Predicting the Parabolic Rate Constants of High-Temperature Oxidation of Ti Alloys Using Machine Learning
- PDF / 1,964,323 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 60 Downloads / 254 Views
Predicting the Parabolic Rate Constants of High‑Temperature Oxidation of Ti Alloys Using Machine Learning Somesh Kr. Bhattacharya1 · Ryoji Sahara1,2 · Takayuki Narushima1,2 Received: 19 May 2020 / Revised: 14 June 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this study, we attempt to build a statistical (machine) learning model to predict the parabolic rate constant (kP ) for the high-temperature oxidation of Ti alloys. Exploring the experimental studies on high-temperature oxidation of Ti alloys, we built our dataset for machine learning. Apart from the alloy composition, we included the constituent phase of the alloy, temperature of oxidation, time for oxidation, oxygen and moisture content, remaining atmosphere (gas except O2 gas in dry atmosphere), and mode of oxidation testing as the independent features while the parabolic rate constant (kP ) is set as the target feature. We employed three different ML models to predict the ‘ kP ’ for Ti alloys. Among the regression models, the gradient boosting regressor yields the coefficient of determination (R2) of 0.92 for kP . The knowledge gained from this study can be used to design novel Ti alloys with excellent resistance towards high-temperature oxidation.
* Somesh Kr. Bhattacharya [email protected] 1
Research Center for Structural Materials, National Institute for Materials Science, 1‑2‑1 Sengen, Tsukuba, Ibaraki 305‑0047, Japan
2
Department of Materials Processing, Tohoku University, 6‑6‑2 Aza Aoba, Aramaki, Aoba‑ku, Sendai 980‑8579, Japan
13
Vol.:(0123456789)
Oxidation of Metals
Graphic Abstract
Keywords Titanium alloys · High-temperature oxidation · Machine learning · Regression · Python
Introduction Titanium (Ti) alloys are extensively used in high-temperature applications like the components of jet engines and automobile exhaust systems [1, 2]. At temperatures above 923 K, the Ti alloy components, particularly the thin sections in the jet engine, degrade rapidly due to oxidation [3]. The Ti alloy oxidation involves the formation of both the oxide layer on the surface and the oxygen rich layer in Ti, ‘α-case’, which is formed due to the high solubility of oxygen in Ti [4–7]. The formation of the ‘α-case’, the oxygen rich layer in Ti, causes the surface embrittlement and degrades the mechanical properties of the Ti alloys [8]. Extensive studies have been performed to study the oxidation of Ti and its alloys. The oxidation of commercially pure (CP) Ti in the temperature range of 1073–1473 K was already studied by Jenkins [9, 10] in the 1950s and by Stringer [4] and Kofstad et al. [5] in the 1960s. Kitashima et al. studied the oxidation of α-type Ti-X (X = Al, Zr, Si, Hf, Nb, Ge, and Sn) binary alloys [11, 12]. They identified Hf, Nb, Si and Zr to have beneficial effects on the oxidation resistance of Ti while Ge and Sn have detrimental effects. Experiments by Chaze et al. [6, 13] and Vojtech et al. [14] have also shown that Si enhances the oxidation resistance of Ti. Matsunaga et al. studied th
Data Loading...
