Reynolds-Averaged Turbulence Modeling Using Type I and Type II Machine Learning Frameworks with Deep Learning
نویسنده
چکیده
Deep learning (DL)-based Reynolds stress with its capability to leverage values of large data can be used to close Reynolds-averaged Navier-Stoke (RANS) equations. Type I and Type II machine learning (ML) frameworks are studied to investigate data and flow feature requirements while training DL-based Reynolds stress. The paper presents a method, flow features coverage mapping (FFCM), to quantify the physics coverage of DL-based closures that can be used to examine the sufficiency of training data points as well as input flow features for data-driven turbulence models. Three case studies are formulated to demonstrate the properties of Type I and Type II ML. The first case indicates that errors of RANS equations with DL-based Reynolds stress by Type I ML are accumulated along with the simulation time when training data do not sufficiently cover transient details. The second case uses Type I ML to show that DL can figure out time history of flow transients from data sampled at various times. The case study also shows that the necessary and sufficient flow features of DL-based closures are first-order spatial derivatives of velocity fields. The last case demonstrates the limitation of Type II ML for unsteady flow simulation. Type II ML requires initial conditions to be sufficiently close to reference data. Then reference data can be used to improve RANS simulation.
منابع مشابه
Modeling of Chloride Ion Separation by Nanofiltration Using Machine Learning Techniques
In this work, several machine learning techniques are presented for nanofiltration modeling. According to the results, specific errors are defined. The rejection due to Nanofiltration increases with pressure but decreases with increasing the concentration of chloride ion. Methods of machine learning represent the rejection of nanofiltration as a function of concentration, pH, pressure and also ...
متن کاملMachine learning algorithms in air quality modeling
Modern studies in the field of environment science and engineering show that deterministic models struggle to capture the relationship between the concentration of atmospheric pollutants and their emission sources. The recent advances in statistical modeling based on machine learning approaches have emerged as solution to tackle these issues. It is a fact that, input variable type largely affec...
متن کاملModeling and Multi-Objective Optimization of Stall Control on NACA0015 Airfoil with a Synthetic Jet using GMDH Type Neural Networks and Genetic Algorithms
This study concerns numerical simulation, modeling and optimization of aerodynamic stall control using a synthetic jet actuator. Thenumerical simulation was carried out by a large-eddy simulation that employs a RNG-based model as the subgrid-scale model. The flow around a NACA0015 airfoil, including a synthetic jet located at 10 % of the chord, is studied under Reynolds number Re = 12.7 × 106 a...
متن کاملComparison of different turbulence models in a high pressure fuel jet
In this study, modeling of a fuel jet which has been injected by high pressure into a low-pressure tank are investigated. Due to the initial conditions and the geometry of this case and similar cases (like CNG injectors in internal combustion engines (ICE)), the barrel shocks and Mach disk are observed. Hence a turbulence and transient flow will be expected with lots of shocks and waves. Accord...
متن کاملModeling Air Entrainment and Transport in a Hydraulic Jump using Two-Fluid RANS and DES Turbulence Models
Both RaNS (Reynolds-averaged Navier-Stokes) and DES (Detached Eddy Simulation) type turbulence models were used in conjunction with a two-fluid model of bubbly flow and a new subgrid air entrainment model to predict air entrainment and transport in a hydraulic jump. It was found that the void fraction profiles predicted by both methods are in agreement with the experimental data in the lower sh...
متن کامل