TECHNICAL PAPERS: Gas Turbines: Controls, Diagnostics, and Instrumentation

Neural Network and Fuzzy Logic Diagnostics of 1x Faults in Rotating Machinery

[+] Author and Article Information
A. El-Shafei, T. A. F. Hassan, A. K. Soliman, Y. Zeyada

 RITEC, New Maadi, Cairo 11435, Egypt

N. Rieger

 STI Technologies, Inc., Rochester, NY 14623

J. Eng. Gas Turbines Power 129(3), 703-710 (Feb 01, 2006) (8 pages) doi:10.1115/1.2227417 History: Received October 01, 2005; Revised February 01, 2006

In this paper, the application of neural networks and fuzzy logic to the diagnosis of faults in rotating machinery is investigated. The learning-vector-quantization (LVQ) neural network is applied in series and in parallel to a fuzzy inference engine, to diagnose 1x faults. The faults investigated are unbalance, misalignment, and structural looseness. The method is applied to a test rig (Hassan, 2003, ASME Paper No. GT 2003-38450), and the effectiveness of the integrated Neural Network and Fuzzy Logic method is illustrated.

Copyright © 2007 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

LVQ neural network

Grahic Jump Location
Figure 2

Feed forward network

Grahic Jump Location
Figure 3

Flow chart of measurement procedure

Grahic Jump Location
Figure 4

Fault implementation on test rig

Grahic Jump Location
Figure 5

Training of LVQ network

Grahic Jump Location
Figure 6

Training of feed forward network

Grahic Jump Location
Figure 7

The features of a membership function (20)

Grahic Jump Location
Figure 8

Diagnosis procedure

Grahic Jump Location
Figure 9

Fuzzy logic system

Grahic Jump Location
Figure 10

Misalignment sample amplitude spectrum



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In