0
Research Papers: Gas Turbines: Controls, Diagnostics, and Instrumentation

Multiple-Model Sensor and Components Fault Diagnosis in Gas Turbine Engines Using Autoassociative Neural Networks

[+] Author and Article Information
Z. N. Sadough Vanini

Department of Electrical
and Computer Engineering,
Concordia University,
Montreal, QC H3G 1M8, Canada

N. Meskin

Department of Electrical Engineering,
Qatar University,
Doha, Qatar
e-mail: nader.meskin@qu.edu.qa

K. Khorasani

Department of Electrical
and Computer Engineering,
Concordia University,
Montreal, QC H3G 1M8, Canada
e-mail: kash@ece.concordia.ca

Contributed by the Controls, Diagnostics and Instrumentation Committee of ASME for publication in the JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER. Manuscript received November 25, 2013; final manuscript received March 5, 2014; published online May 5, 2014. Assoc. Editor: Allan Volponi.

J. Eng. Gas Turbines Power 136(9), 091603 (May 05, 2014) (16 pages) Paper No: GTP-13-1429; doi: 10.1115/1.4027215 History: Received November 25, 2013; Revised March 05, 2014

In this paper the problem of fault diagnosis in an aircraft jet engine is investigated by using an intelligent-based methodology. The proposed fault detection and isolation (FDI) scheme is based on the multiple model approach and utilizes autoassociative neural networks (AANNs). This methodology consists of a bank of AANNs and provides a novel integrated solution to the problem of both sensor and component fault detection and isolation even though possibly both engine and sensor faults may occur concurrently. Moreover, the proposed algorithm can be used for sensor data validation and correction as the first step for health monitoring of jet engines. We have also presented a comparison between our proposed approach and another commonly used neural network scheme known as dynamic neural networks to demonstrate the advantages and capabilities of our approach. Various simulations are carried out to demonstrate the performance capabilities of our proposed fault detection and isolation scheme.

FIGURES IN THIS ARTICLE
<>
Copyright © 2014 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Architecture of an autoassociative neural network (AANN) where σ denotes the sigmoidal nodes and l denotes the linear nodes

Grahic Jump Location
Fig. 2

The dual spool aircraft jet engine modules and information flow chart and interdependencies (for details refer to [21,28,35])

Grahic Jump Location
Fig. 3

Sensor fault detection scheme using the autoassociative neural network (AANN) architecture

Grahic Jump Location
Fig. 4

The parallel bank of AANN architecture proposed for performing the fault detection and isolation tasks simultaneously corresponding to L faulty modes and scenarios

Grahic Jump Location
Fig. 5

Input and output of the AANN0 network for noise filtering

Grahic Jump Location
Fig. 9

The AANN5, AANN6, and AANN8 generated residuals corresponding to the case of a 2% ΔηLT fault

Grahic Jump Location
Fig. 10

The AANN6 and AANN8 generated residuals corresponding to the case of a 3% ΔηLT fault

Grahic Jump Location
Fig. 6

Error correction capability of the AANN0 scheme corresponding to sensor recovery and deviation rates for the TLC and PLC sensors

Grahic Jump Location
Fig. 8

The AANN1 and AANN5 generated residuals corresponding to the case of a 4% ΔΓHT fault

Grahic Jump Location
Fig. 11

The AANN2 and AANN5 generated residuals for the case of a 4% ΔηHT fault injected at t = 15 s and a 20 K bias injected on the THC sensor at t = 20 s

Grahic Jump Location
Fig. 12

Performance of the FDI scheme subject to concurrent faults. Top plots show the AANN7 residuals for the 5% ΔΓLT fault injected at t = 16 s and the 5% ΔηLT fault injected at t = 25 s. The bottom plots show the AANN8 residuals for the 5% ΔΓLT fault injected at t = 16 s and the 5% ΔηLT fault injected at t = 25 s.

Grahic Jump Location
Fig. 7

The AANN1 sensor reconstruction and the residual signals for the sensor drift fault with the rate of 0.06% per second on the THT and N2 sensor measurements

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