This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Engine Knock Estimation Using Neural Networks Based on a Real-World Database
Annotation ability available
Sector:
Language:
English
Abstract
In this paper we present an advanced knock detection approach. The detection concept consists of a two-level feature extraction step followed by neural network detector. A knock tendency index is estimated that takes into account the statistical behavior of the knock phenomena. The configuration of the neural network is based on a signal database that was acquired under almost ‘on-road’ conditions. The experimental set-up consisted of several measurement sessions in a special vehicle test cell. In order to achieve a most realistic knock database the test engine was mounted on an in-production car.
Recommended Content
Authors
Citation
Ortmann, S., Rychetsky, M., Glesner, M., Groppo, R. et al., "Engine Knock Estimation Using Neural Networks Based on a Real-World Database," SAE Technical Paper 980513, 1998, https://doi.org/10.4271/980513.Also In
References
- Checkel M.D. Dale J.D. Computerized knock detection from engine pressure records SAE Techn. Paper 860028
- Kaneyasu M. et al. Engine knock detection using multispectrum method SAE Techn. Paper 920702
- Samimy B. Rizzoni G. Engine knock analysis and detection using time frequency analysis SAE Techn. Paper 960618
- Horner T.G. Knock detection using spectral analysis techniques on a Texas Instrument TMS320 DSP SAE Techn. Paper 960614
- Krichel W. 1990 RWTH Aachen
- Härle N. Analyse VDI Verlag, Reihe, Nr. 113 1989
- Rychetsky M. Ortmann S. Glesner M. Application of hierarchical mixtures of experts networks to engine knock detection In Proceedings of EUFIT '97 1714 1718 Sept. 1997 Aachen
- Groppo R. Ortmann S. et al. FILU: A Digital Filter Unit for Automotive Signal Conditioning Proceedings of the Internation Embedded System Conference 101 112 Sept. 1996 Berlin
- Ortmann S. Rychetsky M. Glesner M. Groppo R. Engine Knock Detection using Multi-Feature Classification by means of Non-Linear Mapping In Procedings of ISATA 97 607 613 Juni 1997 Florence
- Ortmann S. Glesner M. Workshop Fuzzy-Neuro Systems 162 169 1997 Soest
- Fahlman S. The Cascade-Correlation Learning Architecture CMU-CS-90-100 Report Carnegie Mellon University Pittsburgh 1990
- Baluja S. Fahlman S. Reducing Network Depth in the Cascade-Correlation Learning Architecture CMU-CS-94-209 Report Carnegie Mellon University Pittsburgh 1994
- Jordan, Jacobs R. Hierarchies of adaptive experts Moody J. Hanson S. Lippmann R. Advances in Neural Information Processing 4 San Mateo CA: Morgan Kaufmann 985 993 1992
- Mozer M.C. Smolensky P. Skeletonization: A technique for trimming the fat from a neural network via relevance assesment 107 115 D.S. Touretzky: Advances in Neural Information Processing Systems (NIPS) 1 Morgan Kaufman Publishers Inc. San Mateo 1989
- Fukunaga K. Statistical Pattern Recognition Academic Press, Harcourt Brace Javanovich Publishers 1990
- Hornik K. Stinchcombe M. et al. Multilayer Feedforward Networks are Universal Approximators Neural Networks 2 359 366 1989