This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
A Machine Learning Approach to Information Extraction from Cylinder Pressure Sensors
Technical Paper
2012-01-0440
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
As the number of actuators and sensors increases in modern
combustion engines, the task of optimizing engine performance
becomes increasingly complex. Efficient information processing
techniques are therefore important, both for off-line calibration
of engine maps, and on-line adjustments based on sensor data.
In-cylinder pressure sensors are slowly spreading from
laboratory use to production engines, thus making data with high
temporal resolution of the combustion process available. The
standard way of using the cylinder pressure data for control and
diagnostics is to focus on a few important physical features
extracted from the pressure trace, such as the combustion phasing
CA50, the indicated mean effective pressure IMEP, and the ignition
delay. These features give important information on the combustion
process, but much information is lost as the information from the
high-resolution pressure trace is condensed into a few key
parameters.
The final objective of engine calibration and control is to
achieve low fuel consumption and emissions, and high reliability
and durability of the engine. In light of this objective, it is
proposed to approach the problem of extracting key features from
the cylinder pressure data in a more systematic way. Here, a method
is suggested to extract low-dimensional features from the
high-dimensional pressure data such that the information retained
is maximized. This leads to a principal component analysis
approach. It is shown that only a few components are required to
accurately describe the pressure trace.
The low-dimensional principal component coefficients are then
used as input to a neural network that can be trained to predict
engine outputs of interest. It is shown that NOx and λ can be
accurately predicted using the principal components coefficients
and the neural network. Benefits of the scheme during transients
are illustrated, where conventional sensors are too slow to provide
cycle-to-cycle measurements.
Recommended Content
Authors
Topic
Citation
Henningsson, M., Bernhardsson, B., Tunestal, P., and Johansson, R., "A Machine Learning Approach to Information Extraction from Cylinder Pressure Sensors," SAE Technical Paper 2012-01-0440, 2012, https://doi.org/10.4271/2012-01-0440.Also In
References
- Guzzella, L. Onder, C.H. Introduction to Modelling and Control of Internal Combustion Engine Systems Berlin Springer 2004
- Birch, S. “Audi diesel targets Bin 5, Euro 6,” Automotive Engineering International Online: SAE Technology Newsletter January 2008
- Pudenz, K. Audi Sportback Concept with Combustion Chamber Sensors for Lower Emissions ATZ online 2007
- General Motors GM takes new combustion technology out of the lab and on to the road, press release 2007 www.archives.media.gm.com
- Shahroudi, K.E. Robust Design Evolution and Impact of In-Cylinder Pressure Sensors to Combustion Control and Optimization: A Systems and Strategy Perspective Master's Thesis 1 Massachusetts Institute of Technology 2008
- Seykens, X. Baert, R. Somers, L. Willems, F. “Experimental Validation of Extended NO and Soot Model for Advanced HD Diesel Engine Combustion,” SAE Int. J. Engines 2 1 606 619 2009 10.4271/2009-01-0683
- Traver, M. Atkinson, R. Atkinson, C. “Neural Network-Based Diesel Engine Emissions Prediction Using In-Cylinder Combustion Pressure,” SAE Technical Paper 1999-01-1532 1999 10.4271/1999-01-1532
- Rizzoni, G. Methods and Apparatus for Performing Combustion Analysis in an Internal Combustion Engine Utilizing Ignition Voltage Analysis. 5,687,082 United States Patent 1997
- Malaczynski, G. Baker, M. “Real-Time Digital Signal Processing of Ionization Current for Engine Diagnostic and Control,” SAE Technical Paper 2003-01-1119 2003 10.4271/2003-01-1119
- Tunestål, P. Self Tuning Gross Heat Release Computation for Internal Combustion Engines Control Engineering Practice 2009 17 518 524
- Siemens Smart NOx Sensor 2005 www.siemensvdo.com
- Hayes, M. H. Statistical Digital Signal Processing and Modeling John Wiley & Sons, Inc. 1996
- Bishop, C. M. Pattern Recognition and Machine Learning New York Springer 2006
- Risvik, H. PCA Module 1.1.01 2008 www.folk.uio.no/henninri/pca_module
- Geladi, P. och Kowalski, B. R. Partial least-squares regression: A tutorial Analytica Chimica Acta. 1986 185 1 17
- Hastie, T. Tibshirani, R. Friedman, R. The Elements of Statistical Learning 1 Springer 2009
- Wojciechowski, M. Feed-foward Neural Network for Python (ffnet) August 2011 http://ffnet.sourceforge.net/ffnet-0.7