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

Data-Driven Fault Detection in Aircraft Engines With Noisy Sensor Measurements

[+] Author and Article Information
Soumik Sarkar

Department of Mechanical Engineering, Pennsylvania State University, University Park, PA 16802szs200@psu.edu

Xin Jin

Department of Mechanical Engineering, Pennsylvania State University, University Park, PA 16802xuj103@psu.edu

Asok Ray

Department of Mechanical Engineering, Pennsylvania State University, University Park, PA 16802axr2@psu.edu

J. Eng. Gas Turbines Power 133(8), 081602 (Apr 06, 2011) (10 pages) doi:10.1115/1.4002877 History: Received March 12, 2010; Revised September 02, 2010; Published April 06, 2011; Online April 06, 2011

An inherent difficulty in sensor-data-driven fault detection is that the detection performance could be drastically reduced under sensor degradation (e.g., drift and noise). Complementary to traditional model-based techniques for fault detection, this paper proposes symbolic dynamic filtering by optimally partitioning the time series data of sensor observation. The objective here is to mask the effects of sensor noise level variation and magnify the system fault signatures. In this regard, the concepts of feature extraction and pattern classification are used for fault detection in aircraft gas turbine engines. The proposed methodology of data-driven fault detection is tested and validated on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS ) test-bed developed by NASA for noisy (i.e., increased variance) sensor signals.

FIGURES IN THIS ARTICLE
<>
Copyright © 2011 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Gas turbine engine schematic (17)

Grahic Jump Location
Figure 2

Schematic diagram of the C-MAPSS engine model

Grahic Jump Location
Figure 3

Original class labels for data collection

Grahic Jump Location
Figure 4

Profile of throttle resolving angle (TRA)

Grahic Jump Location
Figure 5

Representative time series data for HPC fault and Ps30 degradation conditions

Grahic Jump Location
Figure 6

Revised class assignment for fault detection

Grahic Jump Location
Figure 7

General framework for optimization of feature extraction

Grahic Jump Location
Figure 8

Feature space of the training set using optimal partitioning

Grahic Jump Location
Figure 9

Feature space of training set: uniform partitioning (UP)

Grahic Jump Location
Figure 10

Feature space of training set: maximum entropy partitioning (MEP)

Grahic Jump Location
Figure 11

Representative sensor T48 observation

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