This paper demonstrates a novel approach to condition-based health monitoring for rotating machinery using recent advances in neural network technology and rotordynamic, finite-element modeling. A desktop rotor demonstration rig was used as a proof of concept tool. The approach integrates machinery sensor measurements with detailed, rotordynamic, finite-element models through a neural network that is specifically trained to respond to the machine being monitored. The advantage of this approach over current methods lies in the use of an advanced neural network. The neural network is trained to contain the knowledge of a detailed finite-element model whose results are integrated with system measurements to produce accurate machine fault diagnostics and component stress predictions. This technique takes advantage of recent advances in neural network technology that enable real-time machinery diagnostics and component stress prediction to be performed on a PC with the accuracy of finite-element analysis. The availability of the real-time, finite-element-based knowledge on rotating elements allows for real-time component life prediction as well as accurate and fast fault diagnosis.

Aleksander, I., and Morton, H., 1990, An Introduction to Neural Computing, Chapman and Hall Publishing, New York.
W. E.
E. L.
, and
, “
Jet and Rocket Engine Fault Diagnosis in Real Time
Journal of Neural Network Computing
, Vol.
, pp.
Hong, C. A., 1991, “Analysis and Replacement of the 15th Stage Blading of Martins Creek Unit,” STI Technical Paper.
Pomfret, C., 1993, “Engine Life Monitoring, Performance Trending, and Diagnosis in the USAF: A Concept for the Future,” Discussion paper, WPAFB.
STI, 1993, “Development of Advanced Rotordynamics Software for Root Cause Investigations,” Report PA791.
Widrow, B., 1989, “DARPA Neural Network Study,” AFCEA International Press.
This content is only available via PDF.
You do not currently have access to this content.