arXiv subjects

Amiya Chowdhury

Publications and source records attributed to Amiya Chowdhury.

3 recordsLinked to original sources

arXiv2025

Active Learning Driven Materials Discovery for Low Thermal Conductivity Rare-Earth Pyrochlore for Thermal Barrier Coatings

High-Entropy/multicomponent rare-earth oxides (HECs and MCCs) show promise as alternative materials for thermal barrier coatings (TBC) with the ability to tailor properties based on the combination of rare-earth elements present. By enabling the substitution of scarce or supply-risk rare-earths with more readily available alternatives while maintaining comparable material performance, HECs and MCCs offer a valuable path towards alternative TBC material design. However, navigating this search space of compositionally complex materials is both time and resource intensive. In this study, an active learning (AL) framework was employed to identify HEC/MCC materials with a pyrochlore structure, with acceptable thermal conductivity (TC) for TBC applications. The AL framework was applied through a Bayesian optimisation (BO) strategy, coupled with a random forest surrogate model. TC was selected as the optimisation criterion as that is the most basic requirement of TBC materials. Over two iterations of the AL cycle, four compositions were generated and synthesized in the lab for experimental evaluation. The first iteration yielded two single-phase pyrochlores, $(La_{0.29}Nd_{0.36}Gd_{0.36})_2Zr_2O_7$ and $(La_{0.333}Nd_{0.26}Gd_{0.15}Ho_{0.15}Yb_{0.111})_2Zr_2O_7$, with measured thermal conductivities of 2.03 and 1.90 $W/mK$, respectively. The surrogate model predicted a TC of 2.009 $W/mK$ for both compositions, demonstrating it's accuracy for completely new compositions. The second iteration compositions showed dual-phase when synthesized, highlighting the need to take into account phase formation in the AL framework.

cond-mat.mtrl-sci↗

arXiv2025

A Methodological Study on Data Representation for Machine Learning Modelling of Thermal Conductivity of Rare-Earth Oxides

Quantitative structure-activity relationship (QSAR) modelling is widely employed in materials science to predict properties of interest and extract useful descriptors for measured properties. In thermal barrier coatings (TBC), QSAR can significantly shorten the experimental discovery cycle, which can take years. Although machine learning methods are commonly employed for QSAR, their performance depends on the data quality and how instances are represented. Traditional, hand-crafted descriptors based on known material properties are limited to represent materials that share the same basic crystal structure, limited the size of the dataset. By contrast, graph neural networks offer a more expressive representation, encoding atomic positions and bonds in the crystal lattice. In this study, we compare Random Forest (RF) and Gaussian Process (GP) models trained on hand-crafted descriptors from the literature with graph-based representations for high-entropy, rare-earth pyrochlore oxides using the Crystal Graph Convolutional Neural Network (CGCNN). Two different types of augmentation methods are also explored to account for the limited data size, one of which is only applicable to graph-based representations. Our findings show that the CGCNN model substantially outperforms the RF and GP models, underscoring the potential of graph-based representations for enhanced QSAR modelling in TBC research.

cond-mat.mtrl-sci↗

arXiv2023

Active learning-driven uncertainty reduction for in-flight particle characteristics of atmospheric plasma spraying of silicon

In this study, the first-of-its-kind use of active learning (AL) framework in thermal spray is adapted to improve the prediction accuracy of the in-flight particle characteristics and uses Gaussian Process (GP) ML model as a surrogate that generalises a global solution without necessarily involving physical mechanisms. The AL framework via the Bayesian Optimisation was utilised to: (a) reduce the maximum uncertainty in the given database and (b) reduce local uncertainty around a contrived test point. The initial dataset consists of 26 atmospheric plasma spray (APS) parameters of silicon, aimed at ceramic matrix composites (CMCs) for the next generation of aerospace applications. The maximum uncertainty in the initial dataset was reduced by AL-driven identification of search spaces and conducting six guided spray trails in the identified search spaces. On average, a 52.9% improvement (error reduction) of RMSE and an R2 increase of 8.5% were reported on the predicted in-flight particle velocities and temperatures after the AL-driven optimisation. Furthermore, the Bayesian Optimisation around a contrived test point to predict the best possible characteristics resulted in a three-fold increase in prediction accuracy as compared to the non-optimised prediction. These AL-guided experimental validations not only increase the informativeness of the limited dataset but is adaptable for other thermal spraying methods without necessarily involving physical mechanisms and underlying mechanisms. The use of AL-driven optimisation may drive the thermal spraying towards resource-efficiency and may serve as the first step towards fully digital thermal spraying environments.

physics.plasm-ph↗