Search Results

A Machine Learning-Genetic Algorithm (ML-GA) approach was developed to virtually discover optimum designs using training data generated from multi-dimensional simulations. Machine learning (ML) presents a pathway to transform complex physical processes that occur in a combustion engine into compact informational processes. In the present work, a total of over 2000 sector-mesh computational fluid dynamics (CFD) simulations of a heavy-duty engine were performed. These were run concurrently on a supercomputer to reduce overall turnaround time. The engine being optimized was run on a low-octane (RON70) gasoline fuel under partially premixed compression ignition (PPCI) mode. A total of nine input parameters were varied, and the CFD simulation cases were generated by randomly sampling points from this nine-dimensional input space. These input parameters included fuel injection strategy, injector design, and various in-cylinder flow and thermodynamic conditions at intake valve closure (IVC).

For several years there has been a great deal of effort made in researching ways to run a compression ignition engine with simultaneously high efficiency and low emissions. Recently much of this focus has been dedicated to using gasoline-like fuels that are more volatile and less reactive than conventional diesel fuel to allow the combustion to be more premixed. One of the key challenges to using fuels with such properties in a compression ignition engine is stable engine operation at low loads. This paper provides an analysis of how stable gasoline compression ignition (GCI) engine operation was achieved down to idle speed and load on a multi-cylinder compression ignition engine using only 87 anti-knock index (AKI) gasoline. The variables explored to extend stable engine operation to idle included: uncooled exhaust gas recirculation (EGR), injection timing, injection pressure, and injector nozzle geometry.