Diesel Combustion Parameter Estimation via Machine Learning – A Comparative Study

This paper presents an analysis of distinct approaches for data-driven combustion parameter estimation for Diesel engines. Thereby, characteristic quantities are modeled by a set of selected regression models, and via a convolutional neural network (CNN). While the former use settings from the Engine Control Unit (ECU) as input, the latter works by processing the raw crankshaft vibration signal. The central point of this study is a broad evaluation of data-driven modeling for Diesel combustion. This includes whether using a signal recorded from individual combustion cycles achieves better representation of the target values than using ECU settings which cannot reflect unforeseeable, stochastic phenomena within the combustion chamber. This was evaluated by assessing predictions of six combustion characteristics: CA10, CA50, CA90, Peak-Firing-Pressure (PFP), Combustion Duration (CD), and Ignition Delay (ID). In two series of experiments it is established that individual cycle data processed via a CNN does not provide an advantage over feature-based machine learning using operation parameters. Furthermore, Support Vector Regression and Partial Least Squares are found to produce estimates of satisfactory quality when making predictions over varied conditions within a single operating point, or extrapolating to an entirely unseen operating point.