Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Learning Optimal Aerodynamic Designs

Technical Report ·
DOI:https://doi.org/10.2172/2528653· OSTI ID:2528653

This project created a framework for efficient, accurate, and scalable deep neural network representations of design optimization problem solutions. The inputs to these DNN representations are the vector of design requirement parameters, the outputs are the optimal design variables, and the goal is to learn the map from inputs to outputs (i.e., inverse design). The team addressed the problem of the optimal shape design of aerodynamic lifting surfaces—in particular aircraft wings—using a Reynolds-Average Navier Stokes model to govern the CFD-based aerodynamic shape optimization. The inverse design map for such problems is very complex and high-dimensional, involving inputs and outputs on the order of 1000s. To approximate this inverse design map, the team developed algorithms to construct parsimonious DNN architectures, which automatically identify low-dimensional manifolds in which design requirements affect optimal shape parameters, and trained these architectures with multifidelity optimization methods. The resulting methodology accurately and automatically designs optimal aerodynamic lifting surfaces with very high accuracy (99%) at interactive speeds, of the order of milliseconds, resulting in factors of one million or more speedup relative to CFD-based design optimization.

Research Organization:
Univ. of Texas, Austin, TX (United States)
Sponsoring Organization:
USDOE Advanced Research Projects Agency - Energy (ARPA-E)
DOE Contract Number:
AR0001208
OSTI ID:
2528653
Report Number(s):
DOE--AR0001208
Country of Publication:
United States
Language:
English

Similar Records

Applied computational aerodynamics
Book · Sun Dec 31 23:00:00 EST 1989 · OSTI ID:6080168

AIAA Applied Aerodynamics Conference, 8th, Portland, OR, Aug. 20-22, 1990, Technical Papers. Parts 1 2
Conference · Sun Dec 31 23:00:00 EST 1989 · OSTI ID:6280979

Enhanced Data Efficiency Using Deep Neural Networks and Gaussian Processes for Aerodynamic Design Optimization
Journal Article · Thu Apr 01 00:00:00 EDT 2021 · Aerospace Science and Technology · OSTI ID:1869920

Related Subjects