Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

ACMD Seminar: Invertible neural networks for wind turbine airfoil and blade design

Andrew Glaws
National Renewable Energy Laboratory

Tuesday, November 30, 2021, 3:00 PM EST (1:00 PM MST)

A video of this talk is available to NIST staff in the Math channel on NISTube, which is accessible from the NIST internal home page.

Abstract:  The airfoil design problem, in which an engineer seeks a shape with desired aerodynamic performance or structural characteristics, is fundamental to the aerospace and energy industries. Design workflows traditionally rely on iterative optimization methods using low fidelity integral boundary layer methods as higher fidelity adjoint-based CFD methods are computationally expensive. We leverage emerging invertible neural network (INN) tools to enable the rapid inverse design of airfoil shapes for wind turbines. INNs are specialized deep learning models with well-defined inverse mappings. When trained appropriately, INN surrogate models are capable of forward prediction of aerodynamic and structural quantities for a given airfoil shape as well as inverse recovery of airfoil shapes with specified aerodynamic and structural characteristics. We study to use of this tools for airfoil design and examine pathways toward full three-dimensional wind turbine blade design.

Bio:  Andrew Glaws is a researcher in Computational Sciences Center at the National Renewable Energy Laboratory in Golden, CO. He joined the lab as a postdoc in January 2019 to work on physics-informed deep learning for energy systems. His research focuses on enhancing scientific research into renewable energy and energy efficient problems using machine learning, artificial intelligence, and other data-driven methods. He has collaborated with domain scientists in a variety of energy-related fields, including wind and solar energy, climate science, buildings energy analysis, bioenergy, and battery technology. Prior to joining NREL, Andrew completed his Ph.D. in computer science at the University of Colorado Boulder, researching the use of parameter reduction methods for computational experiments.

Host: Zachary Grey

Note: This talk will be recorded to provide access to NIST staff and associates who could not be present to the time of the seminar. The recording will be made available in the Math channel on NISTube, which is accessible only on the NIST internal network. This recording could be released to the public through a Freedom of Information Act (FOIA) request. Do not discuss or visually present any sensitive (CUI/PII/BII) material. Ensure that no inappropriate material or any minors are contained within the background of any recording. (To facilitate this, we request that cameras of attendees are muted except when asking questions.)

Created October 29, 2021, Updated December 1, 2021