Multiple-Model Fault Diagnosis Method for Gas Turbine Based on Soft Switch

Yunpeng Cao; Kehui Zeng; Shuying Li; Fengshou Gu; Yuandong Xu; Bo He

doi:10.1007/978-3-030-57745-2_31

Multiple-Model Fault Diagnosis Method for Gas Turbine Based on Soft Switch

Yunpeng Cao, Kehui Zeng, Shuying Li, Fengshou Gu, Yuandong Xu, Bo He

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Fault diagnosis based on a multiple-model (MM) approach is an analytical redundancy method. In this paper, we mainly focus on the model switch optimizing problem of the MM method. First, a MM method for gas turbine gas path fault diagnosis was proposed, and the gas turbine state space models are established based on analytical linearization which can simulate the nonlinear dynamic characteristics at the operating points. Then model soft switch method was proposed based on recursive Bayesian to solve the problem that the established state space model is accurate merely in the vicinity of the operating points, and generates the combined generic model for the full operating condition and make it smoother. Finally, the fault simulation was carried out on a marine gas turbine which shows that the proposed method can diagnose both single gas path fault and multiple gas path faults.

Original language	English
Title of host publication	Advances in Asset Management and Condition Monitoring, COMADEM 2019
Editors	Andrew Ball, Len Gelman, B.K.N. Rao
Publisher	Springer, Cham
Pages	363-375
Number of pages	13
Volume	166
ISBN (Electronic)	9783030577452
ISBN (Print)	9783030577445
DOIs	https://doi.org/10.1007/978-3-030-57745-2_31
Publication status	Published - 28 Aug 2020
Event	32nd International Congress and Exhibition on Conditioning Monitoring and Diagnostic Engineering Management Conference - University of Huddersfield, Huddersfield, United Kingdom Duration: 3 Sep 2019 → 5 Sep 2019 Conference number: 32 http://www.comadem2019.com/ (Link to Conference Website)

Publication series

Name	Smart Innovation, Systems and Technologies
Publisher	Springer
Volume	166
ISSN (Print)	2190-3018
ISSN (Electronic)	2190-3026

Conference

Conference	32nd International Congress and Exhibition on Conditioning Monitoring and Diagnostic Engineering Management Conference
Abbreviated title	COMADEM 2019
Country/Territory	United Kingdom
City	Huddersfield
Period	3/09/19 → 5/09/19
Internet address	http://www.comadem2019.com/ (Link to Conference Website)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-57745-2_31Licence: Unspecified

Cite this

Cao, Y., Zeng, K., Li, S., Gu, F., Xu, Y., & He, B. (2020). Multiple-Model Fault Diagnosis Method for Gas Turbine Based on Soft Switch. In A. Ball, L. Gelman, & B. K. N. Rao (Eds.), Advances in Asset Management and Condition Monitoring, COMADEM 2019 (Vol. 166, pp. 363-375). (Smart Innovation, Systems and Technologies; Vol. 166). Springer, Cham. https://doi.org/10.1007/978-3-030-57745-2_31

@inproceedings{023ab68869cb4d469409368384a78e46,

title = "Multiple-Model Fault Diagnosis Method for Gas Turbine Based on Soft Switch",

abstract = "Fault diagnosis based on a multiple-model (MM) approach is an analytical redundancy method. In this paper, we mainly focus on the model switch optimizing problem of the MM method. First, a MM method for gas turbine gas path fault diagnosis was proposed, and the gas turbine state space models are established based on analytical linearization which can simulate the nonlinear dynamic characteristics at the operating points. Then model soft switch method was proposed based on recursive Bayesian to solve the problem that the established state space model is accurate merely in the vicinity of the operating points, and generates the combined generic model for the full operating condition and make it smoother. Finally, the fault simulation was carried out on a marine gas turbine which shows that the proposed method can diagnose both single gas path fault and multiple gas path faults.",

keywords = "Fault diagnosis, Gas turbine, Model, Multiple-model, Soft switch",

author = "Yunpeng Cao and Kehui Zeng and Shuying Li and Fengshou Gu and Yuandong Xu and Bo He",

year = "2020",

month = aug,

day = "28",

doi = "10.1007/978-3-030-57745-2_31",

language = "English",

isbn = "9783030577445",

volume = "166",

series = "Smart Innovation, Systems and Technologies",

publisher = "Springer, Cham",

pages = "363--375",

editor = "Andrew Ball and Len Gelman and B.K.N. Rao",

booktitle = "Advances in Asset Management and Condition Monitoring, COMADEM 2019",

address = "Switzerland",

note = "32nd International Congress and Exhibition on Conditioning Monitoring and Diagnostic Engineering Management Conference, COMADEM 2019 ; Conference date: 03-09-2019 Through 05-09-2019",

url = "http://www.comadem2019.com/",

}

Cao, Y, Zeng, K, Li, S, Gu, F, Xu, Y & He, B 2020, Multiple-Model Fault Diagnosis Method for Gas Turbine Based on Soft Switch. in A Ball, L Gelman & BKN Rao (eds), Advances in Asset Management and Condition Monitoring, COMADEM 2019. vol. 166, Smart Innovation, Systems and Technologies, vol. 166, Springer, Cham, pp. 363-375, 32nd International Congress and Exhibition on Conditioning Monitoring and Diagnostic Engineering Management Conference, Huddersfield, United Kingdom, 3/09/19. https://doi.org/10.1007/978-3-030-57745-2_31

Multiple-Model Fault Diagnosis Method for Gas Turbine Based on Soft Switch. / Cao, Yunpeng; Zeng, Kehui; Li, Shuying et al.

Advances in Asset Management and Condition Monitoring, COMADEM 2019. ed. / Andrew Ball; Len Gelman; B.K.N. Rao. Vol. 166 Springer, Cham, 2020. p. 363-375 (Smart Innovation, Systems and Technologies; Vol. 166).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multiple-Model Fault Diagnosis Method for Gas Turbine Based on Soft Switch

AU - Cao, Yunpeng

AU - Zeng, Kehui

AU - Li, Shuying

AU - Gu, Fengshou

AU - Xu, Yuandong

AU - He, Bo

N1 - Conference code: 32

PY - 2020/8/28

Y1 - 2020/8/28

N2 - Fault diagnosis based on a multiple-model (MM) approach is an analytical redundancy method. In this paper, we mainly focus on the model switch optimizing problem of the MM method. First, a MM method for gas turbine gas path fault diagnosis was proposed, and the gas turbine state space models are established based on analytical linearization which can simulate the nonlinear dynamic characteristics at the operating points. Then model soft switch method was proposed based on recursive Bayesian to solve the problem that the established state space model is accurate merely in the vicinity of the operating points, and generates the combined generic model for the full operating condition and make it smoother. Finally, the fault simulation was carried out on a marine gas turbine which shows that the proposed method can diagnose both single gas path fault and multiple gas path faults.

AB - Fault diagnosis based on a multiple-model (MM) approach is an analytical redundancy method. In this paper, we mainly focus on the model switch optimizing problem of the MM method. First, a MM method for gas turbine gas path fault diagnosis was proposed, and the gas turbine state space models are established based on analytical linearization which can simulate the nonlinear dynamic characteristics at the operating points. Then model soft switch method was proposed based on recursive Bayesian to solve the problem that the established state space model is accurate merely in the vicinity of the operating points, and generates the combined generic model for the full operating condition and make it smoother. Finally, the fault simulation was carried out on a marine gas turbine which shows that the proposed method can diagnose both single gas path fault and multiple gas path faults.

KW - Fault diagnosis

KW - Gas turbine

KW - Model

KW - Multiple-model

KW - Soft switch

UR - http://www.scopus.com/inward/record.url?scp=85091318431&partnerID=8YFLogxK

UR - https://www.springer.com/gb/book/9783030577445

U2 - 10.1007/978-3-030-57745-2_31

DO - 10.1007/978-3-030-57745-2_31

M3 - Conference contribution

AN - SCOPUS:85091318431

SN - 9783030577445

VL - 166

T3 - Smart Innovation, Systems and Technologies

SP - 363

EP - 375

BT - Advances in Asset Management and Condition Monitoring, COMADEM 2019

A2 - Ball, Andrew

A2 - Gelman, Len

A2 - Rao, B.K.N.

PB - Springer, Cham

T2 - 32nd International Congress and Exhibition on Conditioning Monitoring and Diagnostic Engineering Management Conference

Y2 - 3 September 2019 through 5 September 2019

ER -

Multiple-Model Fault Diagnosis Method for Gas Turbine Based on Soft Switch

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this