospace to energy,1 and increasing their operating envelope over the current state of the art is highly desirable. For example, increasing the operating temperature of land-based turbines by 30°C would result in an approximately 1% efficiency increase and can translate into sector-wide fuel savings of $66 billion with significant environmental impact over a 15-year period.2 In addition, high temperature metallic alloys can enable rotation detonation engines for hypersonic vehicles.3 In all of these applications, high-temperature mechanical integrity or high strength is required, and so is oxidation resistance. The latter can be achieved either by the formation of a protective oxide scale during operation4 or by the incorporation of a protective oxide (often sacrificial) during fabrication.5,6 This article combines existing experimental, first principles (Received February 20, 2020; accepted September 4, 2020)
data and physics-based models with data science tools, including uncertainty quantification, to create a comprehensive dataset of potential oxides and the physical properties relevant for materials selection. In recent years, complex concentrated alloys (CCAs, multi-principal component alloys that lack a single dominant component)
Data Loading...
