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).

A wide variety of spray models and their associated sub-models exist to assist with numerical spray development studies in the many applicable areas viz., turbines, internal combustion engines etc. The accuracy of a simulation when compared to the experiments varies, as these models chosen are varied. Also, the computational grid plays a crucial role in model correctness; a grid-converged CFD study is more valuable and assists in proper validation at later stages. Of primary relevance to this paper are the combustion models for a grid-converged Lagrangian spray modeling scenario. CONVERGE CFD code is used for simulation of split injection diesel (n-heptane) sprays and a structured methodology, using RNG k-ε turbulence model, is followed to obtain a grid-converged solution for the key Computational Fluid Dynamics (CFD) parameters viz., grid size, injected parcels and spray break-up time constant.