This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Misfire Detection Using a Dynamic Neural Network with Output Feedback
Annotation ability available
Sector:
Language:
English
Abstract
This paper presents a crankshaft speed fluctuation model based dynamic neural network misfire detection method to achieve high detection performance and compact network size. In this method, a dynamic neural network with output feedback is utilized to model an inverse system from the engine crankshaft speed signal to the firing event signal. The engine misfire detection is based on the output of the inverse system given the input of engine speed signal. Test results for a 4-cylinder engine show its promising capability of misfire detection even for the low sampling rate data under various engine operating conditions and misfire patterns.
Recommended Content
Topic
Citation
Wu, Z. and Lee, A., "Misfire Detection Using a Dynamic Neural Network with Output Feedback," SAE Technical Paper 980515, 1998, https://doi.org/10.4271/980515.Also In
References
- Narenda K.S. Parthasarathy K. “Identification and control of dynamic systems using neural networks,” IEEE Transactions on Neural Networks 1 4 27 March 1990
- Hush D.R. Horne B.G. “Progress in supervised neural networks,” IEEE signal processing Magazine 8 39 January 1993
- Narenda K.S. “Neural networks for control: theory and practice,” Proceedings of the IEEE 84 10 1385 1407 Oct. 1996
- Oppenheim A. Schafer R. W. Digital SignalProcessing Prentice-Hall Englewood Cliffs, NJ 1975
- Williams J. “An overview of misfiring cylinder engine diagnostic techniques based on crankshaft angular velocity measurements,” SAE paper No. 960039 Feb. 1996
- Reyna E. Specht D.F. Lee A. “Small, fast runtime modules for probabilistic neural networks” 1995 IEEE International Conference on Neural Networks Proceedings 1 304 308 Dec. 1995
- Ribbens W.B. Steven Bieser “Advanced signal processing for misfire detection in automotive engines,” Proc. IEEE international Conf. Acoustic, Speech, and Signal Processing (ICASSP) 2963 2966 Detroit May 1995