Predicting the parabolic growth rate constant for high-temperature oxidation of steels using machine learning models

The parabolic growth rate constant (kp) of high-temperature oxidation of steels is predicted via a data analytics approach. Four machine learning models including Artificial Neural Networks, Random Forest, k-Nearest Neighbors, and Support Vector Regression are trained to establish the relations between the input features (composition and temperature) and the target value (kp). The models are evaluated by the indices: Mean Absolute Error, Mean Squared Error, Root Mean Squared Error and Coefficient of Determination. The steel composition regarding Cr and Ni content and the temperature were the most significant input features controlling the oxidation kinetics.Funding Information: This work was supported by the research program of the Materials innovation institute, The Netherlands (M2i, www.m2i.nl ) [project number T17019p ], which is supported by the Dutch government . The authors are indebted to Dr. W. Melfo and Dr. P. J. van der Wolk of Tata Steel (IJmuiden, The Netherlands) for the valuable discussions. Publisher Copyright: © 2023 The Author(s)Design for SustainabilityTeam Amarante BottgerDC systems, Energy conversion & StorageTeam Joris DikTeam Arjan Mo