EVENT DETECTION IN MULTI-VARIATE SCIENTIFIC SIMULATIONS USING FEATURE ANOMALY METRICS
Abstract not provided.
Publications
A machine learning approach for determining the turbulent diffusivity in film cooling flows
Journal of Turbomachinery
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 Reynoldsaveraged 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.
K-ε Turbulence Model Parameter Estimates Using an Approximate Self-similar Jet-in-Crossflow Solution
AIAA Journal
The k-ε turbulence model has been described as perhaps “the most widely used complete turbulence model.” This family of heuristic Reynolds Averaged Navier-Stokes (RANS) turbulence closures is supported by a suite of model parameters that have been estimated by demanding the satisfaction of well-established canonical flows such as homogeneous shear flow, log-law behavior, etc. While this procedure does yield a set of so-called nominal parameters, it is abundantly clear that they do not provide a universally satisfactory turbulence model that is capable of simulating complex flows. Recent work on the Bayesian calibration of the k-ε model using jet-in-crossflow wind tunnel data has yielded parameter estimates that are far more predictive than nominal parameter values. In this paper, we develop a self-similar asymptotic solution for axisymmetric jet-in-crossflow interactions and derive analytical estimates of the parameters that were inferred using Bayesian calibration. The self-similar method utilizes a near field approach to estimate the turbulence model parameters while retaining the classical far-field scaling to model flow field quantities. Our parameter values are seen to be far more predictive than the nominal values, as checked using RANS simulations and experimental measurements. They are also closer to the Bayesian estimates than the nominal parameters. A traditional simplified jet trajectory model is explicitly related to the turbulence model parameters and is shown to yield good agreement with measurement when utilizing the analytical derived turbulence model coefficients. Finally, the close agreement between the turbulence model coefficients obtained via Bayesian calibration and the analytically estimated coefficients derived in this paper is consistent with the contention that the Bayesian calibration approach is firmly rooted in the underlying physical description.
K-ε Turbulence Model Parameter Estimates Using an Approximate Self-similar Jet-in-Crossflow Solution
Abstract not provided.
Machine Learning Models of Errors in LES Predictions of Surface Pressure Fluctuations
Abstract not provided.
Machine Learning Models of Errors in Large Eddy Simulation Predictions of Surface Pressure Fluctuations
Abstract not provided.
Convolutional Neural Networks for Frequency Response Predictions
Abstract not provided.
Investigating Turbulent Wall Pressure Fluctuations using Machine Learning Techniques
Abstract not provided.
Data-driven Adaptive Physics Modeling for Turbulence Simulations
Abstract not provided.
Data-driven Adaptive Physics Modeling for Turbulence Simulations
Abstract not provided.
Using Feature Importance Metrics to Detect Events of Interest in Scientific Computing Applications
Abstract not provided.
Machine Learning + Physics
Abstract not provided.
Machine Learning + Physics
Abstract not provided.
Deep Learning for Turbulence Modeling
Abstract not provided.
A comparative study of contrasting machine learning frameworks applied to rans modeling of jets in crossflow
Proceedings of the ASME Turbo Expo
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.
Visualization of High Dimensional Turbulence Simulation Data using t-SNE
Abstract not provided.
Development of machine learning models for turbulent wall pressure fluctuations
AIAA SciTech Forum - 55th AIAA Aerospace Sciences Meeting
In many aerospace applications, it is critical to be able to model fluid-structure interactions. In particular, correctly predicting the power spectral density of pressure fluctuations at surfaces can be important for assessing potential resonances and failure modes. Current turbulence modeling methods, such as wall-modeled Large Eddy Simulation and Detached Eddy Simulation, cannot reliably predict these pressure fluctuations for many applications of interest. The focus of this paper is on efforts to use data-driven machine learning methods to learn correction terms for the wall pressure fluctuation spectrum. In particular, the non-locality of the wall pressure fluctuations in a compressible boundary layer is investigated using random forests and neural networks trained and evaluated on Direct Numerical Simulation data.
Development of Machine Learning Models for Turbulent Wall Pressure Fluctuations
Abstract not provided.
Machine Learning for Turbulence Modeling: Embedding Invariance Properties
Abstract not provided.
Evaluating RANS Assumptions
Abstract not provided.
Feature Importance
Abstract not provided.
Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
Journal of Fluid Mechanics
There exists significant demand for improved Reynolds-Averaged Navier-Stokes (RANS) turbulence models that are informed by and can represent a richer set of turbulence physics. This paper presents a method of using deep neural networks to learn a model for the Reynolds stress anisotropy tensor from high-fidelity simulation data. A novel neural network architecture is proposed which uses a multiplicative layer with an invariant tensor basis to embed Galilean invariance into the predicted anisotropy tensor. It is demonstrated that this neural network architecture provides improved prediction accuracy compared with a generic neural network architecture that does not embed this invariance property. The Reynolds stress anisotropy predictions of this invariant neural network are propagated through to the velocity field for two test cases. For both test cases, significant improvement versus baseline RANS linear eddy viscosity and nonlinear eddy viscosity models is demonstrated.
A Comparative Study of Contrasting Machine Learning Frameworks Applied to RANS Modeling of Jets in Crossflow
Abstract not provided.
A Machine Learning Approach for Determining the Turbulent Diffusivity in Film Cooling Flows
Abstract not provided.
Using Tensor Theory to Embed Invariances: A Case Study from Turbulence Modeling
Abstract not provided.
Results 1–25 of 56