Transient IC Engine Monitoring Under Temperature Changes Using an AANN

Xun Wang, George W. Irwin, Geoff McCullough, Neil McCullough, Uwe Kruger

2008

Abstract

This paper reports on non-linear principal component analysis for fault detection on an internal combustion (IC) engine. An auto-associative neural network (AANN) model is built from transient engine data collected under varying atmospheric conditions. The experimental data used for modelling was collected for two different drive cycles, the Identification Cycle and the New European Drive Cycle. The key issue here is to decide which data should be used for training the neural network to produce good fault detection generalisation under different atmospheric conditions and with a different drive cycle. This is achieved successfully, with the Q monitoring statistic indicating an absence of unwanted false alarms under fault-free operation, along with successful detection of air leaks of varying magnitude in the inlet manifold.

References

  1. Antory, D., U. Kruger, G.W. Irwin and G. McCullough 2005. Fault diagnosis in internal combustion engines using nonlinear multivariate statistics. Proc Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 219(4), 243-258.
  2. Crossman, J.A., H. Guo, Y.K. Murphey and J. Cardillo 2003. Automotive signal fault diagnostics - part I: signal fault analysis, signal segmentation, feature extraction and quasioptimal feature selection. IEEE Transactions on Vehicular Technology 52(4), 1063-1075.
  3. Grimaldi, C.N. and F. Mariani 2001. OBD Engine Fault Detection Using a Neural Approach. SAE Paper No. 2001-01-0559.
  4. Jackson, J.E. 1991. A Users Guide to Principal Components. Wiley Series in Probability and Mathematical Statistics. John Wiley, New York.
  5. Kimmich, F., A. Schwarte and R. Isermann 2005. Fault detection for modern diesel engines using signal- and process model-based methods. Control Engineering Practice 13, 189-203.
  6. Kramer, M.A. 1992. Autoassociative neural networks. Computers and Chemical Engineering 16(4), 313-328.
  7. Nyberg, M. 1999. Model Based Diagnosis of Both Sensor Faults and Leakage in the AirIntake System of an SI Engine. SAE Paper No. 1999-01-0860.
  8. Sher, E. 1984. Effect of atmospheric conditions on the performance of an air-borne twostroke spark-ignition engine. Proc Institution of Mechanical Engineers, Part D: Transport Engineering. 198(15), 239-251.
  9. Stobart, R. 2003. Control oriented models for exhaust gas aftertreatment; A Review and Prospects, SAE Paper No. 2003-01-1004.
  10. Wang, X., U. Kruger, G.W. Irwin, G. McCullough and N. McDowell 2008a. Nonlinear PCA with the local approach for diesel engine fault detection and diagnosis, IEEE Trans. Control Systems Technology 16 (1), 122-129
  11. Wang, X., G.W. Irwin, G. McCullough, N. McDowell and U. Kruger 2008b. Application of nonlinear dynamic PCA to automotive engine modelling and fault monitoring, Control Engineering
Download


Paper Citation


in Harvard Style

Wang X., W. Irwin G., McCullough G., McCullough N. and Kruger U. (2008). Transient IC Engine Monitoring Under Temperature Changes Using an AANN . In Proceedings of the 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2008) ISBN 978-989-8111-33-3, pages 28-40. DOI: 10.5220/0001507900280040


in Bibtex Style

@conference{anniip08,
author={Xun Wang and George W. Irwin and Geoff McCullough and Neil McCullough and Uwe Kruger},
title={Transient IC Engine Monitoring Under Temperature Changes Using an AANN},
booktitle={Proceedings of the 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2008)},
year={2008},
pages={28-40},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001507900280040},
isbn={978-989-8111-33-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2008)
TI - Transient IC Engine Monitoring Under Temperature Changes Using an AANN
SN - 978-989-8111-33-3
AU - Wang X.
AU - W. Irwin G.
AU - McCullough G.
AU - McCullough N.
AU - Kruger U.
PY - 2008
SP - 28
EP - 40
DO - 10.5220/0001507900280040