Microstructure Estimation by Combining Deep Learning and Phase Transformation Model

DOI Web Site Web Site 29 References
  • Noguchi Satoshi
    Research Institute for Value-Added Information Generation, Japan Agency for Marine-Earth Science and Technology
  • Aihara Syuji
    The University of Tokyo
  • Inoue Junya
    Institute of Industrial Science, The University of Tokyo Department of Material Engineering, The University of Tokyo

Bibliographic Information

Other Title
  • 深層学習と相変態モデルの融合による微細組織推定
  • シンソウ ガクシュウ ト ソウヘンタイ モデル ノ ユウゴウ ニ ヨル ビサイ ソシキ スイテイ

Search this article

Abstract

<p>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 (PixelCNN). 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.</p>

Journal

  • Tetsu-to-Hagane

    Tetsu-to-Hagane 109 (11), 898-914, 2023-11-01

    The Iron and Steel Institute of Japan

References(29)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top