0
Research Papers: Energy Systems Analysis

Fuzzy Expert Systems for the Diagnosis of Component and Sensor Faults in Complex Energy Systems

[+] Author and Article Information
Andrea Toffolo

Department of Mechanical Engineering, University of Padova via Venezia, 1-35151 Padova, Italyandrea.toffolo@unipd.it

J. Energy Resour. Technol 131(4), 042002 (Oct 12, 2009) (10 pages) doi:10.1115/1.4000175 History: Received September 22, 2008; Revised August 05, 2009; Published October 12, 2009

Locating the causes of malfunctions in complex energy systems is an extremely difficult task, since more than one fault mode may produce similar and possibly undistinguishable patterns of effects. This paper shows how fuzzy expert systems can exploit the available measurements from the data acquisition system to identify different component and sensor fault modes. Real sensor data (mass flow rates, pressures, temperatures, and key operating parameters) are compared with the expected values of the same quantities that are calculated using numerical models of local subsystems. This comparison simply determines if the differences between measured and expected values are “negative,” “zero,” or “positive” in fuzzy logic terms. The final objective is to verify the existence of some patterns of these attributes that univocally identify the considered fault modes. These patterns are then implemented as the set of rules forming the knowledge base of a fuzzy expert system. The proposed diagnostic methodology is tested on the gas section of a real combined-cycle cogeneration plant, and the effect of measurement noise is also discussed.

FIGURES IN THIS ARTICLE
<>
Copyright © 2009 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 12

Distributions of measured (in blue) and calculated (in red) quantities for the compressor subsystem in case of compressor fouling (T4=750°C, Δṁcp=−2%, Δηcp=−1%)

Grahic Jump Location
Figure 13

The effects of measurement noise on the membership functions of the attributes used in the antecedents of the rules drawn from the grid in Fig. 9 (dashed lines: functions referring to sensor uncertainty; solid lines: functions for noisy data)

Grahic Jump Location
Figure 1

Examples of membership functions associated with the attributes of the input variables in a qualitative approach

Grahic Jump Location
Figure 2

Examples of membership functions associated with the attributes of the input variables in a semiquantitative approach

Grahic Jump Location
Figure 3

The membership function associated with the attribute of the output variables in a qualitative approach

Grahic Jump Location
Figure 4

Examples of membership functions associated with the attributes of the output variables in a semiquantitative approach

Grahic Jump Location
Figure 5

SIMULINK model of the plant

Grahic Jump Location
Figure 6

The simulated effects of compressor fouling, combustor fouling and hp turbine erosion on the quantities measured by the data acquisition system of the plant (gray bands show the values within the limits of sensor uncertainty at ±3σ)

Grahic Jump Location
Figure 7

Subsystem with compressor only

Grahic Jump Location
Figure 8

Subsystem with combustor and hp turbine

Grahic Jump Location
Figure 9

The grid of the effects of the fault modes on the quantities calculated using the subsystems in Table 2

Grahic Jump Location
Figure 10

The Gaussian membership functions used to fuzzify the input deltas in the presented test case

Grahic Jump Location
Figure 11

Distributions of measured (in blue) and calculated (in red) quantities for the compressor subsystem in case of filter fouling (T4=750°C, ΔAaf=−20%)

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