Search

Environmental barrier coatings (EBCs) are an enabling technology for silicon carbide (SiC)-based ceramic matrix composites (CMCs) in extreme environments such as gas turbine engines. However, development of new coating systems is hindered by the large design space and difficulty in predicting properties for these materials. Density Functional Theory (DFT) has successfully been used to model and predict some thermodynamic and thermo-mechanical properties of high-temperature ceramics for EBCs, although these calculations are challenging due to their high computational costs. In this work, we use machine learning to train a deep neural network potential (DNP) for Y2Si2O7, which is then applied to calculate thermodynamic and thermo-mechanical properties at near-DFT accuracy much faster and using less computational resources than DFT. We use this DNP to predict phonon-based thermodynamic properties of Y2Si2O7 with good agreement to DFT and experiments. We also utilize the DNP to calculate the anisotropic, lattice direction-dependent coefficients of thermal expansion (CTEs) for Y2Si2O7. Molecular dynamics trajectories using the DNP correctly demonstrate accurate prediction of the anisotropy of the CTE in good agreement with diffraction experiments. In the future, this DNP could be applied to accelerate additional property calculations for Y2Si2O7 compared to DFT or experiments.

Mixtures of Y2Si2O7 and Gd2Si2O7 were synthesized by solid-state reaction at 1600°C and characterized via in situ x-ray diffraction (XRD) to determine their coefficients of thermal expansion (CTE). All solid solutions within the system exhibited the orthorhombic δ-RE2Si2O7 (Pna21) structure. Thermal expansion measurements of Y2Si2O7 and Gd2Si2O7 correlated well with reported values in literature, and all synthesized solid solutions exhibited CTEs between Y2Si2O7 and Gd2Si2O7. Generally, there was a slight decrease in CTE exhibited by the materials with increasing Gd2Si2O7 content, with Gd2Si2O7 having the lowest CTEs and Y2Si2O7 the highest CTEs. The decrease in CTE was attributed to stronger bonds of Gd-O over Y-O, as determined by calculated crystal orbital Hamilton populations using density functional theory. However, such differences were very small and crystal structure was the dominating factor in CTE trends.

In this work, a neural network model was developed to predict the constant pressure heat capacity for materials in the rare-earth oxide—silica material space. Several model architectures were trained and tested on heat capacity data generated from first-principles density functional theory calculations. Hyperparameter optimization was performed, and the optimal model was selected for heat capacity predictions. The optimal model architecture was found to have a root-mean-squared error of 5.12 ± 3.37 J/mol-K. The optimal model architecture was then used in a bagging ensemble model trained using the leave-one-group-out method to provide error estimates for model predictions. The out-of-bag score for the ensemble model was 0.997. The predicted heat capacities agree well with the DFT and experimental results and were computed orders of magnitude faster than DFT simulations. Machine learning shows the potential to provide a suitable surrogate model for thermochemical property predictions for candidate environmental barrier coating materials but refining of input material features and model architectures could further improve accuracy for these models.