Convolutional-network models to predict wall-bounded turbulence from wall quantities
نویسندگان
چکیده
Two models based on convolutional neural networks are trained to predict the two-dimensional instantaneous velocity-fluctuation fields at different wall-normal locations in a turbulent open-channel flow, using wall-shear-stress components and wall pressure as inputs. The first model is fully network (FCN) which directly predicts fluctuations, while second one reconstructs flow linear combination of orthonormal basis functions, obtained through proper orthogonal decomposition (POD), hence named FCN-POD. Both data from direct numerical simulations friction Reynolds numbers $Re_{\tau } = 180$ 550. Being able nonlinear interactions both show better predictions than extended (EPOD), establishes relation between input output fields. performance compared fluctuation fields, turbulence statistics power-spectral densities. FCN exhibits best closer wall, whereas FCN-POD provides larger distances. We also assessed feasibility transfer learning for model, parameters learned }=180$ dataset initialize those that }=550$ dataset. After training initialized new }$ , our results indicate possibility matching reference-model up $y^{+}=50$ with $50\,\%$ $25\,\%$ original data. expect these non-intrusive sensing will play an important role applications related closed-loop control wall-bounded turbulence.
منابع مشابه
Coherent structures in wall-bounded turbulence.
The inherent difficulty of understanding turbulence has led to researchers attacking the topic in many different ways over the years of turbulence research. Some approaches have been more successful than others, but most only deal with part of the problem. One approach that has seen reasonable success (or at least popularity) is that of attempting to deconstruct the complex and disorganised tur...
متن کاملPhenomenology of wall-bounded Newtonian turbulence.
We construct a simple analytic model for wall-bounded turbulence, containing only four adjustable parameters. Two of these parameters are responsible for the viscous dissipation of the components of the Reynolds stress tensor. The other two parameters control the nonlinear relaxation of these objects. The model offers an analytic description of the profiles of the mean velocity and the correlat...
متن کاملRelationship between Turbulence Modulation and Skewness in Wall Bounded Flows
Recent investigations into wall-bounded turbulent flows have shown a nonlinear scale interaction, whereby the largescale motion amplitude modulates the small-scale structures (Hutchins & Marusic, 2007b). Mathis et al. (2009) developed a scheme to quantify the degree of modulation using a decoupling procedure, based on the Hilbert transformation applied to the filtered small-scale component of t...
متن کاملHot-wire spatial resolution issues in wall-bounded turbulence
N. HUTCHINS, T. B. NICKELS, I. MARUSIC and M. S. CHONG Journal of Fluid Mechanics / Volume 635 / September 2009, pp 103 136 DOI: 10.1017/S0022112009007721, Published online: 10 September 2009 Link to this article: http://journals.cambridge.org/abstract_S0022112009007721 How to cite this article: N. HUTCHINS, T. B. NICKELS, I. MARUSIC and M. S. CHONG (2009). Hotwire spatial resolution issues ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Fluid Mechanics
سال: 2021
ISSN: ['0022-1120', '1469-7645']
DOI: https://doi.org/10.1017/jfm.2021.812