Skip to main content Start main content

Deep Learning-Driven Phase Field Study on Creep and Accelerated Design of Superalloys

Research Seminar Series

20261113_event image
  • Date

    13 Nov 2026

  • Organiser

    Department of Industrial and Systems Engineering, PolyU

  • Time

    16:00 - 17:30

  • Venue

    PQ305  

Speaker

Prof. Yongsheng Li

Remarks

If you have enquiries regarding E-certificate after the seminar, please contact david.kuo@polyu.edu.hk.

20261113_poster

Summary

High-temperature creep dominates the damage and failure of aerospace materials. Creep behavior of precipitation-strengthened superalloys and lamellar TiAl alloys complicates service life prediction and compositional optimization, while multi-component superalloy development suffers from vast composition difference and nonlinear high-dimensional parameter interactions. This work establishes a dual data–physics driven framework integrating deep learning and phase-field simulations for accelerated superalloy design. Combined with crystal plasticity and creep damage theory, this cross-scale framework efficiently captures thermo-mechanically induced γ′ phase evolution, rafting kinetics and interfacial stability. We reveal cross-scale links between dislocation activity, interface damage and creep failure, and identify key composition–microstructure–property correlations. This paradigm enables intelligent performance prediction and composition-microstructure co-optimization, supporting the development of long-life aerospace hot-section materials.

Keynote Speaker

Prof. Yongsheng Li

Prof. Yongsheng Li

Professor
School of Materials Science and Engineering, Nanjing University of Science and Technology, Nanjing, China

Li Yongsheng, Professor and Doctoral Supervisor, School of Materials Science and Engineering, Nanjing University of Science and Technology. Research interests cover phase transformation and microstructure-property relationships of superalloys, steels and titanium aluminides, irradiation damage and crystal defects, as well as phase-field simulation of material microstructures and machine learning. An AI-empowered multiscale method integrating artificial intelligence with phase-field modelling is established to investigate the microstructure evolution and damage of alloys under complex thermo-mechanical coupling conditions. A total of 130 academic papers are published. More than 20 national and provincial research projects are presided over and participated in. Eight authorized national invention patents and 2 software copyrights are obtained. Seven provincial and ministerial science and technology awards are conferred, including the First Prize of Jiangsu Provincial Science and Technology Award.

Your browser is not the latest version. If you continue to browse our website, Some pages may not function properly.

You are recommended to upgrade to a newer version or switch to a different browser. A list of the web browsers that we support can be found here