Machine learning for nano-scale particulate matter distribution from gasoline direct injection engine

Abstract

Predicting the amount of combustion generated nano-scale particulate matter (PM) emitted by gasoline direct injection (GDI) is a challenging task, but immensely useful for engine calibration engineers in order to meet the stringent emission legislation norms. The present work aimed to link the in-cylinder combustion with engine-out nano-scale PM for the size range of 23.7–1000nm diameter. Neural network with a single hidden layer using first 8 principal components of cylinder pressure was employed for training and predicting the number of nano-scale PM number count. Using a systematic computational approach and comparing its results with experimental data this work demonstrates that machine-learning approach based on neural network is sufficient for predicting engine out nano-scale PM count as a function of engine load and speed.