A novel time-span input neural network for accurate municipal solid waste incineration boiler steam temperature prediction
A novel time-span input neural network was developed to accurately predict the trend of the main steam temperature of a 750-t/d waste incineration boiler. Its historical operating data were used to retrieve sensitive parameters for the boiler output steam temperature by correlation analysis. Then, t...
Gespeichert in:
Veröffentlicht in: | Journal of Zhejiang University. A. Science 2021-10, Vol.22 (10), p.777-791 |
---|---|
Hauptverfasser: | , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 791 |
---|---|
container_issue | 10 |
container_start_page | 777 |
container_title | Journal of Zhejiang University. A. Science |
container_volume | 22 |
creator | Hu, Qin-xuan Long, Ji-sheng Wang, Shou-kang He, Jun-jie Bai, Li Du, Hai-liang Huang, Qun-xing |
description | A novel time-span input neural network was developed to accurately predict the trend of the main steam temperature of a 750-t/d waste incineration boiler. Its historical operating data were used to retrieve sensitive parameters for the boiler output steam temperature by correlation analysis. Then, the 15 most sensitive parameters with specified time spans were selected as neural network inputs. An external testing set was introduced to objectively evaluate the neural network prediction capability. The results show that, compared with the traditional prediction method, the time-span input framework model can achieve better prediction performance and has a greater capability for generalization. The maximum average prediction error can be controlled below 0.2 °C and 1.5 °C in the next 60 s and 5 min, respectively. In addition, setting a reasonable terminal training threshold can effectively avoid overfitting. An importance analysis of the parameters indicates that the main steam temperature and the average temperature around the high-temperature superheater are the two most important variables of the input parameters; the former affects the overall prediction and the latter affects the long-term prediction performance. |
doi_str_mv | 10.1631/jzus.A2000529 |
format | Article |
fullrecord | <record><control><sourceid>wanfang_jour_proqu</sourceid><recordid>TN_cdi_wanfang_journals_zjdxxb_e202110003</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><wanfj_id>zjdxxb_e202110003</wanfj_id><sourcerecordid>zjdxxb_e202110003</sourcerecordid><originalsourceid>FETCH-LOGICAL-c338t-92444cb2bb77a202af267126d4f717ec8903034549ddbc47e634ee68a2988bab3</originalsourceid><addsrcrecordid>eNpt0c9LwzAUB_AiCs7p0XvAk4fO_GiS9jiGv2DgRcFbSdPXkdkmNWnd3F9vxpRdPL3w3icvkG-SXBM8I4KRu_VuDLM5xRhzWpwkE5ILmhIp-Wk8C8lSLvj7eXIRwjoSiYWcJLs5su4LWjSYDtLQK4uM7ccBWRi9amMZNs5_oMZ5pLSOvQFQN1qjTR_HwbWmRhsVYtdYbSxEYJxFlTMteBT7qkMDdP1-MHpAvYfa6L25TM4a1Qa4-q3T5O3h_nXxlC5fHp8X82WqGcuHtKBZlumKVpWUimKqGiokoaLOGkkk6LzADLOMZ0VdVzqTIFgGIHJFizyvVMWmye1h70bZRtlVuXajt_HFcreut9uqhLiVkPhtLNqbg-29-xwhDEdMec4xLzinUaUHpb0LwUNT9t50yn-XBJf7KMp9FOVfFNHPDj5EZ1fgj1v_v_ADOlOOaQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2585059552</pqid></control><display><type>article</type><title>A novel time-span input neural network for accurate municipal solid waste incineration boiler steam temperature prediction</title><source>SpringerNature Journals</source><source>Alma/SFX Local Collection</source><creator>Hu, Qin-xuan ; Long, Ji-sheng ; Wang, Shou-kang ; He, Jun-jie ; Bai, Li ; Du, Hai-liang ; Huang, Qun-xing</creator><creatorcontrib>Hu, Qin-xuan ; Long, Ji-sheng ; Wang, Shou-kang ; He, Jun-jie ; Bai, Li ; Du, Hai-liang ; Huang, Qun-xing</creatorcontrib><description>A novel time-span input neural network was developed to accurately predict the trend of the main steam temperature of a 750-t/d waste incineration boiler. Its historical operating data were used to retrieve sensitive parameters for the boiler output steam temperature by correlation analysis. Then, the 15 most sensitive parameters with specified time spans were selected as neural network inputs. An external testing set was introduced to objectively evaluate the neural network prediction capability. The results show that, compared with the traditional prediction method, the time-span input framework model can achieve better prediction performance and has a greater capability for generalization. The maximum average prediction error can be controlled below 0.2 °C and 1.5 °C in the next 60 s and 5 min, respectively. In addition, setting a reasonable terminal training threshold can effectively avoid overfitting. An importance analysis of the parameters indicates that the main steam temperature and the average temperature around the high-temperature superheater are the two most important variables of the input parameters; the former affects the overall prediction and the latter affects the long-term prediction performance.</description><identifier>ISSN: 1673-565X</identifier><identifier>EISSN: 1862-1775</identifier><identifier>DOI: 10.1631/jzus.A2000529</identifier><language>eng</language><publisher>Hangzhou: Zhejiang University Press</publisher><subject>Boilers ; Civil Engineering ; Classical and Continuum Physics ; Combustion ; Correlation analysis ; Engineering ; High temperature ; Incineration ; Industrial Chemistry/Chemical Engineering ; Mechanical Engineering ; Municipal solid waste ; Municipal waste management ; Neural networks ; Parameter sensitivity ; Performance prediction ; Predictions ; Solid waste management ; Steam ; Waste disposal</subject><ispartof>Journal of Zhejiang University. A. Science, 2021-10, Vol.22 (10), p.777-791</ispartof><rights>Zhejiang University Press 2021</rights><rights>Zhejiang University Press 2021.</rights><rights>Copyright © Wanfang Data Co. Ltd. All Rights Reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c338t-92444cb2bb77a202af267126d4f717ec8903034549ddbc47e634ee68a2988bab3</citedby><cites>FETCH-LOGICAL-c338t-92444cb2bb77a202af267126d4f717ec8903034549ddbc47e634ee68a2988bab3</cites><orcidid>0000-0003-1557-3955 ; 0000-0001-5586-7400</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttp://www.wanfangdata.com.cn/images/PeriodicalImages/zjdxxb-e/zjdxxb-e.jpg</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1631/jzus.A2000529$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1631/jzus.A2000529$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Hu, Qin-xuan</creatorcontrib><creatorcontrib>Long, Ji-sheng</creatorcontrib><creatorcontrib>Wang, Shou-kang</creatorcontrib><creatorcontrib>He, Jun-jie</creatorcontrib><creatorcontrib>Bai, Li</creatorcontrib><creatorcontrib>Du, Hai-liang</creatorcontrib><creatorcontrib>Huang, Qun-xing</creatorcontrib><title>A novel time-span input neural network for accurate municipal solid waste incineration boiler steam temperature prediction</title><title>Journal of Zhejiang University. A. Science</title><addtitle>J. Zhejiang Univ. Sci. A</addtitle><description>A novel time-span input neural network was developed to accurately predict the trend of the main steam temperature of a 750-t/d waste incineration boiler. Its historical operating data were used to retrieve sensitive parameters for the boiler output steam temperature by correlation analysis. Then, the 15 most sensitive parameters with specified time spans were selected as neural network inputs. An external testing set was introduced to objectively evaluate the neural network prediction capability. The results show that, compared with the traditional prediction method, the time-span input framework model can achieve better prediction performance and has a greater capability for generalization. The maximum average prediction error can be controlled below 0.2 °C and 1.5 °C in the next 60 s and 5 min, respectively. In addition, setting a reasonable terminal training threshold can effectively avoid overfitting. An importance analysis of the parameters indicates that the main steam temperature and the average temperature around the high-temperature superheater are the two most important variables of the input parameters; the former affects the overall prediction and the latter affects the long-term prediction performance.</description><subject>Boilers</subject><subject>Civil Engineering</subject><subject>Classical and Continuum Physics</subject><subject>Combustion</subject><subject>Correlation analysis</subject><subject>Engineering</subject><subject>High temperature</subject><subject>Incineration</subject><subject>Industrial Chemistry/Chemical Engineering</subject><subject>Mechanical Engineering</subject><subject>Municipal solid waste</subject><subject>Municipal waste management</subject><subject>Neural networks</subject><subject>Parameter sensitivity</subject><subject>Performance prediction</subject><subject>Predictions</subject><subject>Solid waste management</subject><subject>Steam</subject><subject>Waste disposal</subject><issn>1673-565X</issn><issn>1862-1775</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNpt0c9LwzAUB_AiCs7p0XvAk4fO_GiS9jiGv2DgRcFbSdPXkdkmNWnd3F9vxpRdPL3w3icvkG-SXBM8I4KRu_VuDLM5xRhzWpwkE5ILmhIp-Wk8C8lSLvj7eXIRwjoSiYWcJLs5su4LWjSYDtLQK4uM7ccBWRi9amMZNs5_oMZ5pLSOvQFQN1qjTR_HwbWmRhsVYtdYbSxEYJxFlTMteBT7qkMDdP1-MHpAvYfa6L25TM4a1Qa4-q3T5O3h_nXxlC5fHp8X82WqGcuHtKBZlumKVpWUimKqGiokoaLOGkkk6LzADLOMZ0VdVzqTIFgGIHJFizyvVMWmye1h70bZRtlVuXajt_HFcreut9uqhLiVkPhtLNqbg-29-xwhDEdMec4xLzinUaUHpb0LwUNT9t50yn-XBJf7KMp9FOVfFNHPDj5EZ1fgj1v_v_ADOlOOaQ</recordid><startdate>20211001</startdate><enddate>20211001</enddate><creator>Hu, Qin-xuan</creator><creator>Long, Ji-sheng</creator><creator>Wang, Shou-kang</creator><creator>He, Jun-jie</creator><creator>Bai, Li</creator><creator>Du, Hai-liang</creator><creator>Huang, Qun-xing</creator><general>Zhejiang University Press</general><general>Springer Nature B.V</general><general>State Key Laboratory of Clean Energy Utilization,Institute of Thermal Engineering,Zhejiang University,Hangzhou 310027,China%Shanghai SUS Environment Co.Ltd.,Shanghai 201703,China</general><scope>AAYXX</scope><scope>CITATION</scope><scope>2B.</scope><scope>4A8</scope><scope>92I</scope><scope>93N</scope><scope>PSX</scope><scope>TCJ</scope><orcidid>https://orcid.org/0000-0003-1557-3955</orcidid><orcidid>https://orcid.org/0000-0001-5586-7400</orcidid></search><sort><creationdate>20211001</creationdate><title>A novel time-span input neural network for accurate municipal solid waste incineration boiler steam temperature prediction</title><author>Hu, Qin-xuan ; Long, Ji-sheng ; Wang, Shou-kang ; He, Jun-jie ; Bai, Li ; Du, Hai-liang ; Huang, Qun-xing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c338t-92444cb2bb77a202af267126d4f717ec8903034549ddbc47e634ee68a2988bab3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Boilers</topic><topic>Civil Engineering</topic><topic>Classical and Continuum Physics</topic><topic>Combustion</topic><topic>Correlation analysis</topic><topic>Engineering</topic><topic>High temperature</topic><topic>Incineration</topic><topic>Industrial Chemistry/Chemical Engineering</topic><topic>Mechanical Engineering</topic><topic>Municipal solid waste</topic><topic>Municipal waste management</topic><topic>Neural networks</topic><topic>Parameter sensitivity</topic><topic>Performance prediction</topic><topic>Predictions</topic><topic>Solid waste management</topic><topic>Steam</topic><topic>Waste disposal</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hu, Qin-xuan</creatorcontrib><creatorcontrib>Long, Ji-sheng</creatorcontrib><creatorcontrib>Wang, Shou-kang</creatorcontrib><creatorcontrib>He, Jun-jie</creatorcontrib><creatorcontrib>Bai, Li</creatorcontrib><creatorcontrib>Du, Hai-liang</creatorcontrib><creatorcontrib>Huang, Qun-xing</creatorcontrib><collection>CrossRef</collection><collection>Wanfang Data Journals - Hong Kong</collection><collection>WANFANG Data Centre</collection><collection>Wanfang Data Journals</collection><collection>万方数据期刊 - 香港版</collection><collection>China Online Journals (COJ)</collection><collection>China Online Journals (COJ)</collection><jtitle>Journal of Zhejiang University. A. Science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hu, Qin-xuan</au><au>Long, Ji-sheng</au><au>Wang, Shou-kang</au><au>He, Jun-jie</au><au>Bai, Li</au><au>Du, Hai-liang</au><au>Huang, Qun-xing</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A novel time-span input neural network for accurate municipal solid waste incineration boiler steam temperature prediction</atitle><jtitle>Journal of Zhejiang University. A. Science</jtitle><stitle>J. Zhejiang Univ. Sci. A</stitle><date>2021-10-01</date><risdate>2021</risdate><volume>22</volume><issue>10</issue><spage>777</spage><epage>791</epage><pages>777-791</pages><issn>1673-565X</issn><eissn>1862-1775</eissn><abstract>A novel time-span input neural network was developed to accurately predict the trend of the main steam temperature of a 750-t/d waste incineration boiler. Its historical operating data were used to retrieve sensitive parameters for the boiler output steam temperature by correlation analysis. Then, the 15 most sensitive parameters with specified time spans were selected as neural network inputs. An external testing set was introduced to objectively evaluate the neural network prediction capability. The results show that, compared with the traditional prediction method, the time-span input framework model can achieve better prediction performance and has a greater capability for generalization. The maximum average prediction error can be controlled below 0.2 °C and 1.5 °C in the next 60 s and 5 min, respectively. In addition, setting a reasonable terminal training threshold can effectively avoid overfitting. An importance analysis of the parameters indicates that the main steam temperature and the average temperature around the high-temperature superheater are the two most important variables of the input parameters; the former affects the overall prediction and the latter affects the long-term prediction performance.</abstract><cop>Hangzhou</cop><pub>Zhejiang University Press</pub><doi>10.1631/jzus.A2000529</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0003-1557-3955</orcidid><orcidid>https://orcid.org/0000-0001-5586-7400</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1673-565X |
ispartof | Journal of Zhejiang University. A. Science, 2021-10, Vol.22 (10), p.777-791 |
issn | 1673-565X 1862-1775 |
language | eng |
recordid | cdi_wanfang_journals_zjdxxb_e202110003 |
source | SpringerNature Journals; Alma/SFX Local Collection |
subjects | Boilers Civil Engineering Classical and Continuum Physics Combustion Correlation analysis Engineering High temperature Incineration Industrial Chemistry/Chemical Engineering Mechanical Engineering Municipal solid waste Municipal waste management Neural networks Parameter sensitivity Performance prediction Predictions Solid waste management Steam Waste disposal |
title | A novel time-span input neural network for accurate municipal solid waste incineration boiler steam temperature prediction |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T17%3A27%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-wanfang_jour_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20novel%20time-span%20input%20neural%20network%20for%20accurate%20municipal%20solid%20waste%20incineration%20boiler%20steam%20temperature%20prediction&rft.jtitle=Journal%20of%20Zhejiang%20University.%20A.%20Science&rft.au=Hu,%20Qin-xuan&rft.date=2021-10-01&rft.volume=22&rft.issue=10&rft.spage=777&rft.epage=791&rft.pages=777-791&rft.issn=1673-565X&rft.eissn=1862-1775&rft_id=info:doi/10.1631/jzus.A2000529&rft_dat=%3Cwanfang_jour_proqu%3Ezjdxxb_e202110003%3C/wanfang_jour_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2585059552&rft_id=info:pmid/&rft_wanfj_id=zjdxxb_e202110003&rfr_iscdi=true |