Physics-informed Deep Learning for Flow Modelling and Aerodynamic Optimization

Yubiao Sun, Ushnish Sengupta, Matthew Juniper

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

PDE-constrained optimization is an exceedingly difficult task due to the curse of dimensionality. This is particularly true in aerodynamics optimization as remeshing or deformation of existing meshes is often required. In this paper, we aim to overcome this challenge by proposing a simulation-based optimization framework that can handle various optimization problems efficiently. The proposed approach is able to simultaneous make predictions and perform optimizations. Specifically, the framework consists of a surrogate model to generate high-fidelity solutions and a gradient-based algorithm to address high-dimensional optimization problems. The starting point is to use physics-informed neural network (PINN) to construct surrogate models that output flow fields for airfoils of varied configurations. In this sense, PINN is computationally cheap as no labelled training data from a separate high-fidelity simulation is required. Thus, a trained surrogate model can efficiently generate flow fields for any intermediate optimization scenarios. More importantly, we design the architecture of surrogate models and include design variables as inputs to PINN. This mechanism enables neural network to extract geometric features of various input computational domains. A trained surrogate model can represent solutions on unseen design cases from both seen and unseen categories. 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 parameters. An optimization examples aiming to achieve the maximal lift-to-drag ratio has been presented. The example is a single parameter optimization problem focusing on finding the optimal angle of attack. The proposed method is straightforward to implement and computationally efficient, providing a promising alternative for computationally intensive optimization problems.

Original languageEnglish
Title of host publicationProceedings of the 2022 IEEE Symposium Series on Computational Intelligence, SSCI 2022
EditorsHisao Ishibuchi, Chee-Keong Kwoh, Ah-Hwee Tan, Dipti Srinivasan, Chunyan Miao, Anupam Trivedi, Keeley Crockett
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1149-1155
Number of pages7
ISBN (Electronic)9781665487689
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event2022 IEEE Symposium Series on Computational Intelligence, SSCI 2022 - Singapore, Singapore
Duration: 4 Dec 20227 Dec 2022

Publication series

NameProceedings of the 2022 IEEE Symposium Series on Computational Intelligence, SSCI 2022

Conference

Conference2022 IEEE Symposium Series on Computational Intelligence, SSCI 2022
Country/TerritorySingapore
CitySingapore
Period4/12/227/12/22

Keywords

  • Automatic differentiation
  • Deep learning
  • Lift-to-drag ratio
  • Parameter optimization
  • Physics-informed neural network
  • Sur-rogate modelling

Fingerprint

Dive into the research topics of 'Physics-informed Deep Learning for Flow Modelling and Aerodynamic Optimization'. Together they form a unique fingerprint.

Cite this