Print Email Facebook Twitter Predicting the parabolic growth rate constant for high-temperature oxidation of steels using machine learning models Title Predicting the parabolic growth rate constant for high-temperature oxidation of steels using machine learning models Author Aghaeian, S. (TU Delft Design for Sustainability; TU Delft Team Amarante Bottger) Norouzi, F. (TU Delft DC systems, Energy conversion & Storage) Sloof, W.G. (TU Delft Team Joris Dik) Mol, J.M.C. (TU Delft Team Arjan Mol) Bottger, A.J. (TU Delft Team Amarante Bottger) Date 2023 Abstract 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. Subject A. SteelB. Modeling studiesC. High-temperature corrosionC. Kinetic parametersC. Oxidation To reference this document use: http://resolver.tudelft.nl/uuid:95e66d26-32a6-4019-ae5d-41a72b85642d DOI https://doi.org/10.1016/j.corsci.2023.111309 ISSN 0010-938X Source Corrosion Science: the journal on environmental degradation of materials and its control, 221 Part of collection Institutional Repository Document type journal article Rights © 2023 S. Aghaeian, F. Norouzi, W.G. Sloof, J.M.C. Mol, A.J. Bottger Files PDF 1_s2.0_S0010938X23003517_main.pdf 2.69 MB Close viewer /islandora/object/uuid:95e66d26-32a6-4019-ae5d-41a72b85642d/datastream/OBJ/view