This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Robust AFR Estimation Using the Ion Current and Neural Networks
ISSN: 0148-7191, e-ISSN: 2688-3627
Published March 1, 1999 by SAE International in United States
Annotation ability available
A robust air/fuel ratio “soft sensor” is presented based on non-linear signal processing of the ion current signal using neural networks. Care is taken to make the system insensitive to amplitude variations, due to e.g. fuel additives, by suitable preprocessing of the signal.
The algorithm estimates the air/fuel ratio to within 1.2% from the correct value, defined by a universal exhaust gas oxygen (UEGO) sensor, when tested on steady state test-bench data and using the raw ion current signal. Normalizing the ion current increases robustness but also increases the error by a factor of two.
The neural network soft sensor is about 20 times better in the case where the ion current is not normalized, compared with a linear model. On normalized ion currents the neural network model is about 4 times better than the corresponding linear model.
CitationHellring, M., Munther, T., Rögnvaldsson, T., Wickström, N. et al., "Robust AFR Estimation Using the Ion Current and Neural Networks," SAE Technical Paper 1999-01-1161, 1999, https://doi.org/10.4271/1999-01-1161.
Electronic Engine Controls 1999: Neural Networks, Diagnostic and Electronic Hardware, and Controls
Number: SP-1419; Published: 1999-03-01
Number: SP-1419; Published: 1999-03-01
- Heywood, J. B. Internal Combustion Engine Fundamentals. McGraw-Hill, 1988.
- Andersson. M. J., A feedback A/F control system for low emission vehicles. Technical paper 930388, Society of Automotive Engineers (SAE), 1993.
- Bush, K. J., Adams N. J., Dua S., and Markyvech C. R.. Automatic control of cylinder by cylinder air-fuel mixture using a proportional exhaust gas sensor. Technical paper 940194, Society of Automotive Engineers (SAE), 1994.
- Hasegawa, Y., Akazaki S., Komoryia I., Maki H., Nishimura Y., and Hirota T.. Individual cylinder air-fuel ratio feedback control using an observer. Technical paper 940376, Society of Automotive Engineers (SAE), 1994.
- An, F., Rizzoni G., and Upadhay D.. Combustion diagnostics in methane-fueled SI engines using the spark plug as an ionization probe. Technical paper 970033, Society of Automotive Engineers (SAE), 1997.
- Reinmann, R., Saitzkoff A., and Mauss F.. Local air-fuel ratio measurements using the spark plug as an ionization sensor. Technical paper 970856, Society of Automotive Engineers (SAE), 1997.
- Wickström, N., Taveniku M., Linde A., Larsson M., and Svensson B.. Estimating pressure peak position and air-fuel ratio using the ionization current and artificial neural networks. In Proceedings of IEEE Conference on Intelligent Transportation Systems (ITSC'97), Boston, November 9-12, 1997.
- Upadhyay, D., and Rizzoni G.. AFR control on a single cylinder engine using the ionization current. Technical paper 980203, Society of Automotive Engineers (SAE), 1998.
- Wickström, N., Linde A., Larsson M., and Svensson B.. Neural virtual sensors - estimation of combustion quality in SI engines using the spark plug. In Proceedings of the International Conference on Artificial Neural Networks (ICANN 98), Sköve, September 2-4, 1998.
- Reinmann, R., Saitzkoff A., Lassesson B., and Strandh P.. Fuel and additive influence on the ion current. Technical paper 980161, Society of Automotive Engineers (SAE), 1998.
- Gillbrand, P., Johansson H., and Nytomt J.. Method and apparatus for detecting ion current in an internal combustion engine ignition system. U. S. Patent No. 4,648,367, 1987.
- Auzins, J., Johansson H., and Nytomt J.. Ion-gap sense in misfire detection, knock and engine control. Technical paper 950004, Society of Automotive Engineers (SAE), 1995.
- Johnson, R., and Wichern D.. Applied Multivariate Statistical Analysis, 4/e. Prentice-Hall, 1998.
- Haykin, S. Neural Networks - A Comprehensive Foundation. IEEE Press, 1994.
- Riedmiller, M. and Braun H.. A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In Proceedings of the IEEE International Conference on Neural Networks, San Francisco, CA, March 28-April 1, 1993.
- Sarle, W.S., “Stopped training and other remedies for over-fitting”. In Proceedings of the 27:th Symposium on the Interface of Computing Science and Statistics, 1995.
- Pi, H., and Peterson C.. Finding the embedding dimension and variable dependencies in time series. Neural Computation 6: pp. 509-520, 1994.