Weatheritt, Jack and Sandberg, Richard D. and Ling, Julia and Saez, Gonzalo and Bodart, Julien
A Comparative Study of Contrasting Machine Learning Frameworks Applied to RANS Modeling of Jets in Crossflow.
(2017)
In: ASME Turbo Expo 2017: Turbomachinery Technical Conference and Exposition, 26 June 2017 - 30 June 2017 (Charlotte, United States).
|
(Document in English)
PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader 2MB |
Official URL: http://dx.doi.org/10.1115/GT2017-63403
Abstract
Classical RANS turbulence models have known deficiencies when applied to jets in crossflow. Identifying the linear Boussinesq stress-strain hypothesis as a major contribution to erroneous prediction, we consider and contrast two machine learning frameworks for turbulence model development. Gene Expression Programming, an evolutionary algorithm that employs a survival of the fittest analogy, and a Deep Neural Network, based on neurological processing, add non-linear terms to the stress-strain relationship. The results are Explicit Algebraic Stress Model-like closures. High fidelity data from an inline jet in crossflow study is used to regress new closures. These models are then tested on a skewed jet to ascertain their predictive efficacy. For both methodologies, a vast improvement over the linear relationship is observed.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Audience (conference): | International conference proceedings |
Uncontrolled Keywords: | |
Institution: | Université de Toulouse > Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE) Other partners > University of Melbourne (AUSTRALIA) Other partners > Honeywell (USA) Other partners > National Nuclear Security Administration - NNSA (USA) Other partners > Sandia (USA) |
Laboratory name: | |
Statistics: | download |
Deposited On: | 19 Feb 2018 12:14 |
Repository Staff Only: item control page