One of the most dangerous problems that can occur in both military and civilian helicopters is the failure of the main gearbox. Currently, the principal method of controlling gearbox failure is to regularly overhaul the complete system. This paper considers the feasibility of using a neural network to perform fault detection on vibration measurements given by accelerometer data. The details and results obtained from studying the neural network approach are presented. Some of the elementary underlying physics will be discussed along with the preprocessing necessary for analysis. Several networks were investigated for detection and classification of the gearbox faults. The performance of each network will be presented. Finally, the network weights will be related back to the underlying physics of the problem.

1.
Solorzano, M., Huang, W., and Hollins, M., 1990, “A Real-Time Prognosis System for Helicopter Power Trains,” Presented at IEEE Autotestcon 90, San Antonio, TX Sept 20.
2.
“Summary Report, International Gearbox Monitoring Workshop,” June 12–14, 1990, Gulf Breeze, Fl, Sponsored by the Technical Cooperation Program.
3.
McFadden, P. D., and Smith, J. D., 1985, “A Signal Processing Technique for Detecting Local Defects in a Gear from the Signal Average of the Vibration,” Proceedings of the Institution of Mechanical Engineers, Vol. 199, No. C4.
4.
Sramek, J., “Frequency Calculations for Ball Bearings,” Report for Nicolet Scientific Corporation, 245 Livingston Street, NJ 07647.
5.
Hollins, M., 1990, “The Effects of Vibration Sensor Location in Detecting Gear and Bearing Defects,” Report for Naval Air Test Center, Code RW82B, Patuxent, MD 20670-5304.
6.
Burden, R., and Faires, J., 1989, Numerical Analysis, Fourth Edition, PWS Publishing, Boston, pp. 91–98.
7.
Simpson, P., Artificial Neural Systems, Foundations, Paradigms, Applications, and Implementations, Pergamon Press, Elmsford, NY.
8.
Jacyna
G.
, and
Malaret
E.
,
1989
, “
Classification Performance of a Hopfield Neural Network Based on a Hebbian-like Learning Rule
,”
IEEE Transactions on Information Theory
, Vol.
IT-35
, pp.
263
280
.
9.
Colella, D., Hriljac, P., and Jacyna, G., “A Fokker-Planck Statistical Model for Neural Nets,” Submitted to the Society for Industrial and Applied Mathematics.
10.
Leighton, R., and Wieland, A., 1990, “Aspirin for MIGRANES: User’s Manual,” Report for the MITRE Corporation, 7525 Coleshire Dr., McLean, VA 22102-3481, MP-90W00044, 1990.
11.
Eschmann, Hasbargen, and Weigand, Ball and Roller Bearings, Theory, Design, and Application, Second Edition, revised by L. Hasbargen and J. Brandlein, John Wiley and Sons, New York.
This content is only available via PDF.
You do not currently have access to this content.