The objective of this paper is the development of an efficient intelligent diagnostic procedure that considers several diagnostic indices for the quantification of developing faults and for monitoring machine condition. In this procedure, the condition monitoring is performed based on the on-line vibration measurements, and further, the fault quantification is formulated into a multivariate trend analysis. Self-organizing neural networks are then deployed to perform the multivariable trending of the fault development. The attributes for the disordering of “knots” in the trend analysis are determined. The disordering of neural network units is then eliminated by suitably altering the self-organizing neural network algorithm. Applications of this diagnostic procedure to the condition monitoring and life estimation of a bearing system are fully developed and demonstrated. The efficiency and advantages of the intelligent diagnostic procedure in precisely monitoring and quantifying the fault development are systematically brought out considering this bearing system.

Issue Section:
Gas Turbines: Controls and Diagnostics
Topics:
Artificial neural networks, Machinery, Trend analysis, Bearings, Condition monitoring, Self-organization, Algorithms, Vibration measurement
1.
Baum, E. B., 1990, “When Are K-Nearest Neighbour and Back Propagation Accurate for Feasible Sized Sets of Examples” in: Proc. of Eurasia Workshop on Neural Networks, L. B. Almedia & C. J. Wellekens, eds., Springer-Verlag, New York, pp. 2–25.
2.
Cempel
C.
,
1988
, “
Vibroacoustical Diagnostics of Machinery: An Outline
,”
Mechanical Systems and Signal Processing
, Vol.
2
(
2
), pp.
1352
–
151
.
3.
Cherkassky, V., and Lari-Najafi, H., 1991, “Constrained Topological Mapping for Nonparametric Regression Analysis,” Neural Networks, Pergamon, Vol. 4, pp. 272–40.
4.
Cherkassky, V., and Lari-Najafi, H., 1992, “Nonparametric Regression Using Self-Organizing Topological Maps,” Neural Networks for Human and Machine Perception, H. Wechsler, ed., Academic Press, Vol. 2, pp. 40–64.
5.
Collacott, R. A., 1977, Mechanical Fault Diagnosis and Condition Monitoring, Chapman and Hall, London.
6.
Collacott, R. A., 1979, Vibration Monitoring and Diagnosis, George Goodwin Ltd., London.
7.
Friedman
J. H.
, and
Silverman
B. W.
,
1989
, “
Flexible Parsimonious Smoothing and Additive Modelling
,”
Technometrics
, Vol.
31
, No.
1
, pp.
3
–
21
.
8.
Kohonen
T.
,
1989
, “
The Self-Organizing Map
,”
Proc. IEEE
, Vol.
78
, No.
9
, pp.
1464
–
1480
.
9.
Lipovszky, G., So´lyomva´ri, K., and Varga, G., 1990, Vibration Testing of Machines and Their Maintenance, Elsevier Science Publishing Co., Amsterdam.
10.
Mathew
J.
, and
Alfredson
R. J.
,
1984
, “
The Condition Monitoring of Rolling Element Bearing Using Vibration Analysis
,”
ASME Journal of Vibration, Acoustics, Stress, and Reliability in Design
, Vol.
106
, pp.
447
–
453
.
11.
Specht
D. F.
,
1991
, “
A General Regression Neural Network
,”
IEEE Trans., Neural Networks
, Vol.
2
, No.
6
, pp.
568
–
576
.
12.
Tranter, J., 1989, “The Fundamentals of, and the Application of Computers to, Condition Monitoring and Predictive Maintenance,” in: Proc. of 1st Inter. Machinery Monitoring and Diagnosis Conf., Las Vegas, NV, Sept., pp. 394–401.
13.
Zhang, S., 1995, “Development of a Knowledge-Base System for Rotating Machinery Diagnostics,” Ph.D. Thesis, Concordia University, Montreal, Canada.
This content is only available via PDF.
Copyright © 1997
 by The American Society of Mechanical Engineers
You do not currently have access to this content.