Combined Mechanistic and Empirical Modelling
We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differ...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
The Berkeley Electronic Press ; 2004 |
|---|
| Schlagwörter: |
|---|
| Reproduktion: |
Berkeley Electronic Press Academic Journals |
|---|---|
| Übergeordnetes Werk: |
In: International journal of chemical reactor engineering - Berkeley, Calif. : Bepress, 2003, 2.2004, 1, A3 |
| Übergeordnetes Werk: |
volume:2 ; year:2004 ; number:1 ; pages:3 |
| Links: |
|---|
| Katalog-ID: |
NLEJ21955644X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLEJ21955644X | ||
| 003 | DE-627 | ||
| 005 | 20230506181735.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 090716s2004 xxu|||||o 00| ||eng c | ||
| 035 | |a (DE-627)NLEJ21955644X | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 044 | |c XD-US | ||
| 245 | 1 | 0 | |a Combined Mechanistic and Empirical Modelling |
| 264 | 1 | |b The Berkeley Electronic Press |c 2004 | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors. | ||
| 533 | |f Berkeley Electronic Press Academic Journals | ||
| 650 | 4 | |a Hybrid Modelling | |
| 650 | 4 | |a Gray Box Modelling | |
| 650 | 4 | |a Multivariate Adaptive Regression Splines | |
| 700 | 1 | |a Duarte, Belmiro |4 oth | |
| 700 | 1 | |a Saraiva, P. M. |4 oth | |
| 700 | 1 | |a Pantelides, C. C. |4 oth | |
| 773 | 0 | 8 | |i In |t International journal of chemical reactor engineering |d Berkeley, Calif. : Bepress, 2003 |g 2.2004, 1, A3 |h Online-Ressource |w (DE-627)NLEJ219537194 |w (DE-600)2112754-2 |x 1542-6580 |7 nnns |
| 773 | 1 | 8 | |g volume:2 |g year:2004 |g number:1 |g pages:3 |
| 856 | 4 | 0 | |u http://www.bepress.com/ijcre/vol2/A3 |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a ZDB-1-BEP | ||
| 912 | |a GBV_NL_ARTICLE | ||
| 951 | |a AR | ||
| 952 | |d 2 |j 2004 |e 1 |h 3 |y 2.2004, 1, A3 | ||
| matchkey_str |
article:15426580:2004----::obndehnsiadmiia |
|---|---|
| hierarchy_sort_str |
2004 |
| publishDate |
2004 |
| allfields |
(DE-627)NLEJ21955644X DE-627 ger DE-627 rakwb eng XD-US Combined Mechanistic and Empirical Modelling The Berkeley Electronic Press 2004 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors. Berkeley Electronic Press Academic Journals Hybrid Modelling Gray Box Modelling Multivariate Adaptive Regression Splines Duarte, Belmiro oth Saraiva, P. M. oth Pantelides, C. C. oth In International journal of chemical reactor engineering Berkeley, Calif. : Bepress, 2003 2.2004, 1, A3 Online-Ressource (DE-627)NLEJ219537194 (DE-600)2112754-2 1542-6580 nnns volume:2 year:2004 number:1 pages:3 http://www.bepress.com/ijcre/vol2/A3 GBV_USEFLAG_U ZDB-1-BEP GBV_NL_ARTICLE AR 2 2004 1 3 2.2004, 1, A3 |
| spelling |
(DE-627)NLEJ21955644X DE-627 ger DE-627 rakwb eng XD-US Combined Mechanistic and Empirical Modelling The Berkeley Electronic Press 2004 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors. Berkeley Electronic Press Academic Journals Hybrid Modelling Gray Box Modelling Multivariate Adaptive Regression Splines Duarte, Belmiro oth Saraiva, P. M. oth Pantelides, C. C. oth In International journal of chemical reactor engineering Berkeley, Calif. : Bepress, 2003 2.2004, 1, A3 Online-Ressource (DE-627)NLEJ219537194 (DE-600)2112754-2 1542-6580 nnns volume:2 year:2004 number:1 pages:3 http://www.bepress.com/ijcre/vol2/A3 GBV_USEFLAG_U ZDB-1-BEP GBV_NL_ARTICLE AR 2 2004 1 3 2.2004, 1, A3 |
| allfields_unstemmed |
(DE-627)NLEJ21955644X DE-627 ger DE-627 rakwb eng XD-US Combined Mechanistic and Empirical Modelling The Berkeley Electronic Press 2004 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors. Berkeley Electronic Press Academic Journals Hybrid Modelling Gray Box Modelling Multivariate Adaptive Regression Splines Duarte, Belmiro oth Saraiva, P. M. oth Pantelides, C. C. oth In International journal of chemical reactor engineering Berkeley, Calif. : Bepress, 2003 2.2004, 1, A3 Online-Ressource (DE-627)NLEJ219537194 (DE-600)2112754-2 1542-6580 nnns volume:2 year:2004 number:1 pages:3 http://www.bepress.com/ijcre/vol2/A3 GBV_USEFLAG_U ZDB-1-BEP GBV_NL_ARTICLE AR 2 2004 1 3 2.2004, 1, A3 |
| allfieldsGer |
(DE-627)NLEJ21955644X DE-627 ger DE-627 rakwb eng XD-US Combined Mechanistic and Empirical Modelling The Berkeley Electronic Press 2004 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors. Berkeley Electronic Press Academic Journals Hybrid Modelling Gray Box Modelling Multivariate Adaptive Regression Splines Duarte, Belmiro oth Saraiva, P. M. oth Pantelides, C. C. oth In International journal of chemical reactor engineering Berkeley, Calif. : Bepress, 2003 2.2004, 1, A3 Online-Ressource (DE-627)NLEJ219537194 (DE-600)2112754-2 1542-6580 nnns volume:2 year:2004 number:1 pages:3 http://www.bepress.com/ijcre/vol2/A3 GBV_USEFLAG_U ZDB-1-BEP GBV_NL_ARTICLE AR 2 2004 1 3 2.2004, 1, A3 |
| allfieldsSound |
(DE-627)NLEJ21955644X DE-627 ger DE-627 rakwb eng XD-US Combined Mechanistic and Empirical Modelling The Berkeley Electronic Press 2004 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors. Berkeley Electronic Press Academic Journals Hybrid Modelling Gray Box Modelling Multivariate Adaptive Regression Splines Duarte, Belmiro oth Saraiva, P. M. oth Pantelides, C. C. oth In International journal of chemical reactor engineering Berkeley, Calif. : Bepress, 2003 2.2004, 1, A3 Online-Ressource (DE-627)NLEJ219537194 (DE-600)2112754-2 1542-6580 nnns volume:2 year:2004 number:1 pages:3 http://www.bepress.com/ijcre/vol2/A3 GBV_USEFLAG_U ZDB-1-BEP GBV_NL_ARTICLE AR 2 2004 1 3 2.2004, 1, A3 |
| language |
English |
| source |
In International journal of chemical reactor engineering 2.2004, 1, A3 volume:2 year:2004 number:1 pages:3 |
| sourceStr |
In International journal of chemical reactor engineering 2.2004, 1, A3 volume:2 year:2004 number:1 pages:3 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Hybrid Modelling Gray Box Modelling Multivariate Adaptive Regression Splines |
| isfreeaccess_bool |
false |
| container_title |
International journal of chemical reactor engineering |
| authorswithroles_txt_mv |
Duarte, Belmiro @@oth@@ Saraiva, P. M. @@oth@@ Pantelides, C. C. @@oth@@ |
| publishDateDaySort_date |
2004-01-01T00:00:00Z |
| hierarchy_top_id |
NLEJ219537194 |
| id |
NLEJ21955644X |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">NLEJ21955644X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506181735.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">090716s2004 xxu|||||o 00| ||eng c</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)NLEJ21955644X</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="044" ind1=" " ind2=" "><subfield code="c">XD-US</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Combined Mechanistic and Empirical Modelling</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="b">The Berkeley Electronic Press</subfield><subfield code="c">2004</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors.</subfield></datafield><datafield tag="533" ind1=" " ind2=" "><subfield code="f">Berkeley Electronic Press Academic Journals</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hybrid Modelling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Gray Box Modelling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multivariate Adaptive Regression Splines</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Duarte, Belmiro</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Saraiva, P. M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pantelides, C. C.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">International journal of chemical reactor engineering</subfield><subfield code="d">Berkeley, Calif. : Bepress, 2003</subfield><subfield code="g">2.2004, 1, A3</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)NLEJ219537194</subfield><subfield code="w">(DE-600)2112754-2</subfield><subfield code="x">1542-6580</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:2</subfield><subfield code="g">year:2004</subfield><subfield code="g">number:1</subfield><subfield code="g">pages:3</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://www.bepress.com/ijcre/vol2/A3</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-1-BEP</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_NL_ARTICLE</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">2</subfield><subfield code="j">2004</subfield><subfield code="e">1</subfield><subfield code="h">3</subfield><subfield code="y">2.2004, 1, A3</subfield></datafield></record></collection>
|
| series2 |
Berkeley Electronic Press Academic Journals |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)NLEJ219537194 |
| format |
electronic Article |
| delete_txt_mv |
keep |
| collection |
NL |
| remote_str |
true |
| illustrated |
Not Illustrated |
| issn |
1542-6580 |
| topic_title |
Combined Mechanistic and Empirical Modelling Hybrid Modelling Gray Box Modelling Multivariate Adaptive Regression Splines |
| publisher |
The Berkeley Electronic Press |
| publisherStr |
The Berkeley Electronic Press |
| topic |
misc Hybrid Modelling misc Gray Box Modelling misc Multivariate Adaptive Regression Splines |
| spellingShingle |
misc Hybrid Modelling misc Gray Box Modelling misc Multivariate Adaptive Regression Splines Combined Mechanistic and Empirical Modelling |
| topic_unstemmed |
misc Hybrid Modelling misc Gray Box Modelling misc Multivariate Adaptive Regression Splines |
| topic_browse |
misc Hybrid Modelling misc Gray Box Modelling misc Multivariate Adaptive Regression Splines |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
b d bd p m s pm pms c c p cc ccp |
| hierarchy_parent_title |
International journal of chemical reactor engineering |
| hierarchy_parent_id |
NLEJ219537194 |
| hierarchy_top_title |
International journal of chemical reactor engineering |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)NLEJ219537194 (DE-600)2112754-2 |
| title |
Combined Mechanistic and Empirical Modelling |
| ctrlnum |
(DE-627)NLEJ21955644X |
| title_full |
Combined Mechanistic and Empirical Modelling |
| journal |
International journal of chemical reactor engineering |
| journalStr |
International journal of chemical reactor engineering |
| lang_code |
eng |
| isOA_bool |
false |
| recordtype |
marc |
| publishDateSort |
2004 |
| contenttype_str_mv |
zzz |
| container_start_page |
3 |
| container_volume |
2 |
| format_se |
Elektronische Aufsätze |
| countryofpublication_str_mv |
XD-US |
| title_sort |
combined mechanistic and empirical modelling |
| title_auth |
Combined Mechanistic and Empirical Modelling |
| abstract |
We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors. |
| abstractGer |
We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors. |
| abstract_unstemmed |
We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors. |
| collection_details |
GBV_USEFLAG_U ZDB-1-BEP GBV_NL_ARTICLE |
| container_issue |
1 |
| title_short |
Combined Mechanistic and Empirical Modelling |
| url |
http://www.bepress.com/ijcre/vol2/A3 |
| remote_bool |
true |
| author2 |
Duarte, Belmiro Saraiva, P. M. Pantelides, C. C. |
| author2Str |
Duarte, Belmiro Saraiva, P. M. Pantelides, C. C. |
| ppnlink |
NLEJ219537194 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth |
| up_date |
2024-07-06T05:29:16.533Z |
| _version_ |
1803806317254541312 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">NLEJ21955644X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506181735.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">090716s2004 xxu|||||o 00| ||eng c</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)NLEJ21955644X</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="044" ind1=" " ind2=" "><subfield code="c">XD-US</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Combined Mechanistic and Empirical Modelling</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="b">The Berkeley Electronic Press</subfield><subfield code="c">2004</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors.</subfield></datafield><datafield tag="533" ind1=" " ind2=" "><subfield code="f">Berkeley Electronic Press Academic Journals</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hybrid Modelling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Gray Box Modelling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multivariate Adaptive Regression Splines</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Duarte, Belmiro</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Saraiva, P. M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pantelides, C. C.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">International journal of chemical reactor engineering</subfield><subfield code="d">Berkeley, Calif. : Bepress, 2003</subfield><subfield code="g">2.2004, 1, A3</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)NLEJ219537194</subfield><subfield code="w">(DE-600)2112754-2</subfield><subfield code="x">1542-6580</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:2</subfield><subfield code="g">year:2004</subfield><subfield code="g">number:1</subfield><subfield code="g">pages:3</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://www.bepress.com/ijcre/vol2/A3</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-1-BEP</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_NL_ARTICLE</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">2</subfield><subfield code="j">2004</subfield><subfield code="e">1</subfield><subfield code="h">3</subfield><subfield code="y">2.2004, 1, A3</subfield></datafield></record></collection>
|
| score |
7.399598 |