0
TECHNICAL PAPERS: Gas Turbines: Controls, Diagnostics & Instrumentation

An Integrated Fault Diagnostics Model Using Genetic Algorithm and Neural Networks

[+] Author and Article Information
Suresh Sampath, Riti Singh

Department of Power Propulsion and Aerospace, School of Engineering, Cranfield University, Cranfield, Bedfordshire MK43 0AL, UK

J. Eng. Gas Turbines Power 128(1), 49-56 (Mar 01, 2004) (8 pages) doi:10.1115/1.1995771 History: Received October 01, 2003; Revised March 01, 2004

This paper presents the development of an integrated fault diagnostics model for identifying shifts in component performance and sensor faults using the Genetic Algorithm and Artificial Neural Network. The diagnostics model operates in two distinct stages. The first stage uses response surfaces for computing objective functions to increase the exploration potential of the search space while easing the computational burden. The second stage uses the concept of a hybrid diagnostics model in which a nested neural network is used with genetic algorithm to form a hybrid diagnostics model. The nested neural network functions as a pre-processor or filter to reduce the number of fault classes to be explored by the genetic algorithm based diagnostics model. The hybrid model improves the accuracy, reliability, and consistency of the results obtained. In addition significant improvements in the total run time have also been observed. The advanced cycle Intercooled Recuperated WR21 engine has been used as the test engine for implementing the diagnostics model.

FIGURES IN THIS ARTICLE
<>
Copyright © 2006 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Objective function using Gaussian function

Grahic Jump Location
Figure 2

Data representation using FFBPNN

Grahic Jump Location
Figure 3

Comparison of time taken for objective function

Grahic Jump Location
Figure 4

Schematic of a hybrid diagnostics model

Grahic Jump Location
Figure 5

Results from L1N1 classification

Grahic Jump Location
Figure 6

Results from L2N1 classification

Grahic Jump Location
Figure 7

Results from L2N2 node (Sensor bias detection)

Grahic Jump Location
Figure 8

Results from multiple runs of HDM

Grahic Jump Location
Figure 9

Distribution of fault quantification

Grahic Jump Location
Figure 10

Comparison of run times for different schemes

Grahic Jump Location
Figure 11

Comparison of accuracy of fault detection

Tables

Errata

Discussions

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