Fault diagnosis of an industrial gas turbine using neuro-fuzzy methods

Vasile Palade; Ron J. Patton; Faisel J. Uppal; Joseba Quevedo; S. Daley

doi:10.3182/20020721-6-ES-1901.01632

Fault diagnosis of an industrial gas turbine using neuro-fuzzy methods

Vasile Palade, Ron J. Patton, Faisel J. Uppal, Joseba Quevedo, S. Daley

Research output: Contribution to journal › Article › peer-review

40 Citations (Scopus)

Abstract

The paper focuses on the application of neuro-fuzzy techniques in fault detection and isolation. The objective of this paper is to detect and isolate faults to an industrial gas turbine, with emphasis on faults occurred in the actuator part of the gas turbine. A neuro-fuzzy based learning and adaptation of TSK fuzzy models is used for residual generation, while for residual evaluation a neuro-fuzzy classifier for Mamdani models is used. The paper is concerned on how to obtain an interpretable fault classifier as well as interpretable models for residual generation.

Original language	English
Pages (from-to)	471-476
Number of pages	6
Journal	IFAC papers online
Volume	15
Issue number	1
DOIs	https://doi.org/10.3182/20020721-6-ES-1901.01632
Publication status	Published - 2002
Externally published	Yes
Event	15th World Congress of the International Federation of Automatic Control: IFAC 2002 - Barcelona, Spain Duration: 21 Jul 2002 → 26 Jul 2002 Conference number: 15

Keywords

Fault detection
Fault diagnosis
Fuzzy models
Neural networks
Neuro-fuzzy

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.3182/20020721-6-ES-1901.01632

Cite this

@article{88f515bdc8264f0383df809306d006ed,

title = "Fault diagnosis of an industrial gas turbine using neuro-fuzzy methods",

abstract = "The paper focuses on the application of neuro-fuzzy techniques in fault detection and isolation. The objective of this paper is to detect and isolate faults to an industrial gas turbine, with emphasis on faults occurred in the actuator part of the gas turbine. A neuro-fuzzy based learning and adaptation of TSK fuzzy models is used for residual generation, while for residual evaluation a neuro-fuzzy classifier for Mamdani models is used. The paper is concerned on how to obtain an interpretable fault classifier as well as interpretable models for residual generation.",

keywords = "Fault detection, Fault diagnosis, Fuzzy models, Neural networks, Neuro-fuzzy",

author = "Vasile Palade and Patton, {Ron J.} and Uppal, {Faisel J.} and Joseba Quevedo and S. Daley",

year = "2002",

doi = "10.3182/20020721-6-ES-1901.01632",

language = "English",

volume = "15",

pages = "471--476",

journal = "IFAC papers online",

issn = "2405-8963",

publisher = "IFAC Secretariat",

number = "1",

note = "15th World Congress of the International Federation of Automatic Control : IFAC 2002, IFAC 2002 ; Conference date: 21-07-2002 Through 26-07-2002",

}

TY - JOUR

T1 - Fault diagnosis of an industrial gas turbine using neuro-fuzzy methods

AU - Palade, Vasile

AU - Patton, Ron J.

AU - Uppal, Faisel J.

AU - Quevedo, Joseba

AU - Daley, S.

N1 - Conference code: 15

PY - 2002

Y1 - 2002

N2 - The paper focuses on the application of neuro-fuzzy techniques in fault detection and isolation. The objective of this paper is to detect and isolate faults to an industrial gas turbine, with emphasis on faults occurred in the actuator part of the gas turbine. A neuro-fuzzy based learning and adaptation of TSK fuzzy models is used for residual generation, while for residual evaluation a neuro-fuzzy classifier for Mamdani models is used. The paper is concerned on how to obtain an interpretable fault classifier as well as interpretable models for residual generation.

AB - The paper focuses on the application of neuro-fuzzy techniques in fault detection and isolation. The objective of this paper is to detect and isolate faults to an industrial gas turbine, with emphasis on faults occurred in the actuator part of the gas turbine. A neuro-fuzzy based learning and adaptation of TSK fuzzy models is used for residual generation, while for residual evaluation a neuro-fuzzy classifier for Mamdani models is used. The paper is concerned on how to obtain an interpretable fault classifier as well as interpretable models for residual generation.

KW - Fault detection

KW - Fault diagnosis

KW - Fuzzy models

KW - Neural networks

KW - Neuro-fuzzy

UR - http://www.scopus.com/inward/record.url?scp=84945575284&partnerID=8YFLogxK

U2 - 10.3182/20020721-6-ES-1901.01632

DO - 10.3182/20020721-6-ES-1901.01632

M3 - Article

AN - SCOPUS:84945575284

SN - 2405-8963

VL - 15

SP - 471

EP - 476

JO - IFAC papers online

JF - IFAC papers online

IS - 1

T2 - 15th World Congress of the International Federation of Automatic Control

Y2 - 21 July 2002 through 26 July 2002

ER -

Fault diagnosis of an industrial gas turbine using neuro-fuzzy methods

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this