CCP-NTH Webinar – Data-Driven and Physics-Enhanced Machine Learning Frameworks for Uncertainty Quantification and Numerical Simulation of Turbomachinery Flows

Topic: CCP-NTH Webinar – Data-Driven and Physics-Enhanced Machine Learning Frameworks for Uncertainty Quantification and Numerical Simulation of Turbomachinery Flows

Time: Sep 26, 2025 01:30 PM London

Speaker: Dr. Zhihui Li, Liverpool University

Topic: Data-Driven and Physics-Enhanced Machine Learning Frameworks for Uncertainty Quantification and Numerical Simulation of Turbomachinery Flows

Abstract: 

This presentation highlights my recent work on developing data-driven, physics-enhanced machine learning frameworks aimed at improving uncertainty quantification and numerical simulation of turbomachinery flows. By incorporating a multi-fidelity approach, the framework significantly reduces reliance on high-fidelity data. Integrating neural networks with physical laws enables accurate, high-fidelity flow predictions, particularly for solving inverse problems. This method tackles key challenges in modelling complex multiphysical phenomena and supports robust optimization of turbomachinery components. Ultimately, the proposed frameworks seek to accelerate the design and analysis of next-generation power and energy systems, enhancing efficiency and sustainability in aerospace and energy sectors.

A short bio of the speaker:

Dr. Li is a Lecturer in the Department of Mechanical and Aerospace Engineering at the University of Liverpool and a Visiting Researcher at Imperial College London. Prior to these roles, he served as a Marie Curie Individual Research Fellow (funded by the EU Marie Skłodowska-Curie Individual Fellowship) at the Department of Aeronautics at Imperial College London, as well as a Research Fellow at the Gas Turbine and Transmissions Research Centre at University of Nottingham. His research interests primarily focus on numerical simulation, uncertainty quantification, and optimization design using advanced machine learning techniques, with applications in advanced power and energy systems.