Fault detection of a helicopter gearbox by pattern classification is discussed. The detection system is composed of two components, a quantization matrix to flag the measurements, and a multi-valued influence matrix (MVIM) that represents the behavior of measurements during normal operation and at fault instances. Both the quantization matrix and the influence matrix are tuned during a training session so as to minimize the error in detection. This detection system was applied to vibration measurements collected from a helicopter gearbox test stand during accelerated fatigue tests and at various fault instances. The results indicate that the MVIM method provides accurate detection when the full range of faults effects on the measurements are included in the training set. Furthermore, the fixed structure of MVIM allows evaluation of individual measurements. This feature was utilized to select a subset of measurements crucial to detection.

1.
Astridge, D. G., 1986, “Vibration Health Monitoring of the Westland 30 Helicopter Transmission—Development and Service Experience,” Mechanical Failure Prevention Group 41th Meeting, Oct., pp. 200–215.
2.
Braun, S., 1986, Mechanical Signature Analysis—Theory and Applications, Academic Press, New York, NY.
3.
Cempel
C.
,
1988
, “
Vibroacoustical Diagnostics of Machinery: An Outline
,”
Mechanical Systems and Signal Processing
, Vol.
2
, No.
2
, pp.
135
151
.
4.
Chin, H., and Danai, K., 1991, “Fault Diagnosis of Helicopter Power Trains,” Proc. of the 17th Annual NSF Grantees Conference in Design and Manufacturing Systems Research, Austin, TX, Jan., pp. 787–790.
5.
Chin
H.
,
Danai
K.
, and
Lewicki
D. G.
,
1993
, “
Pattern Classifier for Fault Diagnosis of Helicopter Gearboxes
,”
IFAC J. of Control Engineering Practice
, Vol.
1
, No.
5
, pp.
771
778
.
6.
Collier-March, M. E., and Astridge, D. G., 1985, “Operational Experience with the Advanced Transmission Health Monitoring Techniques on the Westland 30 Helicopter,” 11th European Rotorcraft Forum, p. 43.
7.
Danai
K.
, and
Chin
H.
,
1991
, “
Fault Diagnosis with Process Uncertainty
,”
ASME Journal of Dynamic Systems, Measurement and Control
, Vol.
113
, No.
3
, Sept., pp.
339
343
.
8.
Dimarogonas, A., and Haddad, S. D., 1992, “Machinery Vibrations: Monitoring and Diagnosis,” Chapter 14 of Vibration for Engineers, Prentice-Hall, Inc., Englewood Cliffs, NJ.
9.
Gertler, J. J., 1991, “Analytical Redundancy Methods in Fault Detection and Isolation,” Proc. of IFAC SAFEPROCESS Symposium, Baden-Baden, Germany.
10.
Hertz, J., Krogh, A., and Palmer, R. G., 1991, Introduction to the Theory of Neural Computation, Addison-Wesley, Redwood City, CA.
11.
Kaufman, A. B., 1975, “Measure Machinery Vibration—It Can Help You Anticipate and Prevent Failure,” Instruments & Control Systems, Feb., pp. 59–62.
12.
Lewicki, D. G., Decker, H. J., and Shimski, J. T., 1992, “Full-Scale Transmission Testing to Evaluate Advanced Lubricants,” Technical Report, NASA TM-105668, AVSCOM TR-91-C-035.
13.
Ljung, L., 1987, System Identification: Theory for the User, Prentice-Hall, Inc., Englewood Cliffs, NJ.
14.
Mertaugh, L. J., 1986, “Evaluation of Vibration Analysis Techniques for the Detection of Gear and Bearing Faults in Helicopter Gearboxes,” Mechanical Failure Prevention Group 41th Meeting, Oct., pp. 28–30.
15.
Pratt, J. L., 1986, “Engine and Transmission Monitoring—A Summary of Promising Approaches,” Mechanical Failure Prevention Group 41th Meeting, Oct., pp. 229–236.
16.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J., 1988, “Learning Error Representation by Error Propagation,” Rumelhart, D. E. and McClelland, J. L., eds., Parallel Distributed Processing—Explorations in the Microstructure of Cognition, Volume 1: Foundations, The MIT Press, Cambridge, MA.
17.
Stewart Hughes Limited, 1986, MSDA User’s Guide, Southampton, UK.
This content is only available via PDF.
You do not currently have access to this content.