Large-Eddy Simulation (LES) of Spray Transients: Start and End of Injection Phenomena

This work reports investigations on Diesel spray transients, accounting for internal nozzle flow and needle motion, and demonstrates how seamless calculations of internal flow and external jet can be accomplished in a Large-Eddy Simulation (LES) framework using an Eulerian mixture model. Sub-grid stresses are modeled with the Dynamic Structure (DS) model, a non-viscosity based one-equation LES model. Two problems are studied with high level of spatial and temporal resolution. The first one concerns an End-Of-Injection (EOI) case where gas ingestion, cavitation, and dribble formation are resolved. The second case is a Start-Of-Injection (SOI) simulation that aims at analyzing the effect of residual gas trapped inside the injector sac on spray penetration and rate of fuel injection. Simulation results are compared against experiments carried out at Argonne National Laboratory (ANL) using synchrotron X-ray. A mesh sensitivity analysis is conducted to assess the quality of the LES approach by evaluating the resolved turbulent kinetic energy budget and comparing the outcomes with a length-scale resolution index. LES of both EOI and SOI processes have been carried out on a single hole Diesel injector, providing insights in to the physics of the processes, with internal and external flow details, and linking the phenomena at the end of an injection event to those at the start of a new injection. Concerning the EOI, the model predicts ligament formation and gas ingestion, as observed experimentally, and the amount of residual gas in the nozzle sac matches with the available data. The fast dynamics of the process is described in detail. The simulation provides unique insights into the physics at the EOI. Similarly, the SOI simulation shows how gas is ejected first, and liquid fuel starts being injected with a delay. The simulation starts from a very low needle lift and is able to predict the actual Rate-Of-Injection (ROI) and jet penetration, based only on the prescribed needle motion. Finally, guidelines and future improvements of the model are discussed concerning the simulation of the transient injection phases.