Surrogate Modeling-Driven Physics-Informed Multi-fidelity Kriging for the Prediction of Accident-Tolerant Fuel Properties

The Gaussian Process (GP)-based surrogate model will not be very accurate when we have limited high-fidelity (experimental) data. In addition, it is challenging to apply higher-dimensional functions (>20-dimensional function) to approximate predictions with the GP. Furthermore, noisy data or data-containing erroneous observations and outliers are major challenges for advanced accident-tolerant fuel (ATF) concepts. This challenge can be aggravated by a lack of data, missing data, and inconsistencies in data, which require techniques to identify missing data in a dataset before the dataset is used in a predictive algorithm. Also, the governing differential equation is empirical for longer-term ATF candidates, and data availability is an issue. Physics-informed Multi-fidelity Kriging (MFK) can be useful for identifying and predicting the required material properties. MFK is particularly useful with low-fidelity physics (approximating physics) and limited high-fidelity data – which is the case for ATF candidates since there is limited data availability. This chapter explores the method and presents its application to experimental thermal conductivity measurement data for ATF. The MFK method showed its significance for a small number of data that could not be modeled by the conventional Kriging method. Mathematical models constructed with this method can be easily connected to later-stage analysis such as uncertainty quantification and sensitivity analysis and are expected to be applied to fundamental research and a wide range of product development fields.