|About this Abstract
||2018 TMS Annual Meeting & Exhibition
||Computational Method and Experimental Approaches for Model Development and Validation, Uncertainty Quantification, and Stochastic Predictions
||Bayesian Linear Regression and Kriging Methods for Uncertainty Quantification in Process-structure-property Linkages of Low Carbon Steels and Superalloys
||Yuksel Yabansu, Almambet Iskakov, Sudhir Rajagopalan, Anna Kapustina, Surya R Kalidindi
|On-Site Speaker (Planned)
Process-structure-property (P-S-P) linkages play a critical role in advanced material design. However, there are uncertainties originating from variance in microstructure, processing conditions and property measurements. These uncertainties must be incorporated in the machine learning approaches to evaluate the performance of the linkages and their associated uncertainty. In this study, low dimensional representation of the microstructure was obtained through Materials Knowledge Systems (MKS). Then, Bayesian linear regression (BLR) and Kriging methods were employed to establish S-P linkages and P-S linkages, respectively. Bayesian linear regression approach was utilized to establish the linkages between the low carbon steel microstructures and their yield strength measurements obtained through instrumented microindentation. On the other hand, the Kriging approach was employed to link the processing parameters of stress and temperature to nickel based superalloy microstructures.
||Planned: Supplemental Proceedings volume