Advanced

A Virtual Sensor for Predicting Diesel Engine Emissions from Cylinder Pressure Data

Henningsson, Maria LU ; Tunestål, Per LU and Johansson, Rolf LU (2012) 2012 IFAC Workshop on Engine and Powertrain Control, Simulation and Modeling (E-COSM'12) In 2012 IFAC Workshop on Engine and Powertrain Control, Simulation and Modeling p.424-431
Abstract
Cylinder pressure sensors provide detailed information on the diesel engine combustion process. This paper presents a method to use cylinder-pressure data for prediction of engine emissions by exploiting data-mining techniques. The proposed method uses principal component analysis to reduce the dimension of the cylinder-pressure data, and a neural network to model the nonlinear relationship between the cylinder pressure and emissions. An algorithm is presented for training the neural network to predict cylinder-individual emissions even though the training data only provides cylinder-averaged target data. The algorithm was applied to an experimental data set from a six-cylinder heavy-duty engine, and it is verified that trends in emissions... (More)
Cylinder pressure sensors provide detailed information on the diesel engine combustion process. This paper presents a method to use cylinder-pressure data for prediction of engine emissions by exploiting data-mining techniques. The proposed method uses principal component analysis to reduce the dimension of the cylinder-pressure data, and a neural network to model the nonlinear relationship between the cylinder pressure and emissions. An algorithm is presented for training the neural network to predict cylinder-individual emissions even though the training data only provides cylinder-averaged target data. The algorithm was applied to an experimental data set from a six-cylinder heavy-duty engine, and it is verified that trends in emissions during transient engine operation are captured successfully by the model. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
2012 IFAC Workshop on Engine and Powertrain Control, Simulation and Modeling
pages
424 - 431
publisher
IFAC
conference name
2012 IFAC Workshop on Engine and Powertrain Control, Simulation and Modeling (E-COSM'12)
external identifiers
  • scopus:84881009518
ISSN
1474-6670
ISBN
978-3-902823-16-8
DOI
10.3182/20121023-3-FR-4025.00063
project
Competence Centre for Combustion Processes
language
English
LU publication?
yes
id
9b0d152b-e6ed-4ce2-8a68-e157d901c718 (old id 3404642)
date added to LUP
2013-06-12 09:19:42
date last changed
2017-09-10 04:18:21
@inproceedings{9b0d152b-e6ed-4ce2-8a68-e157d901c718,
  abstract     = {Cylinder pressure sensors provide detailed information on the diesel engine combustion process. This paper presents a method to use cylinder-pressure data for prediction of engine emissions by exploiting data-mining techniques. The proposed method uses principal component analysis to reduce the dimension of the cylinder-pressure data, and a neural network to model the nonlinear relationship between the cylinder pressure and emissions. An algorithm is presented for training the neural network to predict cylinder-individual emissions even though the training data only provides cylinder-averaged target data. The algorithm was applied to an experimental data set from a six-cylinder heavy-duty engine, and it is verified that trends in emissions during transient engine operation are captured successfully by the model.},
  author       = {Henningsson, Maria and Tunestål, Per and Johansson, Rolf},
  booktitle    = {2012 IFAC Workshop on Engine and Powertrain Control, Simulation and Modeling},
  isbn         = {978-3-902823-16-8},
  issn         = {1474-6670},
  language     = {eng},
  pages        = {424--431},
  publisher    = {IFAC},
  title        = {A Virtual Sensor for Predicting Diesel Engine Emissions from Cylinder Pressure Data},
  url          = {http://dx.doi.org/10.3182/20121023-3-FR-4025.00063},
  year         = {2012},
}