Artificial neural networks and their applications in computational materials science: A review and a case study

Shaoping Xiao, John Li, Stéphane Pierre Alain Bordas, Tae Yeon Kim

    Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

    4 Scopus citations

    Abstract

    Current advances in artificial intelligence (AI), especially machine learning and deep learning, provide an alternative approach to problem-solving for engineers and scientists in various disciplines, including materials science. Artificial neural networks (ANNs), including their variations as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), have become one of the most effective machine learning approaches. This paper comprehensively reviews ANNs and their applications in different computational materials science research topics, such as multiscale modeling, microstructure-dependent material properties, and model-free constitutive relationships. In addition, we intend to share AI insights in the materials science community and promote the applications of ANNs in our research.

    Original languageBritish English
    Title of host publicationAdvances in Applied Mechanics
    PublisherAcademic Press Inc.
    Pages1-33
    Number of pages33
    DOIs
    StatePublished - Jan 2023

    Publication series

    NameAdvances in Applied Mechanics
    Volume57
    ISSN (Print)0065-2156

    Keywords

    • Artificial neural networks
    • Constitutive modeling
    • Convolutional neural networks
    • Microstructure
    • Multiscale
    • Physics-informed neural networks
    • Recurrent neural networks

    Fingerprint

    Dive into the research topics of 'Artificial neural networks and their applications in computational materials science: A review and a case study'. Together they form a unique fingerprint.

    Cite this