Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor
In this research a dynamic grey box model (GBM) of ethylene oxide (EO) fixed bed reactor has been presented. In the first step of the study, kinetic model of the existing reactions was obtained using artificial neural network (ANN) approach. In order to build the ANN model industrial data of a typic...
Gespeichert in:
| Veröffentlicht in: | Fuel processing technology 2011-09, Vol.92 (9), p.1725-1732 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1732 |
|---|---|
| container_issue | 9 |
| container_start_page | 1725 |
| container_title | Fuel processing technology |
| container_volume | 92 |
| creator | Zahedi, G. Lohi, A. Mahdi, K.A. |
| description | In this research a dynamic grey box model (GBM) of ethylene oxide (EO) fixed bed reactor has been presented. In the first step of the study, kinetic model of the existing reactions was obtained using artificial neural network (ANN) approach. In order to build the ANN model industrial data of a typical EO reactor were employed. Time, C
2H
4, C
2H
4O, CO
2, H
2O and O
2 mole fractions were network inputs and the multiplication of reaction rate and catalyst deactivation (
r
*
a)was ANN output. From 164 data, 109 data were employed to train ANN. After employing different training algorithms, it was found that, the radial basis function network (RBFN) training algorithm provides the best estimations of the data. This best obtained network was tested against fifty five unseen data. The network estimations were close to unseen data which confirmed generalization capability of the obtained network.
In the next step of study, (
r
*
a) was estimated with ANN and then the hybrid model of the reactor was solved. Simulation results were compared with EO mechanistic model and also with plant industrial data. It was found that GBM is 8.437 times more accurate than the mechanistic model.
► ANN can model rate of ethylen epoxidation. ► Grey box model is more accurate than mechanistic model. ► Grey box model provides good extrapolation. |
| doi_str_mv | 10.1016/j.fuproc.2011.04.022 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_896231859</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0378382011001433</els_id><sourcerecordid>896231859</sourcerecordid><originalsourceid>FETCH-LOGICAL-c392t-1c3a133abc6fb5b904e5b75447bc51395932c1cbca172c4037465a7cee6b675a3</originalsourceid><addsrcrecordid>eNp9kM1qGzEURkVIIY6bNwhkNqGrmepfM5tCMGkcCGSRZC00d-44MmPLlcalfvvKGdPuspIQ53767iHkmtGKUaa_r6t-v4sBKk4Zq6isKOdnZMZqI0rD6vqczKgwdSlqTi_IZUprSqlSjZmRxfLQRt8Vm9Dh4LerIvQFju-HAbdYjOH_PfzxHRbvOGIMq_wQ9qmI6GAM8Sv50rsh4dXpnJO3n_evi2X59PzwuLh7KkE0fCwZCMeEcC3ovlVtQyWq1igpTQuKiUY1ggODFhwzHGRuLLVyBhB1q41yYk6-Tbl51197TKPd-AQ4DO6jjq0bzQWrc86cyImEGFKK2Ntd9BsXD5ZRe1Rm13ZSZo_KLJU2K8tjt6cPXAI39NFtwad_s1xyI5jSmbuZuN4F61YxM28vOUhnrVpLLjPxYyIw-_jtMdoEHreAnY8Io-2C_7zKX_5_jPo</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>896231859</pqid></control><display><type>article</type><title>Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor</title><source>Elsevier ScienceDirect Journals</source><creator>Zahedi, G. ; Lohi, A. ; Mahdi, K.A.</creator><creatorcontrib>Zahedi, G. ; Lohi, A. ; Mahdi, K.A.</creatorcontrib><description>In this research a dynamic grey box model (GBM) of ethylene oxide (EO) fixed bed reactor has been presented. In the first step of the study, kinetic model of the existing reactions was obtained using artificial neural network (ANN) approach. In order to build the ANN model industrial data of a typical EO reactor were employed. Time, C
2H
4, C
2H
4O, CO
2, H
2O and O
2 mole fractions were network inputs and the multiplication of reaction rate and catalyst deactivation (
r
*
a)was ANN output. From 164 data, 109 data were employed to train ANN. After employing different training algorithms, it was found that, the radial basis function network (RBFN) training algorithm provides the best estimations of the data. This best obtained network was tested against fifty five unseen data. The network estimations were close to unseen data which confirmed generalization capability of the obtained network.
In the next step of study, (
r
*
a) was estimated with ANN and then the hybrid model of the reactor was solved. Simulation results were compared with EO mechanistic model and also with plant industrial data. It was found that GBM is 8.437 times more accurate than the mechanistic model.
► ANN can model rate of ethylen epoxidation. ► Grey box model is more accurate than mechanistic model. ► Grey box model provides good extrapolation.</description><identifier>ISSN: 0378-3820</identifier><identifier>EISSN: 1873-7188</identifier><identifier>DOI: 10.1016/j.fuproc.2011.04.022</identifier><identifier>CODEN: FPTEDY</identifier><language>eng</language><publisher>Amsterdam: Elsevier B.V</publisher><subject>Algorithms ; Applied sciences ; carbon dioxide ; catalysts ; Dynamic modeling ; Energy ; Energy. Thermal use of fuels ; ethylene ; Ethylene oxide ; Ethylene oxide reactor ; Exact sciences and technology ; Fuels ; Grey box modeling ; Learning theory ; Networks ; Neural network ; Neural networks ; oxygen ; Reactors ; Simulation ; Training ; Trains</subject><ispartof>Fuel processing technology, 2011-09, Vol.92 (9), p.1725-1732</ispartof><rights>2011 Elsevier B.V.</rights><rights>2015 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c392t-1c3a133abc6fb5b904e5b75447bc51395932c1cbca172c4037465a7cee6b675a3</citedby><cites>FETCH-LOGICAL-c392t-1c3a133abc6fb5b904e5b75447bc51395932c1cbca172c4037465a7cee6b675a3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0378382011001433$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65306</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=24273156$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Zahedi, G.</creatorcontrib><creatorcontrib>Lohi, A.</creatorcontrib><creatorcontrib>Mahdi, K.A.</creatorcontrib><title>Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor</title><title>Fuel processing technology</title><description>In this research a dynamic grey box model (GBM) of ethylene oxide (EO) fixed bed reactor has been presented. In the first step of the study, kinetic model of the existing reactions was obtained using artificial neural network (ANN) approach. In order to build the ANN model industrial data of a typical EO reactor were employed. Time, C
2H
4, C
2H
4O, CO
2, H
2O and O
2 mole fractions were network inputs and the multiplication of reaction rate and catalyst deactivation (
r
*
a)was ANN output. From 164 data, 109 data were employed to train ANN. After employing different training algorithms, it was found that, the radial basis function network (RBFN) training algorithm provides the best estimations of the data. This best obtained network was tested against fifty five unseen data. The network estimations were close to unseen data which confirmed generalization capability of the obtained network.
In the next step of study, (
r
*
a) was estimated with ANN and then the hybrid model of the reactor was solved. Simulation results were compared with EO mechanistic model and also with plant industrial data. It was found that GBM is 8.437 times more accurate than the mechanistic model.
► ANN can model rate of ethylen epoxidation. ► Grey box model is more accurate than mechanistic model. ► Grey box model provides good extrapolation.</description><subject>Algorithms</subject><subject>Applied sciences</subject><subject>carbon dioxide</subject><subject>catalysts</subject><subject>Dynamic modeling</subject><subject>Energy</subject><subject>Energy. Thermal use of fuels</subject><subject>ethylene</subject><subject>Ethylene oxide</subject><subject>Ethylene oxide reactor</subject><subject>Exact sciences and technology</subject><subject>Fuels</subject><subject>Grey box modeling</subject><subject>Learning theory</subject><subject>Networks</subject><subject>Neural network</subject><subject>Neural networks</subject><subject>oxygen</subject><subject>Reactors</subject><subject>Simulation</subject><subject>Training</subject><subject>Trains</subject><issn>0378-3820</issn><issn>1873-7188</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><recordid>eNp9kM1qGzEURkVIIY6bNwhkNqGrmepfM5tCMGkcCGSRZC00d-44MmPLlcalfvvKGdPuspIQ53767iHkmtGKUaa_r6t-v4sBKk4Zq6isKOdnZMZqI0rD6vqczKgwdSlqTi_IZUprSqlSjZmRxfLQRt8Vm9Dh4LerIvQFju-HAbdYjOH_PfzxHRbvOGIMq_wQ9qmI6GAM8Sv50rsh4dXpnJO3n_evi2X59PzwuLh7KkE0fCwZCMeEcC3ovlVtQyWq1igpTQuKiUY1ggODFhwzHGRuLLVyBhB1q41yYk6-Tbl51197TKPd-AQ4DO6jjq0bzQWrc86cyImEGFKK2Ntd9BsXD5ZRe1Rm13ZSZo_KLJU2K8tjt6cPXAI39NFtwad_s1xyI5jSmbuZuN4F61YxM28vOUhnrVpLLjPxYyIw-_jtMdoEHreAnY8Io-2C_7zKX_5_jPo</recordid><startdate>20110901</startdate><enddate>20110901</enddate><creator>Zahedi, G.</creator><creator>Lohi, A.</creator><creator>Mahdi, K.A.</creator><general>Elsevier B.V</general><general>Elsevier</general><scope>FBQ</scope><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>20110901</creationdate><title>Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor</title><author>Zahedi, G. ; Lohi, A. ; Mahdi, K.A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c392t-1c3a133abc6fb5b904e5b75447bc51395932c1cbca172c4037465a7cee6b675a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Algorithms</topic><topic>Applied sciences</topic><topic>carbon dioxide</topic><topic>catalysts</topic><topic>Dynamic modeling</topic><topic>Energy</topic><topic>Energy. Thermal use of fuels</topic><topic>ethylene</topic><topic>Ethylene oxide</topic><topic>Ethylene oxide reactor</topic><topic>Exact sciences and technology</topic><topic>Fuels</topic><topic>Grey box modeling</topic><topic>Learning theory</topic><topic>Networks</topic><topic>Neural network</topic><topic>Neural networks</topic><topic>oxygen</topic><topic>Reactors</topic><topic>Simulation</topic><topic>Training</topic><topic>Trains</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zahedi, G.</creatorcontrib><creatorcontrib>Lohi, A.</creatorcontrib><creatorcontrib>Mahdi, K.A.</creatorcontrib><collection>AGRIS</collection><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Fuel processing technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zahedi, G.</au><au>Lohi, A.</au><au>Mahdi, K.A.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor</atitle><jtitle>Fuel processing technology</jtitle><date>2011-09-01</date><risdate>2011</risdate><volume>92</volume><issue>9</issue><spage>1725</spage><epage>1732</epage><pages>1725-1732</pages><issn>0378-3820</issn><eissn>1873-7188</eissn><coden>FPTEDY</coden><abstract>In this research a dynamic grey box model (GBM) of ethylene oxide (EO) fixed bed reactor has been presented. In the first step of the study, kinetic model of the existing reactions was obtained using artificial neural network (ANN) approach. In order to build the ANN model industrial data of a typical EO reactor were employed. Time, C
2H
4, C
2H
4O, CO
2, H
2O and O
2 mole fractions were network inputs and the multiplication of reaction rate and catalyst deactivation (
r
*
a)was ANN output. From 164 data, 109 data were employed to train ANN. After employing different training algorithms, it was found that, the radial basis function network (RBFN) training algorithm provides the best estimations of the data. This best obtained network was tested against fifty five unseen data. The network estimations were close to unseen data which confirmed generalization capability of the obtained network.
In the next step of study, (
r
*
a) was estimated with ANN and then the hybrid model of the reactor was solved. Simulation results were compared with EO mechanistic model and also with plant industrial data. It was found that GBM is 8.437 times more accurate than the mechanistic model.
► ANN can model rate of ethylen epoxidation. ► Grey box model is more accurate than mechanistic model. ► Grey box model provides good extrapolation.</abstract><cop>Amsterdam</cop><pub>Elsevier B.V</pub><doi>10.1016/j.fuproc.2011.04.022</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0378-3820 |
| ispartof | Fuel processing technology, 2011-09, Vol.92 (9), p.1725-1732 |
| issn | 0378-3820 1873-7188 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_896231859 |
| source | Elsevier ScienceDirect Journals |
| subjects | Algorithms Applied sciences carbon dioxide catalysts Dynamic modeling Energy Energy. Thermal use of fuels ethylene Ethylene oxide Ethylene oxide reactor Exact sciences and technology Fuels Grey box modeling Learning theory Networks Neural network Neural networks oxygen Reactors Simulation Training Trains |
| title | Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T01%3A15%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Hybrid%20modeling%20of%20ethylene%20to%20ethylene%20oxide%20heterogeneous%20reactor&rft.jtitle=Fuel%20processing%20technology&rft.au=Zahedi,%20G.&rft.date=2011-09-01&rft.volume=92&rft.issue=9&rft.spage=1725&rft.epage=1732&rft.pages=1725-1732&rft.issn=0378-3820&rft.eissn=1873-7188&rft.coden=FPTEDY&rft_id=info:doi/10.1016/j.fuproc.2011.04.022&rft_dat=%3Cproquest_cross%3E896231859%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=896231859&rft_id=info:pmid/&rft_els_id=S0378382011001433&rfr_iscdi=true |