Identification-Based Condition Monitoring of Technical Systems
A novel identification-based technique for fault detection and condition monitoring of hydro- and electromechanical servomechanisms is proposed. It is based on neural network analyses of the control charts presenting behavior of the dynamic model parameters. There were derived analytical expressions that allow minimizing impact of the measurement errors on the identification accuracy. The proposed technique has been implemented in a software tool that allows automating the decision-making.
Key wordscondition monitoring identification control charts neural networks
Unable to display preview. Download preview PDF.
- 1.Anagun A. S., 1998. A neural network applied to pattern recognition in statistical process control. Proceedings of the 23rd Int. Conf. on Computers and Ind. Engineering, Chicago, IL, 185–188.Google Scholar
- 2.Basseville M. and Nikiforov I.V., 1993. Detection of abrupt changes: theory and applications, Englewood Cliffs, NJ: Prentice-Hall.Google Scholar
- 3.Chang S. I., 2000. An Integrated Scheme for Process Monitoring and Diagnosis. Proceedings of ASQC 49th Annual Quality Congress, Cincinnati, OH, 725–732.Google Scholar
- 5.Dash S. and Venkatasubramanian V., 2000. Challenges in the industrial applications of fault diagnostic systems. Proceedings of the conference on Process Systems Engineering, Keystone, Colorado, 785–791.Google Scholar
- 7.Grant E.L. and Leavenworth R.S., 1996. Statistical quality control, New York: McGraw-Hill.Google Scholar
- 8.Hwarng H.B. and Hubele N.F., 1993. X-bar control chart pattern identification through efficient off-line neural network training. IIE Transactions, 25, 27–40.Google Scholar
- 9.Kulikov G.G., Breikin, T.V., Arkov V.Y. and Fleming, P.J., 1999. Real-time simulation of aviation engines for FADEC test-beds. Proceedings of the International Gas Turbine Congress, Kobe, Japan, 949–952.Google Scholar
- 10.Lucy-Bouler T.L., 1993. Application to forecasting of neural network recognition of shifts and trends in quality control data. Proceedings of WCNN’93—World Congress on Neural Networks, Portland, UK, vol. 1, 631–633.Google Scholar
- 11.Montgomery D.C., 1996. Introduction to Statistical Quality Control, John Wiley and Sons, Inc., New York.Google Scholar
- 12.Pham D.T. and Oztemel E., 1994. Control chart pattern recognition using learning vector quantization networks. International Journal of Production Research, 32, 721–729.Google Scholar