Modeling the Dynamic Coupling of Internal Nozzle Flow and Spray Formation for Gasoline Direct Injection Applications

Abstract

A numerical study has been carried out to assess the effects of needle movement and internal nozzle flow on spray formation for a multi-hole Gasoline Direct Injection system. The coupling of nozzle flow and spray formation is dynamic in nature and simulations with pragmatic choice of spatial and temporal resolutions are needed to analyze the sprays in a GDI system. The dynamic coupling of nozzle flow and spray formation will be performed using an Eulerian-Lagrangian Spray Atomization (ELSA) approach. In this approach, the liquid fuel will remain in the Eulerian framework while exiting the nozzle, while, depending on local instantaneous liquid concentration in a given cell and amount of liquid in the neighboring cells, part of the liquid mass will be transferred to the Lagrangian framework in the form of Lagrangian parcels. Such approach requires solving an additional transport equation apart from the conservation equations of mass, momentum, species, energy, and turbulence in Eulerian framework. This additional equation is termed as the Σ equation. Σ represents the liquid-gas interfacial area per unit volume in a given computational cell. Once the liquid mass is transferred to the Lagrangian framework, parcels undergo breakup, collision, coalescence and evaporation, similar to any typical Lagrangian spray approach. This hybrid approach will have the potential of capturing the transient flow characteristics due to needle movement transcending downstream and affecting time-fluctuating spray phenomenon. The Spray G condition from the Engine Combustion Network (ECN) has been chosen for this study. Parametric studies on the effect of turbulence models, Eulerian to Lagrangian mass transfer criterion, breakup models have been performed. While these simulations are very expensive, they are expected to be more predictive than the standing approach of initializing a Lagrangian simulation with a ‘blob’ injection model. Simulation predictions with ELSA are shown to be in good agreement with measured data on spray penetration, and gas velocities, available in the literature.