Applications of neural networks to the real-time prediction of metal temperatures in gas turbine engine components

Michael Widrich; Alok Sinha; Eva Suarez; Brice Cassenti

doi:10.1115/GT2006-90317

Applications of neural networks to the real-time prediction of metal temperatures in gas turbine engine components

Michael Widrich, Alok Sinha, Eva Suarez, Brice Cassenti

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

1 Scopus citations

Abstract

Several methods for predicting metal temperatures in a turbine engine are presented. Proper Orthogonal Decomposition (POD) is used to determine the system modes from temperature data sets from an engine mission. The coefficients of the system POD modes are used to identify the system dynamics. The linear state space model in conjunction with a multi-layer feedforward neural network is shown to produce superior prediction values for untrained temperature data when compared to those values produced by the state space model alone.

Original language	English (US)
Title of host publication	Proceedings of the ASME Turbo Expo 2006 - Power for Land, Sea, and Air
Pages	561-569
Number of pages	9
Volume	2
DOIs	https://doi.org/10.1115/GT2006-90317
State	Published - 2006
Event	2006 ASME 51st Turbo Expo - Barcelona, Spain Duration: May 6 2006 → May 11 2006

Other

Other	2006 ASME 51st Turbo Expo
Country	Spain
City	Barcelona
Period	5/6/06 → 5/11/06

All Science Journal Classification (ASJC) codes

Engineering(all)

Access to Document

10.1115/GT2006-90317

Fingerprint Dive into the research topics of 'Applications of neural networks to the real-time prediction of metal temperatures in gas turbine engine components'. Together they form a unique fingerprint.

Cite this

@inproceedings{91edb19d33ee4761b5a0fbca7949fe4b,

title = "Applications of neural networks to the real-time prediction of metal temperatures in gas turbine engine components",

abstract = "Several methods for predicting metal temperatures in a turbine engine are presented. Proper Orthogonal Decomposition (POD) is used to determine the system modes from temperature data sets from an engine mission. The coefficients of the system POD modes are used to identify the system dynamics. The linear state space model in conjunction with a multi-layer feedforward neural network is shown to produce superior prediction values for untrained temperature data when compared to those values produced by the state space model alone.",

author = "Michael Widrich and Alok Sinha and Eva Suarez and Brice Cassenti",

year = "2006",

doi = "10.1115/GT2006-90317",

language = "English (US)",

isbn = "0791842371",

volume = "2",

pages = "561--569",

booktitle = "Proceedings of the ASME Turbo Expo 2006 - Power for Land, Sea, and Air",

note = "2006 ASME 51st Turbo Expo ; Conference date: 06-05-2006 Through 11-05-2006",

}

TY - GEN

T1 - Applications of neural networks to the real-time prediction of metal temperatures in gas turbine engine components

AU - Widrich, Michael

AU - Sinha, Alok

AU - Suarez, Eva

AU - Cassenti, Brice

PY - 2006

Y1 - 2006

N2 - Several methods for predicting metal temperatures in a turbine engine are presented. Proper Orthogonal Decomposition (POD) is used to determine the system modes from temperature data sets from an engine mission. The coefficients of the system POD modes are used to identify the system dynamics. The linear state space model in conjunction with a multi-layer feedforward neural network is shown to produce superior prediction values for untrained temperature data when compared to those values produced by the state space model alone.

AB - Several methods for predicting metal temperatures in a turbine engine are presented. Proper Orthogonal Decomposition (POD) is used to determine the system modes from temperature data sets from an engine mission. The coefficients of the system POD modes are used to identify the system dynamics. The linear state space model in conjunction with a multi-layer feedforward neural network is shown to produce superior prediction values for untrained temperature data when compared to those values produced by the state space model alone.

UR - http://www.scopus.com/inward/record.url?scp=33750831269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750831269&partnerID=8YFLogxK

U2 - 10.1115/GT2006-90317

DO - 10.1115/GT2006-90317

M3 - Conference contribution

AN - SCOPUS:33750831269

SN - 0791842371

SN - 9780791842379

VL - 2

SP - 561

EP - 569

BT - Proceedings of the ASME Turbo Expo 2006 - Power for Land, Sea, and Air

T2 - 2006 ASME 51st Turbo Expo

Y2 - 6 May 2006 through 11 May 2006

ER -

Applications of neural networks to the real-time prediction of metal temperatures in gas turbine engine components

Abstract

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this