1712 Machine Learning and Computational Modeling for Mechanical Behavior of Materials

  • C-S David Chen, National Taiwan University
  • C.T. Wu, Ansys
  • Nien-Ti Tsou, National Yang Ming Chiao Tung University

Mechanical behavior is dominated by defects, materials compositions, microstructures, phase transformation etc. A wide variety of computational methods are used to study the underneath physical mechanisms, predict the mechanical behavior of materials, and enable the design/optimization of mechanical properties. A few notable computational methods include atomistic calculations, crystal plasticity, phase field method, two-scale homogenization, finite element method etc. Recent surge in machine learning and deep learning provides another spectrum for accelerating the paradigm of materials by design. A few notable examples include rapid screening with a surrogate model, topology optimization, genetic algorithm, generative adversarial networks and transformer, reinforcement learning etc. This mini-symposium aims to offer a forum to present and exchange research results and practical applications featuring contributions on machine learning and computational modeling in all aspects of mechanical behavior of materials. In this mini-symposium, we not only wish to share the cutting-edge research works of machine learning and computational methods, but also to identify the emergent needs of industry to make more rapid progress in practical applications.

© WCCM-APCOM 2022. All Rights Reserved.