Search Results

This paper examines the combustion and emissions produced using a prototype fuel injector nozzle for pilot-ignited direct-injection natural gas engines. In the new geometry, 7 individual equally-spaced gas injection holes were replaced by 7 pairs of closely-aligned holes (“paired-hole nozzle”). The paired-hole nozzle was intended to reduce particulate formation by increasing air entrainment due to jet interaction. Tests were performed on a single-cylinder research engine at different speeds and loads, and over a range of fuel injection and air handling conditions. Emissions were compared to those resulting from a reference injector with equally spaced holes (“single-hole nozzle”). Contrary to expectations, the CO and PM emissions were 3 to 10 times higher when using the paired-hole nozzles. Despite the large differences in emissions, the relative change in emissions in response to parametric changes was remarkably similar for single-hole and paired-hole nozzles.

The emissions and efficiency of modern internal combustion engines need to be improved to reduce their environmental impact. Many strategies to address this (e.g., alternative fuels, exhaust gas aftertreatment, novel injection systems, etc.) require engine calibrations to be modified, involving extensive experimental data collection. A new approach to modeling and data collection is proposed to expedite the development of these new technologies and to reduce their upfront cost. This work evaluates a Gaussian Process Regression, Artificial Neural Network and Bayesian Optimization based strategy for the efficient development of machine learning models, intended for engine optimization and calibration. The objective of this method is to minimize the size of the required experimental data set and reduce the associated data collection cost for engine modeling.