Design Space Exploration of Turbulent Multiphase Flows Using Machine Learning-Based Surrogate Model
Open Access
Abstract
This study focuses on establishing a surrogate model based on machine learning techniques to predict the time-averaged spatially distributed behaviors of vaporizing liquid jets in turbulent air crossflow for momentum flux ratios between 5 and 120. This surrogate model extends a previously developed Gaussian-process-based framework applicable to laminar flows to accommodate turbulent flows and demonstrates that in addition to detailed fields of primitive variables, second-order turbulence statistics can also be predicted using machine learning techniques. The framework proceeds in 3 steps—(1) design of experiment studies to identify training points and conducting high-fidelity calculations to build the training dataset; (2) Gaussian process regression (supervised training) for the range of operating conditions under consideration for gaseous and dispersed phase quantities; and (3) error quantification of the surrogate model by comparing the machine learning predictions with the truth model for test conditions (i.e., conditions not used for training). The framework was trained using data generated by high-fidelity large eddy simulation (LES)-based calculations (also referred to as the truth model), which solves the complete set of conservation equations for mass, momentum, energy, and species in an Eulerian reference frame, coupled with a Lagrangian solver that tracks the dispersed phase. Simulations were conducted for the range of momentum flux ratios between 5 and 120 for liquid water injected into crossflowing air at a pressure of 1 atm and temperature of 600 K. Results from the machine-learned surrogate model, also called emulations, were compared with the truth model under testing conditions identified by momentum flux ratios of 7 and 40. L1 errors for time-averaged field quantities, including velocity magnitudes, pressure, temperature, vapor fraction of the evaporated liquid, and turbulent kinetic energy in the gas phase, and spray penetration and Sauter mean diameters in the dispersed phase are reported. Speedup of 65 was achieved with this emulator when compared against LES simulation of the same test conditions with errors for all quantities below 14%, thus demonstrating the potential benefits of using machine learning techniques for design space exploration of devices that are based on turbulent multiphase fluid flows. This is the first effort of its kind in the literature that demonstrates the application of machine learning techniques on turbulent multiphase flows.Keywords
This publication has 39 references indexed in Scilit:
- A large eddy simulation of the breakup and atomization of a liquid jet into a cross turbulent flow at various spray conditionsInternational Journal of Heat and Mass Transfer, 2017
- Liquid jet in a subsonic gaseous crossflow: Recent progress and remaining challengesProgress in Energy and Combustion Science, 2016
- A Large-Eddy-Simulation Study of Combustion Dynamics of Bluff-Body Stabilized FlamesCombustion Science and Technology, 2015
- Liquid Jets in Subsonic Air Crossflow at Elevated PressureJournal of Engineering for Gas Turbines and Power, 2014
- Physical modelling and advanced simulations of gas–liquid two-phase jet flows in atomization and spraysProgress in Energy and Combustion Science, 2010
- Primary Breakup of Turbulent Round Liquid Jets in Uniform CrossflowsAIAA Journal, 2007
- Large-Eddy Simulation of Realistic Gas Turbine CombustorsAIAA Journal, 2006
- A MODEL FOR NUMERICAL SIMULATION OF BREAKUP OF A LIQUID JET IN CROSSFLOWAtomization and Sprays, 2003
- Investigation of a Liquid Jet in a Subsonic Cross-FlowInternational Journal of Fluid Mechanics Research, 1997
- Toward the large-eddy simulation of compressible turbulent flowsJournal of Fluid Mechanics, 1992