NOx Virtual Sensor Based on Structure Identification and Global Optimization
Published April 11, 2005 by SAE International in United States
Annotation of this paper is available
On-line measurement of engine NOx emissions is the object of a substantial effort, as it would strongly improve the control of CI engines. Many efforts have been directed towards hardware solutions, in particular to physical sensors, which have already reached a certain degree of maturity.
In this paper, we are concerned with an alternative approach, a virtual sensor, which is essentially a software code able to estimate the correct value of an unmeasured variable, thus including in some sense an input/output model of the process. Most virtual sensors are either derived by fitting data to a generic structure (like an artificial neural network, ANN) or by physical principles. In both cases, the quality of the sensor tends to be poor outside the measured values. In this paper, we present a new approach: the data are screened for hidden analytical structures, combining structure identification and evolutionary algorithms, and these structures are then used to develop the sensor presented. While the computational time for the sensor design can be significant (e.g. 1 or more hours), the resulting formula is very compact and proves able to predict the behaviour of the system at other operating points.
The method has been validated with NOx data from a production engine measured with a Horiba Mexa 7000. The approach is able to yield a good prediction behaviour over a whole cycle. The results are consistent with physical knowledge.
- Luigi del Re - Institute of Design and Control of Mechatronic Systems, Johannes Kepler University Linz
- Peter Langthaler - Institute of Design and Control of Mechatronic Systems, Johannes Kepler University Linz
- Christian Furtmueller - Institute of Design and Control of Mechatronic Systems, Johannes Kepler University Linz
- Stephan Winkler - Institute for Formal Models and Verification, Johannes Kepler University Linz
- Michael Affenzeller - Institute for Formal Models and Verification, Johannes Kepler University Linz
Citationdel Re, L., Langthaler, P., Furtmueller, C., Winkler, S. et al., "NOx Virtual Sensor Based on Structure Identification and Global Optimization," SAE Technical Paper 2005-01-0050, 2005, https://doi.org/10.4271/2005-01-0050.
- Heywood J.B., “Internal combustion engine fundamentals”, Mc Graw Hill, 1988
- Chikahisa T., Konno M., Murayama T., Analysis of NO formation characteristics and control concepts on diesel engines from NO reaction kinetic considerations, SAE Paper 950215
- Zeldovich Y. A., The Oxidation of Nitrogen in Combustion and Explosions, Acta Physicochim. USSR 21: pp. 577-628, 1946
- Lavoie G.A., Heywood J.B., KeckJ.C., Experimental and Theoretical Investigation of Nitric Oxide Formation in Internal Combustion Engines, Combust. Sci. Technol. 1: pp. 313-326, 1975
- Miller J.A., Bowman C.T., Mechanism and Modeling of Nitrogen Chemistry in Combustion, Prog. Energy Combust. Sci. 15: pp. 287-338, 1989
- Wolfrum J., Bildung von Stickstoffoxiden bei der Verbrennung, Chemie Ing. Technik 44: pp. 656-659, 1972
- Fenimore C. P., Formation of Nitric Oxide in Premixed Hydrocarbon Flames, 13th Symp. Int. Combust.: pp. 373-379, 1971
- Arsie I., Pianese C., Rizzo G., Enhancement of control oriented engine models using neural network, Proceedings of the 6th Mediterranean Conference on Theory and Practice of Control Systems, p 465-471, 1998
- Gärtner U., Die Simulation der Stickoxid-Bildung in Nutzfahrzeug-Dieselmotoren, Dissertation TU Darmstadt, 2001
- Arsie I., Pianese C., Rizzo G., Identification of Emission Models in a Spark Ignition Engine for Control Applications. Proc. of 5th IEEE Mediterranean Conference on Control and Systems, Paphos (Cyprus), July 21-23 1997
- Ljung L., System Identification, Theory for the User, 1995
- Akaike H., “A new look at the statistical model identification”, IEEE Transactions on Automatic Control, Vol, AC-19, n. 6, December 1974
- Zheng G.L. and Billings S.A., “Effects of overparametrization in non-linear system identification and neural networks”, International-Journal-of-Systems-Science. 15 April 2002; 33(5): 331-49.]
- del Re L., et al, Fast model prototyping for control and fault detection, Strategic Project 4.3, Report, LCM GmbH Linz, 2004, available through mechsys.mechatronik.uni-linz.ac.at
- Reeves S. J., Zhe Zhao, Sequential Algorithms for Observation Selection, IEEE Transactions on Signal Processing, vol. 47, N.1, January 1999, 123-132
- Winkler S., Affenzeller M., Wagner S., “Identifying Nonlinear Model Structures Using Genetic Programming Techniques”, Cybernetics and Systems 2004, pp. 689-694, Austrian Society for Cybernetic Studies, 2004.
- Winkler S., Affenzeller M., Wagner S., “New Methods for the Identification of Nonlinear Model Structures Based Upon Genetic Programming Techniques”, Proceedings of the 15th International Conference on Systems Science, vol. 1, pp. 386-393, Oficyna Wydawnicza Politechniki Wroclawskiej, 2004.
- Affenzeller M., Wagner S., “SASEGASA: A New Generic Parallel Evolutionary Algorithm for Achieving Highest Quality Results”, Journal of Heuristics - Special Issue on New Advances on Parallel Meta-Heuristics for Complex Problems, vol. 10, pp. 239-263, Kluwer Academic Publishers, 2004.
- Wagner S., Affenzeller M., “HeuristicLab: A Generic and Extensible Optimization Environment”, accepted to be published in: Proceedings of the International Conference on Adaptive and Natural Computing Algorithms (ICANNGA) 2005.