Abstract
An intelligent sensor validation and on-line fault diagnosis technique for a 6 cylinder turbocharged diesel engine is proposed and studied. A single auto-associative 3-layer Artificial Neural Network (ANN), is trained to examine the accuracy of the measured data and allocate a confidence level to each signal. The same ANN is used to recover the missing or faulty data with a close approximation. For on-line fault detection a feed-forward ANN is trained to classify and consequently recognize faulty and healthy behavior of the engine for a wide range of operating conditions. The proposed technique is also equipped with an on-line learning mechanism, which is activated when the confidence level in predicted fault is poor. It is hoped that a feasible, practical, and reliable sensor reading, as well as highly accurate fault diagnosis system, would be achieved.
1.
Merrill
, W. C.
, De Laat
, J. C.
, and Burton
, W. M.
, 1988
, “Advanced detection, isolation and accommodation of sensor failures, real-time evaluation
,” AIAA Journal of Guidance and Control Dynamics
, 11
, p. 6
6
.2.
Dinca
, L.
, Aldemir
, T.
, and Rizzoni
, G.
, 1999
, “A model-based probabilistic Approach for Fault Detection and Identification with Application to Diagnosis of Automotive Engines
,” IEEE Trans. Autom. Control
, 44
, pp. 2200
–2205
.3.
Romagnoli, J. A., and Sanchez M. C., 1999, Data Processing and Reconciliation for Chemical Process Operations, Academic Press, NY.
4.
Heyen, G., 2000, “Application of Data Reconciliation to Process Monitoring,” Proceedings of International Symposium on Computer Aided Process Engineering, Colombia.
5.
Woud, J. K., and Boot, P., 1993, “Diesel engine condition monitoring and fault diagnosis based on process models,” CIMAC’93, Proceedings of 21st International Congress on Combustion Engines, Vol. D81, pp. 1–19.
6.
Arefzadeh, S., Burgwinkel, P., and Geropp, B., 1996, “Diagnosis of Diesel Engines based on Vibration Analysis and Fuzzy Logic,” Proceedings of 4th European Congress on Intelligent Techniques and Soft Computing, Vol. 2, pp. 1497–1500.
7.
Hargarve, S. M., and Fleming, P. J., 1998, “The Use of Case-Based Reasoning Technology to Aid Fault Isolation In Modern gas Turbine Engine Design,” Proceedings of ASME International Gas and Aeroengine Congress & Exhibition, Sweden.
8.
Frank
, P. M.
, and Ding
, X.
, 1994
, “Frequency domain Approach to Optimally Robust Residual Generation and Evaluation for Model-based Fault Diagnosis
,” Automatica
, 30
, pp. 789
–804
.9.
Mesbahi, E., and Atlar, M., 1998, “Applications of Artificial Neural networks in marine design and modelling,” Proceedings of AIOMA’98 International Conference on Artificial Intelligence on Marine Applications, pp. 34–46.
10.
Mesbahi, E., and Roskilly, A. P., 1998, “A Model Reference Neural Adaptive Controller (MRNAC) for time-variant systems with uncertainties,” Proceedings of IASTED International Conference on Control and Application, pp. 48–53.
11.
Naidu
, S. R.
, Zafiriou
, E.
, and McAvoy
, T.
, 1990
, “Use of Neural Networks for Sensor Detection in an Control System
,” IEEE Control Syst. Mag.
, 4
, pp. 49
–55
.12.
Parlos
, A. G.
, Muthusami
, J.
, and Atiya
, A. F.
, 1994
, “Incipient fault detection and identification in Process systems using accelerated neural network learning
,” Nucl. Technol.
, 105
, pp. 145
–161
.13.
DePold, H. R., and Gass, F. D., 1998, “The application of expert systems and neural networks to gas turbine prognostics and diagnostics, Proceedings of ASME International Gas and Aeroengine Congress & Exhibition, Sweden.
14.
Napolitabo
, M. R.
, Silvestri
, G.
, Windon
, D. A.
II, Casanova
, J. L.
, and Innocenti
, M.
, 1998
, “Sensor Validation Using Hardware-based On-line Learning Neural Networks
,” IEEE Trans. Aerosp. Electron. Syst.
, 34
, pp. 456
–468
.15.
Hines
, J. W.
, Uhring
, R. E.
, and Wrest
, D. J.
, 1998
, “Use of Autoassociative Neural Networks for signal validation
,” Journal of Intelligent and Robotic Systems: Theory and Applications
, 21
, pp. 143
–154
.16.
Isaias, L., 1989, “Performance simulation of a medium speed diesel engine under optimum and fault conditions,” Ph.D. thesis, Department of Marine Technology, University of Newcastle upon Tyne, UK.
17.
Malloy, D. J., Chappel, M. A., and Biegel, C., 1997, “Real-time fault identification for developmental turbine engine testing,” Proceedings of ASME International Gas Turbine and Aeroengine Congress and Exposition, Sweden.
Copyright © 2001
by ASME
You do not currently have access to this content.
