scholarly journals A Machine Learning Approach for Determining the Turbulent Diffusivity in Film Cooling Flows

2017 ◽  
Vol 140 (2) ◽  
Author(s):  
Pedro M. Milani ◽  
Julia Ling ◽  
Gonzalo Saez-Mischlich ◽  
Julien Bodart ◽  
John K. Eaton
Keyword(s):  
Machine Learning ◽  
Film Cooling ◽  
Turbulent Heat Flux ◽  
Navier Stokes ◽  
Data Sets ◽  
Turbulent Heat ◽  
Turbulent Diffusivity ◽  
Film Cooling Effectiveness ◽  
Cooling Flows ◽  
Novel Approach

In film cooling flows, it is important to know the temperature distribution resulting from the interaction between a hot main flow and a cooler jet. However, current Reynolds-averaged Navier–Stokes (RANS) models yield poor temperature predictions. A novel approach for RANS modeling of the turbulent heat flux is proposed, in which the simple gradient diffusion hypothesis (GDH) is assumed and a machine learning (ML) algorithm is used to infer an improved turbulent diffusivity field. This approach is implemented using three distinct data sets: two are used to train the model and the third is used for validation. The results show that the proposed method produces significant improvement compared to the common RANS closure, especially in the prediction of film cooling effectiveness.

scholarly journals A Machine Learning Approach for Determining the Turbulent Diffusivity in Film Cooling Flows

2017 ◽  
Author(s):  
Pedro M. Milani ◽  
Julia Ling ◽  
Gonzalo Saez-Mischlich ◽  
Julien Bodart ◽  
John K. Eaton
Keyword(s):  
Machine Learning ◽  
Film Cooling ◽  
Learning Algorithm ◽  
Turbulent Heat Flux ◽  
Navier Stokes ◽  
Turbulent Heat ◽  
Turbulent Diffusivity ◽  
Film Cooling Effectiveness ◽  
Cooling Flows ◽  
Novel Approach

In film cooling flows, it is important to know the temperature distribution resulting from the interaction between a hot main flow and a cooler jet. However, current Reynolds-averaged Navier-Stokes (RANS) models yield poor temperature predictions. A novel approach for RANS modeling of the turbulent heat flux is proposed, in which the simple gradient diffusion hypothesis (GDH) is assumed and a machine learning algorithm is used to infer an improved turbulent diffusivity field. This approach is implemented using three distinct data sets: two are used to train the model and the third is used for validation. The results show that the proposed method produces significant improvement compared to the common RANS closure, especially in the prediction of film cooling effectiveness.

LES Informed Data-Driven Modelling of a Spatially Varying Turbulent Diffusivity Coefficient in Film Cooling Flows

2020 ◽  
Author(s):  
Christopher D. Ellis ◽  
Hao Xia ◽  
Gary J. Page
Keyword(s):  
Random Forests ◽  
Film Cooling ◽  
Turbulent Heat Flux ◽  
Data Driven ◽  
Turbulent Heat ◽  
Diffusivity Coefficient ◽  
Turbulent Diffusivity ◽  
Cooling Flows ◽  
Gradient Diffusion ◽  
Spatially Varying

Abstract A novel data-driven approach is used to describe a spatially varying turbulent diffusivity coefficient for the Higher Order Generalised Gradient Diffusion Hypothesis (HOGGDH) closure of the turbulent heat flux to improve upon RANS cooling predictions in film cooling flows. Machine learning algorithms are trained on two film cooling flows and tested on a case of a different density and blowing ratio. The Random Forests and Neural Network algorithms successfully reproduced the LES described coefficient and the magnitude of the turbulent heat flux vector. The Random Forests model was implemented in a steady RANS solver with a k-ω SST turbulence model and applied to four cases. All cases saw improvements in the predicted Adiabatic Cooling Effectiveness (ACE) over the cooled surface compared to the standard Gradient Diffusion Hypothesis (GDH) approach, but only minor improvements in the centreline and lateral spread are seen compared to a HOGGDH model with a constant cθ of 0.6. Further improvements to cooling predictions are highlighted by extending these data-driven approaches into turbulence modelling to improve flow field predictions.

Physical Interpretation of Machine Learning Models Applied to Film Cooling Flows

2018 ◽  
Author(s):  
Pedro M. Milani ◽  
Julia Ling ◽  
John K. Eaton
Keyword(s):  
Machine Learning ◽  
Film Cooling ◽  
Turbulent Heat Flux ◽  
Turbulent Heat ◽  
Cooling Flows ◽  
Gradient Diffusion ◽  
Machine Learning Approach ◽  
Accurate Temperature ◽  
Injection Region ◽  
Model Features

Current turbulent heat flux models fail to predict accurate temperature distributions in film cooling flows. The present paper focuses on a machine learning approach to this problem, in which the Gradient Diffusion Hypothesis (GDH) is used in conjunction with a data-driven prediction for the turbulent diffusivity field αt. An overview of the model is presented, followed by validation against two film cooling datasets. Despite insufficiencies, the model shows some improvement in the near-injection region. The present work also attempts to interpret the complex machine learning decision process, by analyzing the model features and determining their importance. These results show that the model is heavily reliant of distance to the wall d and eddy viscosity vt, while other features display localized prominence.

scholarly journals Generalization of Machine-Learned Turbulent Heat Flux Models Applied to Film Cooling Flows

2019 ◽  
Author(s):  
Pedro M. Milani ◽  
Julia Ling ◽  
John K. Eaton
Keyword(s):  
Heat Flux ◽  
Film Cooling ◽  
Cross Validation ◽  
Turbulent Heat Flux ◽  
Navier Stokes ◽  
Turbulent Heat ◽  
Turbulent Prandtl Number ◽  
Cooling Systems ◽  
Cooling Flows ◽  
Visualization Techniques

Abstract The design of film cooling systems relies heavily on Reynolds-Averaged Navier-Stokes (RANS) simulations, which solve for mean quantities and model all turbulent scales. Most turbulent heat flux models, which are based on isotropic diffusion with a fixed turbulent Prandtl number (Prt), fail to accurately predict heat transfer in film cooling flows. In the present work, machine learning models are trained to predict a non-uniform Prt field, using various datasets as training sets. The ability of these models to generalize beyond the flows on which they were trained is explored. Furthermore, visualization techniques are employed to compare distinct datasets and to help explain the cross-validation results.

scholarly journals Generalization of Machine-Learned Turbulent Heat Flux Models Applied to Film Cooling Flows

2019 ◽  
Vol 142 (1) ◽  
Author(s):  
Pedro M. Milani ◽  
Julia Ling ◽  
John K. Eaton
Keyword(s):  
Heat Flux ◽  
Film Cooling ◽  
Cross Validation ◽  
Turbulent Heat Flux ◽  
Navier Stokes ◽  
Turbulent Heat ◽  
Turbulent Prandtl Number ◽  
Cooling Systems ◽  
Cooling Flows ◽  
Visualization Techniques

Abstract The design of film cooling systems relies heavily on Reynolds-averaged Navier–Stokes (RANS) simulations, which solve for mean quantities and model all turbulent scales. Most turbulent heat flux models, which are based on isotropic diffusion with a fixed turbulent Prandtl number (Prt), fail to accurately predict heat transfer in film cooling flows. In the present work, machine learning models are trained to predict a non-uniform Prt field using various datasets as training sets. The ability of these models to generalize beyond the flows on which they were trained is explored. Furthermore, visualization techniques are employed to compare distinct datasets and to help explain the cross-validation results.

Physical Interpretation of Machine Learning Models Applied to Film Cooling Flows

2018 ◽  
Vol 141 (1) ◽  
Author(s):  
Pedro M. Milani ◽  
Julia Ling ◽  
John K. Eaton
Keyword(s):  
Machine Learning ◽  
Film Cooling ◽  
Eddy Viscosity ◽  
Turbulent Heat Flux ◽  
Turbulent Heat ◽  
Cooling Flows ◽  
Gradient Diffusion ◽  
Accurate Temperature ◽  
Injection Region ◽  
Model Features

Current turbulent heat flux models fail to predict accurate temperature distributions in film cooling flows. The present paper focuses on a machine learning (ML) approach to this problem, in which the gradient diffusion hypothesis (GDH) is used in conjunction with a data-driven prediction for the turbulent diffusivity field αt. An overview of the model is presented, followed by validation against two film cooling datasets. Despite insufficiencies, the model shows some improvement in the near-injection region. The present work also attempts to interpret the complex ML decision process, by analyzing the model features and determining their importance. These results show that the model is heavily reliant of distance to the wall d and eddy viscosity νt, while other features display localized prominence.

Evaluation of a Machine Learning Turbulence Model in a Square Transverse Jet in Crossflow

2020 ◽  
Author(s):  
Fabíola Paula Costa ◽  
Rubén Bruno Díaz ◽  
Pedro M. Milani ◽  
Jesuíno Takachi Tomita ◽  
Cleverson Bringhenti
Keyword(s):  
Machine Learning ◽  
Heat Flux ◽  
Prandtl Number ◽  
Film Cooling ◽  
Computational Cost ◽  
Learning Model ◽  
Turbulent Heat Flux ◽  
Turbulent Heat ◽  
Turbulent Prandtl Number ◽  
Machine Learning Model

Abstract Film cooling is an important technique to ensure safe operation and performance fulfillment of turbines. Its ultimate goal is to protect the axial turbine blades from high gas temperatures. An appropriate study is necessary in order to obtain a reliable representation of the flow characteristics involved in such phenomena. Because of the high computational cost of high-fidelity simulations, the low-fidelity simulation method Reynolds Averaged Navier Stokes (RANS) is commonly used in practical configurations. However, the majority of the current turbulent heat flux models fail to accurately predict heat transfer in film cooling flows. Recent work suggests the use of machine learning models to improve turbulent closure in these flows. In the present work, a machine learning model for spatially varying turbulent Prandtl number previously described in the literature is applied to a transverse film cooling flow consisting of a jet square channel. The results obtained in the present work were compared to adiabatic effectiveness experimental data available in the literature to assess the performance of the machine learning model. The results shown that for low blowing ratios (BR = 0.2 and BR = 0.4) the proposed machine learning model has poor performance. However, for the case with the highest blowing ratio (BR = 0.8), the proposed model presented better results. These results are then explained in terms of the resulting turbulent Prandtl number field and suggest that the training set is not appropriate for capturing the turbulent heat flux in fully attached jets in crossflow.

Film Cooling From Novel Sister Shaped Single-Holes

2014 ◽  
Author(s):  
Siavash Khajehhasani ◽  
Bassam Jubran
Keyword(s):  
Film Cooling ◽  
Three Dimensional ◽  
Lateral Spreading ◽  
Navier Stokes ◽  
The Novel ◽  
Cooling Performance ◽  
Film Cooling Effectiveness ◽  
Blowing Ratio ◽  
Shaped Hole ◽  
Lift Off

A numerical investigation of the film cooling performance from novel sister shaped single-holes (SSSH) is presented in this paper and the obtained results are compared with a single cylindrical hole, a forward diffused shaped hole, as well as discrete sister holes. Three types of the novel sister shaped single-hole schemes namely downstream, upstream and up/downstream SSSH, are designed based on merging the discrete sister holes to the primary hole in order to reduce the jet lift-off effect and increase the lateral spreading of the coolant on the blade surface as well as a reduction in the amount of coolant in comparison with discrete sister holes. The simulations are performed using three-dimensional Reynolds-Averaged Navier Stokes analysis with the realizable k–ε model combined with the standard wall function. The upstream SSSH demonstrates similar film cooling performance to that of the forward diffused shaped hole for the low blowing ratio of 0.5. While it performs more efficiently at M = 1, where the centerline and laterally averaged effectiveness results improved by 70% and 17%, respectively. On the other hand, the downstream and up/downstream SSSH schemes show a considerable improvement in film cooling performance in terms of obtaining higher film cooling effectiveness and less jet lift-off effect as compared with the single cylindrical and forward diffused shaped holes for both blowing ratios of M = 0.5 and 1. For example, the laterally averaged effectiveness for the downstream SSSH configuration shows an improvement of approximately 57% and 110% on average as compared to the forward diffused shaped hole for blowing ratios of 0.5 and 1, respectively.

Leading Edge Film Cooling: Computations and Experiments Including Density Effects

1996 ◽  
Author(s):  
Pingfan He ◽  
Dragos Licu ◽  
Martha Salcudean ◽  
Ian S. Gartshore
Keyword(s):  
Experimental Data ◽  
Film Cooling ◽  
Stokes Equations ◽  
Leading Edge ◽  
Variable Density ◽  
Navier Stokes ◽  
Cooling Effectiveness ◽  
Stagnation Line ◽  
Film Cooling Effectiveness ◽  
Blowing Ratio

The effect of varying coolant density on film cooling effectiveness for a turbine blade-model was numerically investigated and compared with experimental data. This model had a semi-circular leading edge with four rows of laterally-inclined film cooling orifices positioned symmetrically about the stagnation line. A curvilinear coordinate-based CFD code was developed and used for the numerical investigation. The code used a domain segmentation strategy in conjunction with general curvilinear grids to model the complex blade configuration. A multigrid method was used to accelerate the convergence rate. The time-averaged, variable-density, Navier-Stokes equations together with the energy or scalar equation were solved. Turbulence closure was attained by the standard k–ε model with a near-wall k model. Either air or CO2 was used as coolant in three cases of injection through single rows and alternatively staggered double raws of holes. Two different blowing rates were investigated in each case and compared with experimental data. The experimental results were obtained using a wind tunnel model, and the mass/heat analogy was used to determine the film cooling effectiveness. The higher density of the carbon dioxide coolant (approximately 1.5 times the density of air) in the isothermal mass injection experiments, was used to simulate the effects of injection of a colder air in the corresponding adiabatic heat transfer situation. Good agreement between calculated and measured film cooling effectiveness was found for low blowing ratio M ≤ 0.5 and the effect of density was not significant. At higher blowing ratio M > 1 the calculations consistently overpredict the measured values of film cooling effectiveness.

Large Eddy Simulations of Film-Cooling Flows With a Micro-Ramp Vortex Generator

2011 ◽  
Author(s):  
Aaron F. Shinn ◽  
S. Pratap Vanka
Keyword(s):  
Film Cooling ◽  
Cross Flow ◽  
Vortex Generator ◽  
Vortex Pair ◽  
Large Eddy Simulations ◽  
Wind Tunnel Experiments ◽  
Cooling Effectiveness ◽  
Film Cooling Effectiveness ◽  
Cooling Flows ◽  
Large Eddy

Large Eddy Simulations were performed to study the effect of a micro-ramp on an inclined turbulent jet interacting with a cross-flow in a film-cooling configuration. The micro-ramp vortex generator is placed downstream of the film-cooling jet. Changes in vortex structure and film-cooling effectiveness are evaluated and the genesis of the counter-rotating vortex pair in the jet is discussed. Results are reported with the jet modeled using a plenum/pipe configuration. This configuration was designed based on previous wind tunnel experiments at NASA Glenn Research Center, and the present results are meant to supplement those experiments. It is found that the micro-ramp improves film-cooling effectiveness by generating near-wall counter-rotating vortices which help entrain coolant from the jet and transport it to the surface. The pair of vortices generated by the micro-ramp are of opposite sense to the vortex pair embedded in the jet.

Sign in / Sign up

Export Citation Format

Share Document