Abstract
Although of practical importance, there is no established modeling framework to accurately predict high-temperature cyclic oxidation kinetics of multi-component alloys due to the inherent complexity. We present a data analytics approach to predict the oxidation rate constant of NiCr-based alloys as a function of composition and temperature with a highly consistent and well-curated experimental dataset. Two characteristic oxidation models, i.e., a simple parabolic law and a statistical cyclic oxidation model, have been chosen to numerically represent the high-temperature oxidation kinetics of commercial and model NiCr-based alloys. We have successfully trained machine learning (ML) models using highly ranked key input features identified by correlation analysis to accurately predict experimental parabolic rate constants (kp). This study demonstrates the potential of ML approaches to predict oxidation kinetics of alloys over wide composition and temperature ranges. This approach can also serve as a basis for introducing more physically meaningful ML input features to predict the comprehensive cyclic oxidation behavior of multi-component high-temperature alloys with proper constraints based on the known underlying mechanisms.
Highlights
Ni-based alloys used at high temperatures are required to have both good mechanical properties and oxidation resistance
Improvements in the machine learning (ML) approach have propelled the use of data analytics to assist the discovery of materials and the prediction of properties[12,13,14,15,16,17,18,19]
It possesses many advantages in handling complex multicomponent alloys and offers the potential to extract insights from complex experiments or synthetic datasets generated from physics-based simulations
Summary
Ni-based alloys used at high temperatures are required to have both good mechanical properties and oxidation resistance. Improvements in the machine learning (ML) approach have propelled the use of data analytics to assist the discovery of materials and the prediction of properties[12,13,14,15,16,17,18,19]. It possesses many advantages in handling complex multicomponent alloys and offers the potential to extract insights from complex experiments or synthetic datasets generated from physics-based simulations. The performance of five widely used ML models, i.e., linear regression (LR)[31], Bayesian ridge regression (BR)[32,33], k-nearest neighbor regression (NN)[34], random forest regression (RF)[35], and support vector machines (SVM) regression[36], in accurately predicting the kp as a function of the number of top-ranking input features is evaluated and discussed in this paper
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
