Nonlinear Identification Modeling for PCCI Engine Emissions Prediction Using Unsupervised Learning and Neural Networks 2020-01-0558
Premixed charged compression ignition (PCCI) is an advanced combustion strategy, which has the potential to achieve ultra-low nitrogen oxide and soot emissions at high thermal efficiencies. PCCI combustion is characterized by a complex nonlinear chemical-physical process, which indicates that a physical description involves significant development times and also high computation cost. This paper presents a method to use cylinder pressure data and engine operations parameters for prediction of PCCI engine emissions by unsupervised learning and nonlinear identification techniques. The proposed method first uses principal component analysis (PCA) to reduce the dimension of the cylinder-pressure data. Based on the PCA analysis, a multi-input multi-out model was developed for nitrogen oxide and soot emission prediction by multi-layer perceptron (MLP) neural network. Before the training process, a second principal component analysis was done to reduce the input dimension with hyper-parameters thereby reducing memory requirements of the models. The algorithm is applied to an experimental data set from a single-cylinder light-duty engine with piezo injection system. By comparing the model predictions with experimental results, it is shown that the neural network coupling with the unsupervised learning method can successfully capture the nonlinear relationship between the state parameters and the emissions of PCCI combustion system.
Citation: Pan, W., Korkmaz, M., Beeckmann, J., and Pitsch, H., "Nonlinear Identification Modeling for PCCI Engine Emissions Prediction Using Unsupervised Learning and Neural Networks," SAE Technical Paper 2020-01-0558, 2020, https://doi.org/10.4271/2020-01-0558. Download Citation
Wang Pan, Metin Korkmaz, Joachim Beeckmann, Heinz Pitsch
RWTH Aachen University
WCX SAE World Congress Experience
Combustion and combustion processes
Particulate matter (PM)
Subscribers can view annotate, and download all of SAE's content.
Learn More »