This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Feasibility Study Of Neural Network Approach In Engine Management System In S.I. Engine
ISSN: 0148-7191, e-ISSN: 2688-3627
Published January 15, 2000 by SAE International in United States
Annotation ability available
As neural network approach has shown very encouraging results in different fields of engineering. The present work is an attempt to use the NN approach in engine management system to control the air fuel ratio and ignition timing with highest possible accuracy to meet the more and more stringent emission regulation. A feed-forward Neural network with one hidden layer has been used to predict the pulse width & ignition timing. Optimum number of hidden neurons and learning rate were observed to be 13 and 0.7 respectively. After training, the network was validated for 180 sample data and further cross-validated for about 400 data samples. The neural network output results show that the maximum absolute error for pulse width is 0.016 during validation and 0.050 during cross-validation. The analysis of the neural network output shows that the neural network has learn the input output data relations really well and is capable to predict the pulse width and ignition timing in the decided domain.
CitationKhatri, D. and Kumar, B., "Feasibility Study Of Neural Network Approach In Engine Management System In S.I. Engine," SAE Technical Paper 2000-01-1426, 2000, https://doi.org/10.4271/2000-01-1426.
- McCullochW.S., and PittsW., “A logical calculas of the idea Imminent in Nervous Activity”, Bulletin of Mathematical Biophysics, 5, 115-133, 1943.
- HebbD.O., The organisation of the behavior, John Willey&, New York, 1949
- Rosenblatt R., Principles of Neurodynamics, New York, Spartan Books 1959.
- WidrowB., and Hoff M.E., “Adaptive Switching circuits”, 1960 IRE WESCON Con, Record prt 4,96-104.
- HopfieldJ.J., Neural Networks and Physical Systems with Emergent Collective Computational Abilities”, Proc. Natl. Acad. Sci. USA, Vol.79, April 1982.
- HopfieldJ.J., “Neurons with Graded Response Have Collective Computational Properties Like Those of Two State Neurons”, Proc. Natl. Acad. Sci. USA, Vol. 81, May 1984
- HopfieldJ.J., and TankD.W.,“Computing With Neural Circuits: A Model Properties Like Those of Two State Neurons”, Proc. Natl. Acad. Sci. USA, Vol. 233, August 1986
- RumelhartD.E., and MeClelland J.I.,“Parallel Distributed Processing: Exploration in the microstructure of Cognition. Vol 1, MIT Press, 1986
- SejnowskiT. and RosenbergC.R., “NETtalk: A Parallel Network That Learns to Read Aloud,” John Hopkins University, Technical report JHU/EECS-86/01, 1986.
- FeldmanJ.A. and Ballard D.H.,“Connectionist Models and Their Properties”, Cognitive science Vol.6, 205-254,1982.
- GrossbergS., The Adaptive Brain I: Cognition, Learning, Reinforcement, and Rhythm, and Adaptive Brain II: Vision, Speech, Language, and Motor Control, Elsevier/North Holland, Amsterdam, 1986
- Hush, D.R. and HorneB.G., “Progressed in supervised neural networks: what is new since Lippmann? IEEE Signal Processing Magazine 10, 8-39, 1993