Predicting the parabolic growth rate constant for high-temperature oxidation of steels using machine learning models
Soroush Aghaeian, F. Nourouzi, Willem G. Sloof, J.M.C. Mol, A. Böttger
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.
Topics & Concepts
Support vector machineMean squared errorConstant (computer programming)Random forestArtificial neural networkRegressionCoefficient of determinationMean absolute errorRoot mean squareComposition (language)Regression analysisCorrelation coefficientMathematicsMaterials scienceArtificial intelligenceStatisticsComputer scienceEngineeringLinguisticsProgramming languageElectrical engineeringPhilosophyHydrogen embrittlement and corrosion behaviors in metalsMetallurgical Processes and ThermodynamicsHigh-Temperature Coating Behaviors