Track 12

Applications of machine learning in mechanics

Machine learning-based computational techniques have brought great opportunities for many fields and offer new approaches to address engineering challenges. This symposium welcomes high-quality presentations that report cutting-edge advances on the development and application of data-driven machine learning-based computational techniques for engineering problems. Topics of interest include, but are not limited to, data-driven computational modelling across different length and time scales for both materials and engineering structures; artificial intelligence/machine learning-based methods for material and structure designs; combined model and data-driven approaches for multi-physics problems; machine learning models for atomistic simulations; non-destructive evaluation techniques; and physics-informed neural networks with applications to structures and materials.

This symposium will cover a comprehensive range of topics with an example selection including:

  • Applications of machine learning for continuum mechanical modelling of materials and engineering structures;
  • Applications of machine learning to atomistic simulations;
  • Applications of machine learning to non-destructive evaluation techniques;
  • Mechanical design of materials and engineering structures via machine learning techniques;
  • Applications of machine learning to experimental mechanical and microstructural characterization;
  • Integration of physics-based and machine learning models;
  • Data generation for machine learning models.

~ Speakers’ list forthcoming ~

Track Chairs

George Karniadakis
Brown University, USA

Xu Guo
Dalian University of Technology, China

Zachary Aitken
Institute of High Performance Computing, A*STAR, Singapore

Correspondence

George Karniadakis
Brown University, USA
Email: george_karniadakis@brown.edu