Microstructure Estimation by Combining Deep Learning and Phase Transformation Model

In material design, the establishment of process structure property relationship is crucial for analyzing and controlling material microstructures. For the establishment of process structure property relationship, a central problem is the analysis, characterization, and control of microstructures, since microstructures are highly sensitive to material processing and critically affect material's properties. Therefore, accurately estimating the morphology of material microstructures plays a significant role in understanding the process structure property relationship. In this paper, we propose a deep -learning framework for estimating material microstructures under specific process conditions. The framework utilizes two deep learning networks: Vector Quantized Variational Autoencoder (VQVAE) and Pixel Convolutional Neural Network (PixeICNN). The framework can predict material micrographs from the transformation behavior given by some physical model. In this sense, the framework is consistent with the physical knowledge accumulated in the field of material science. Importantly our study demonstrates qualitative and quantitative evidences that incorporating physical models enhances the accuracy of microstructure estimation by deep learning models. These results highlight the importance of appropriately integrating field -specific knowledge when applying data-driven frameworks to materials design. Consequently, our results provide a foundation for integrating data-driven methods with the accumulated knowledge in the field. This integration holds great potential for advancing material design through deep learning.

Automated summary

This paper highlights the importance of establishing the process structure property relationship in material design and proposes a deep learning framework for estimating material microstructures. The study demonstrates that incorporating physical models enhances the accuracy of microstructure estimation by deep learning models. This integration holds great potential for advancing material design through deep learning.