University of Cambridge > Talks.cam > Fluids Group Seminar (CUED) > Physics-informed Neural Networks for Simultaneous Surrogate Modelling and Aerodynamic Optimization

Physics-informed Neural Networks for Simultaneous Surrogate Modelling and Aerodynamic Optimization

Add to your list(s) Download to your calendar using vCal

  • UserDr. Yubiao Sun
  • ClockFriday 13 May 2022, 12:30-13:30
  • HouseCUED, LR3B.

If you have a question about this talk, please contact .

Optimizing multiple variable problems is an exceedingly difficult task due to the curse of dimensionality. This is particularly true for airfoil shape optimization as remeshing or deformation of existing meshes is required, which is computationally expensive. Our study aims to overcome this challenge by introducing a deep learning-based framework that can handle multiple optimization problems efficiently. The essence of this framework is using surrogate modelling to produce high-fidelity solutions and then perform gradient-based optimizations for high-dimensional problems. The starting point is to use PINN to construct surrogate models that output flow fields for airfoils of varied configurations. The key feature of PINN is the incorporation of physical problem description, including the governing laws of physics, domain geometry, and boundary conditions, which enables neural networks to solve underlying differential equations (e.g., Navier—Stokes equations) as a learning problem. Thus, the surrogate models can efficiently generate flow fields as no labelled training data from a separate high-fidelity simulation is required. More importantly, we extend the employed surrogate models by including design parameters as inputs to PINN . In the optimization process, a quasi-Newton algorithm is used and further accelerated by automatic differentiation, a popular algorithm designed to efficiently compute the gradients of objective functions with respect to design variables. Two examples have been presented to demonstrate the feasibility of using PINN -based surrogate modelling for aerodynamic optimization, both single parameter and multiple parameter problems. The proposed method is straightforward to implement and computationally efficient, providing a promising alternative for computationally intensive optimization problems.

This talk is part of the Fluids Group Seminar (CUED) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity