The combustion system of a heavy-duty diesel engine operated in a gasoline compression ignition mode was optimized using a CFD-based response surface methodology and a machine learning genetic algorithm. One common dataset obtained from a CFD design of experiment campaign was used to construct response surfaces and train machine learning models. 128 designs were included in the campaign and were evaluated across three engine load conditions using the CONVERGE CFD solver. The design variables included piston bowl geometry, injector specifications, and swirl ratio, and the objective variables were fuel consumption, criteria emissions, and mechanical design constraints. In this study, the two approaches were extensively investigated and applied to a common dataset. The response surface-based approach utilized a combination of three modeling techniques to construct response surfaces to enhance the performance of predictions. The machine learning-genetic algorithm optimization strategy adopted an active learning approach. Its training and prediction accuracies were significantly improved by combining the datasets from three different loads into one single training dataset. Both methodologies generated designs that performed better than the optimal CFD-DoE design, with improved weighted average merit values 6% above the baseline.
Machine Learning and Response Surface-Based Numerical Optimization of the Combustion System for a Heavy-Duty Gasoline Compression Ignition Engine
Sae Technical Papers
SAE WCX Digital Summit ; 2021
2021-04-06
Conference paper
English
SAE Technical Papers | 2011
|EGR System Optimization for Light-Duty Gasoline Compression Ignition (GCI) Engine
SAE Technical Papers | 2021
|British Library Conference Proceedings | 2011
|Gasoline Compression Ignition Operation of a Heavy-Duty Engine at High Load
SAE Technical Papers | 2018
|