Loading…
Fault Detection for Gas Turbine Hot Components Based on a Convolutional Neural Network
Gas turbine hot component failures often cause catastrophic consequences. Fault detection can improve the availability and economy of hot components. The exhaust gas temperature (EGT) profile is usually used to monitor the performance of the hot components. The EGT profile is uniform when the hot co...
Saved in:
Published in: | Energies (Basel) 2018-08, Vol.11 (8), p.2149 |
---|---|
Main Authors: | , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c361t-b1041b47c16502a5daea709ff6e499924101a7faa3eec897ee839a91bd3cf7e23 |
---|---|
cites | cdi_FETCH-LOGICAL-c361t-b1041b47c16502a5daea709ff6e499924101a7faa3eec897ee839a91bd3cf7e23 |
container_end_page | |
container_issue | 8 |
container_start_page | 2149 |
container_title | Energies (Basel) |
container_volume | 11 |
creator | Liu, Jiao Liu, Jinfu Yu, Daren Kang, Myeongsu Yan, Weizhong Wang, Zhongqi Pecht, Michael |
description | Gas turbine hot component failures often cause catastrophic consequences. Fault detection can improve the availability and economy of hot components. The exhaust gas temperature (EGT) profile is usually used to monitor the performance of the hot components. The EGT profile is uniform when the hot component is healthy, whereas hot component faults lead to large temperature differences between different EGT values. The EGT profile swirl under different operating and ambient conditions also cause temperature differences. Therefore, the influence of EGT profile swirl on EGT values must be eliminated. To improve the detection sensitivity, this paper develops a fault detection method for hot components based on a convolutional neural network (CNN). This paper demonstrates that a CNN can extract the information between adjacent EGT values and consider the impact of the EGT profile swirl. This paper reveals, in principle, that a CNN is a viable solution for dealing with fault detection for hot components. Based on the distribution characteristics of EGT thermocouples, the circular padding method is developed in the CNN. The sensitivity of the developed method is verified by real-world data. Moreover, the developed method is visualized in detail. The visualization results reveal that the CNN effectively considers the influence of the EGT profile swirl. |
doi_str_mv | 10.3390/en11082149 |
format | article |
fullrecord | <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_45922ad13d2a4f5a950441aa85b4a275</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_45922ad13d2a4f5a950441aa85b4a275</doaj_id><sourcerecordid>2108522317</sourcerecordid><originalsourceid>FETCH-LOGICAL-c361t-b1041b47c16502a5daea709ff6e499924101a7faa3eec897ee839a91bd3cf7e23</originalsourceid><addsrcrecordid>eNpNUctOwzAQjBBIVNALX2CJG1LAazsPH6HQh1TBpXC1NskGpaRxsR0Qf0_aImAvsxrNzmp3ougC-LWUmt9QB8BzAUofRSPQOo2BZ_L4X38ajb1f86GkBCnlKHqZYt8Gdk-BytDYjtXWsRl6tupd0XTE5jawid1sbUdd8OwOPVVs0OHAdh-27XdT2LJH6t0ewqd1b-fRSY2tp_EPnkXP04fVZB4vn2aLye0yLmUKIS6AKyhUVkKacIFJhYQZ13WdktJaCwUcMKsRJVGZ64wolxo1FJUs64yEPIsWB9_K4tpsXbNB92UsNmZPWPdq0IWmbMmoRAuBFchKoKoT1AlXChDzpFAosmTwujx4bZ1978kHs7a9G27zRgx_TYSQkA2qq4OqdNZ7R_XvVuBmF4P5i0F-A6PEeIM</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2108522317</pqid></control><display><type>article</type><title>Fault Detection for Gas Turbine Hot Components Based on a Convolutional Neural Network</title><source>ProQuest Publicly Available Content database</source><creator>Liu, Jiao ; Liu, Jinfu ; Yu, Daren ; Kang, Myeongsu ; Yan, Weizhong ; Wang, Zhongqi ; Pecht, Michael</creator><creatorcontrib>Liu, Jiao ; Liu, Jinfu ; Yu, Daren ; Kang, Myeongsu ; Yan, Weizhong ; Wang, Zhongqi ; Pecht, Michael</creatorcontrib><description>Gas turbine hot component failures often cause catastrophic consequences. Fault detection can improve the availability and economy of hot components. The exhaust gas temperature (EGT) profile is usually used to monitor the performance of the hot components. The EGT profile is uniform when the hot component is healthy, whereas hot component faults lead to large temperature differences between different EGT values. The EGT profile swirl under different operating and ambient conditions also cause temperature differences. Therefore, the influence of EGT profile swirl on EGT values must be eliminated. To improve the detection sensitivity, this paper develops a fault detection method for hot components based on a convolutional neural network (CNN). This paper demonstrates that a CNN can extract the information between adjacent EGT values and consider the impact of the EGT profile swirl. This paper reveals, in principle, that a CNN is a viable solution for dealing with fault detection for hot components. Based on the distribution characteristics of EGT thermocouples, the circular padding method is developed in the CNN. The sensitivity of the developed method is verified by real-world data. Moreover, the developed method is visualized in detail. The visualization results reveal that the CNN effectively considers the influence of the EGT profile swirl.</description><identifier>ISSN: 1996-1073</identifier><identifier>EISSN: 1996-1073</identifier><identifier>DOI: 10.3390/en11082149</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>convolutional neural network (CNN) ; Cooling ; exhaust gas temperature (EGT) ; Exhaust gases ; Fault detection ; Gas temperature ; gas turbine ; Gas turbine engines ; Gas turbines ; hot component ; Information processing ; Neural networks ; Sensitivity ; Temperature effects ; Temperature gradients ; Thermocouples</subject><ispartof>Energies (Basel), 2018-08, Vol.11 (8), p.2149</ispartof><rights>2018. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c361t-b1041b47c16502a5daea709ff6e499924101a7faa3eec897ee839a91bd3cf7e23</citedby><cites>FETCH-LOGICAL-c361t-b1041b47c16502a5daea709ff6e499924101a7faa3eec897ee839a91bd3cf7e23</cites><orcidid>0000-0002-7916-8476</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925,37012</link.rule.ids></links><search><creatorcontrib>Liu, Jiao</creatorcontrib><creatorcontrib>Liu, Jinfu</creatorcontrib><creatorcontrib>Yu, Daren</creatorcontrib><creatorcontrib>Kang, Myeongsu</creatorcontrib><creatorcontrib>Yan, Weizhong</creatorcontrib><creatorcontrib>Wang, Zhongqi</creatorcontrib><creatorcontrib>Pecht, Michael</creatorcontrib><title>Fault Detection for Gas Turbine Hot Components Based on a Convolutional Neural Network</title><title>Energies (Basel)</title><description>Gas turbine hot component failures often cause catastrophic consequences. Fault detection can improve the availability and economy of hot components. The exhaust gas temperature (EGT) profile is usually used to monitor the performance of the hot components. The EGT profile is uniform when the hot component is healthy, whereas hot component faults lead to large temperature differences between different EGT values. The EGT profile swirl under different operating and ambient conditions also cause temperature differences. Therefore, the influence of EGT profile swirl on EGT values must be eliminated. To improve the detection sensitivity, this paper develops a fault detection method for hot components based on a convolutional neural network (CNN). This paper demonstrates that a CNN can extract the information between adjacent EGT values and consider the impact of the EGT profile swirl. This paper reveals, in principle, that a CNN is a viable solution for dealing with fault detection for hot components. Based on the distribution characteristics of EGT thermocouples, the circular padding method is developed in the CNN. The sensitivity of the developed method is verified by real-world data. Moreover, the developed method is visualized in detail. The visualization results reveal that the CNN effectively considers the influence of the EGT profile swirl.</description><subject>convolutional neural network (CNN)</subject><subject>Cooling</subject><subject>exhaust gas temperature (EGT)</subject><subject>Exhaust gases</subject><subject>Fault detection</subject><subject>Gas temperature</subject><subject>gas turbine</subject><subject>Gas turbine engines</subject><subject>Gas turbines</subject><subject>hot component</subject><subject>Information processing</subject><subject>Neural networks</subject><subject>Sensitivity</subject><subject>Temperature effects</subject><subject>Temperature gradients</subject><subject>Thermocouples</subject><issn>1996-1073</issn><issn>1996-1073</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNpNUctOwzAQjBBIVNALX2CJG1LAazsPH6HQh1TBpXC1NskGpaRxsR0Qf0_aImAvsxrNzmp3ougC-LWUmt9QB8BzAUofRSPQOo2BZ_L4X38ajb1f86GkBCnlKHqZYt8Gdk-BytDYjtXWsRl6tupd0XTE5jawid1sbUdd8OwOPVVs0OHAdh-27XdT2LJH6t0ewqd1b-fRSY2tp_EPnkXP04fVZB4vn2aLye0yLmUKIS6AKyhUVkKacIFJhYQZ13WdktJaCwUcMKsRJVGZ64wolxo1FJUs64yEPIsWB9_K4tpsXbNB92UsNmZPWPdq0IWmbMmoRAuBFchKoKoT1AlXChDzpFAosmTwujx4bZ1978kHs7a9G27zRgx_TYSQkA2qq4OqdNZ7R_XvVuBmF4P5i0F-A6PEeIM</recordid><startdate>20180801</startdate><enddate>20180801</enddate><creator>Liu, Jiao</creator><creator>Liu, Jinfu</creator><creator>Yu, Daren</creator><creator>Kang, Myeongsu</creator><creator>Yan, Weizhong</creator><creator>Wang, Zhongqi</creator><creator>Pecht, Michael</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-7916-8476</orcidid></search><sort><creationdate>20180801</creationdate><title>Fault Detection for Gas Turbine Hot Components Based on a Convolutional Neural Network</title><author>Liu, Jiao ; Liu, Jinfu ; Yu, Daren ; Kang, Myeongsu ; Yan, Weizhong ; Wang, Zhongqi ; Pecht, Michael</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c361t-b1041b47c16502a5daea709ff6e499924101a7faa3eec897ee839a91bd3cf7e23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>convolutional neural network (CNN)</topic><topic>Cooling</topic><topic>exhaust gas temperature (EGT)</topic><topic>Exhaust gases</topic><topic>Fault detection</topic><topic>Gas temperature</topic><topic>gas turbine</topic><topic>Gas turbine engines</topic><topic>Gas turbines</topic><topic>hot component</topic><topic>Information processing</topic><topic>Neural networks</topic><topic>Sensitivity</topic><topic>Temperature effects</topic><topic>Temperature gradients</topic><topic>Thermocouples</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Liu, Jiao</creatorcontrib><creatorcontrib>Liu, Jinfu</creatorcontrib><creatorcontrib>Yu, Daren</creatorcontrib><creatorcontrib>Kang, Myeongsu</creatorcontrib><creatorcontrib>Yan, Weizhong</creatorcontrib><creatorcontrib>Wang, Zhongqi</creatorcontrib><creatorcontrib>Pecht, Michael</creatorcontrib><collection>CrossRef</collection><collection>Directory of Open Access Journals</collection><jtitle>Energies (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Jiao</au><au>Liu, Jinfu</au><au>Yu, Daren</au><au>Kang, Myeongsu</au><au>Yan, Weizhong</au><au>Wang, Zhongqi</au><au>Pecht, Michael</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Fault Detection for Gas Turbine Hot Components Based on a Convolutional Neural Network</atitle><jtitle>Energies (Basel)</jtitle><date>2018-08-01</date><risdate>2018</risdate><volume>11</volume><issue>8</issue><spage>2149</spage><pages>2149-</pages><issn>1996-1073</issn><eissn>1996-1073</eissn><abstract>Gas turbine hot component failures often cause catastrophic consequences. Fault detection can improve the availability and economy of hot components. The exhaust gas temperature (EGT) profile is usually used to monitor the performance of the hot components. The EGT profile is uniform when the hot component is healthy, whereas hot component faults lead to large temperature differences between different EGT values. The EGT profile swirl under different operating and ambient conditions also cause temperature differences. Therefore, the influence of EGT profile swirl on EGT values must be eliminated. To improve the detection sensitivity, this paper develops a fault detection method for hot components based on a convolutional neural network (CNN). This paper demonstrates that a CNN can extract the information between adjacent EGT values and consider the impact of the EGT profile swirl. This paper reveals, in principle, that a CNN is a viable solution for dealing with fault detection for hot components. Based on the distribution characteristics of EGT thermocouples, the circular padding method is developed in the CNN. The sensitivity of the developed method is verified by real-world data. Moreover, the developed method is visualized in detail. The visualization results reveal that the CNN effectively considers the influence of the EGT profile swirl.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/en11082149</doi><orcidid>https://orcid.org/0000-0002-7916-8476</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1996-1073 |
ispartof | Energies (Basel), 2018-08, Vol.11 (8), p.2149 |
issn | 1996-1073 1996-1073 |
language | eng |
recordid | cdi_doaj_primary_oai_doaj_org_article_45922ad13d2a4f5a950441aa85b4a275 |
source | ProQuest Publicly Available Content database |
subjects | convolutional neural network (CNN) Cooling exhaust gas temperature (EGT) Exhaust gases Fault detection Gas temperature gas turbine Gas turbine engines Gas turbines hot component Information processing Neural networks Sensitivity Temperature effects Temperature gradients Thermocouples |
title | Fault Detection for Gas Turbine Hot Components Based on a Convolutional Neural Network |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T19%3A37%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Fault%20Detection%20for%20Gas%20Turbine%20Hot%20Components%20Based%20on%20a%20Convolutional%20Neural%20Network&rft.jtitle=Energies%20(Basel)&rft.au=Liu,%20Jiao&rft.date=2018-08-01&rft.volume=11&rft.issue=8&rft.spage=2149&rft.pages=2149-&rft.issn=1996-1073&rft.eissn=1996-1073&rft_id=info:doi/10.3390/en11082149&rft_dat=%3Cproquest_doaj_%3E2108522317%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c361t-b1041b47c16502a5daea709ff6e499924101a7faa3eec897ee839a91bd3cf7e23%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2108522317&rft_id=info:pmid/&rfr_iscdi=true |