SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study
A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is...
Ausführliche Beschreibung
Autor*in: |
Jigjid, Kherlen [verfasserIn] Minamoto, Yuki [verfasserIn] Doan, Nguyen Anh Khoa [verfasserIn] Tanahashi, Mamoru [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2022 |
---|
Schlagwörter: |
---|
Übergeordnetes Werk: |
Enthalten in: Proceedings of the Combustion Institute - Combustion Institute ; ID: gnd/1004025-0, Amsterdam [u.a.] : Elsevier, 2000, 39, Seite 4489-4499 |
---|---|
Übergeordnetes Werk: |
volume:39 ; pages:4489-4499 |
DOI / URN: |
10.1016/j.proci.2022.07.020 |
---|
Katalog-ID: |
ELV010206809 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | ELV010206809 | ||
003 | DE-627 | ||
005 | 20230609194900.0 | ||
007 | cr uuu---uuuuu | ||
008 | 230609s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.proci.2022.07.020 |2 doi | |
035 | |a (DE-627)ELV010206809 | ||
035 | |a (ELSEVIER)S1540-7489(22)00049-9 | ||
040 | |a DE-627 |b ger |c DE-627 |e rda | ||
041 | |a eng | ||
082 | 0 | 4 | |a 660 |q VZ |
100 | 1 | |a Jigjid, Kherlen |e verfasserin |0 (orcid)0000-0003-3814-9487 |4 aut | |
245 | 1 | 0 | |a SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study |
264 | 1 | |c 2022 | |
336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well. | ||
650 | 4 | |a SGS Reaction rate modelling | |
650 | 4 | |a MILD Combustion | |
650 | 4 | |a Combustion mode | |
650 | 4 | |a Machine learning | |
650 | 4 | |a Direct numerical simulation (DNS) | |
700 | 1 | |a Minamoto, Yuki |e verfasserin |0 (orcid)0000-0002-6157-8370 |4 aut | |
700 | 1 | |a Doan, Nguyen Anh Khoa |e verfasserin |0 (orcid)0000-0002-9890-3173 |4 aut | |
700 | 1 | |a Tanahashi, Mamoru |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |a Combustion Institute ; ID: gnd/1004025-0 |t Proceedings of the Combustion Institute |d Amsterdam [u.a.] : Elsevier, 2000 |g 39, Seite 4489-4499 |h Online-Ressource |w (DE-627)495741140 |w (DE-600)2197968-6 |w (DE-576)259486582 |x 1873-2704 |7 nnns |
773 | 1 | 8 | |g volume:39 |g pages:4489-4499 |
912 | |a GBV_USEFLAG_U | ||
912 | |a SYSFLAG_U | ||
912 | |a GBV_ELV | ||
912 | |a SSG-OLC-PHA | ||
912 | |a GBV_ILN_31 | ||
912 | |a GBV_ILN_63 | ||
912 | |a GBV_ILN_95 | ||
912 | |a GBV_ILN_150 | ||
912 | |a GBV_ILN_2004 | ||
912 | |a GBV_ILN_2068 | ||
912 | |a GBV_ILN_2111 | ||
912 | |a GBV_ILN_2336 | ||
912 | |a GBV_ILN_4251 | ||
951 | |a AR | ||
952 | |d 39 |h 4489-4499 |
author_variant |
k j kj y m ym n a k d nak nakd m t mt |
---|---|
matchkey_str |
article:18732704:2022----::gratortmdligomlcmutobsdnahnlanncmutomdcasfc |
hierarchy_sort_str |
2022 |
publishDate |
2022 |
allfields |
10.1016/j.proci.2022.07.020 doi (DE-627)ELV010206809 (ELSEVIER)S1540-7489(22)00049-9 DE-627 ger DE-627 rda eng 660 VZ Jigjid, Kherlen verfasserin (orcid)0000-0003-3814-9487 aut SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well. SGS Reaction rate modelling MILD Combustion Combustion mode Machine learning Direct numerical simulation (DNS) Minamoto, Yuki verfasserin (orcid)0000-0002-6157-8370 aut Doan, Nguyen Anh Khoa verfasserin (orcid)0000-0002-9890-3173 aut Tanahashi, Mamoru verfasserin aut Enthalten in Combustion Institute ; ID: gnd/1004025-0 Proceedings of the Combustion Institute Amsterdam [u.a.] : Elsevier, 2000 39, Seite 4489-4499 Online-Ressource (DE-627)495741140 (DE-600)2197968-6 (DE-576)259486582 1873-2704 nnns volume:39 pages:4489-4499 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OLC-PHA GBV_ILN_31 GBV_ILN_63 GBV_ILN_95 GBV_ILN_150 GBV_ILN_2004 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2336 GBV_ILN_4251 AR 39 4489-4499 |
spelling |
10.1016/j.proci.2022.07.020 doi (DE-627)ELV010206809 (ELSEVIER)S1540-7489(22)00049-9 DE-627 ger DE-627 rda eng 660 VZ Jigjid, Kherlen verfasserin (orcid)0000-0003-3814-9487 aut SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well. SGS Reaction rate modelling MILD Combustion Combustion mode Machine learning Direct numerical simulation (DNS) Minamoto, Yuki verfasserin (orcid)0000-0002-6157-8370 aut Doan, Nguyen Anh Khoa verfasserin (orcid)0000-0002-9890-3173 aut Tanahashi, Mamoru verfasserin aut Enthalten in Combustion Institute ; ID: gnd/1004025-0 Proceedings of the Combustion Institute Amsterdam [u.a.] : Elsevier, 2000 39, Seite 4489-4499 Online-Ressource (DE-627)495741140 (DE-600)2197968-6 (DE-576)259486582 1873-2704 nnns volume:39 pages:4489-4499 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OLC-PHA GBV_ILN_31 GBV_ILN_63 GBV_ILN_95 GBV_ILN_150 GBV_ILN_2004 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2336 GBV_ILN_4251 AR 39 4489-4499 |
allfields_unstemmed |
10.1016/j.proci.2022.07.020 doi (DE-627)ELV010206809 (ELSEVIER)S1540-7489(22)00049-9 DE-627 ger DE-627 rda eng 660 VZ Jigjid, Kherlen verfasserin (orcid)0000-0003-3814-9487 aut SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well. SGS Reaction rate modelling MILD Combustion Combustion mode Machine learning Direct numerical simulation (DNS) Minamoto, Yuki verfasserin (orcid)0000-0002-6157-8370 aut Doan, Nguyen Anh Khoa verfasserin (orcid)0000-0002-9890-3173 aut Tanahashi, Mamoru verfasserin aut Enthalten in Combustion Institute ; ID: gnd/1004025-0 Proceedings of the Combustion Institute Amsterdam [u.a.] : Elsevier, 2000 39, Seite 4489-4499 Online-Ressource (DE-627)495741140 (DE-600)2197968-6 (DE-576)259486582 1873-2704 nnns volume:39 pages:4489-4499 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OLC-PHA GBV_ILN_31 GBV_ILN_63 GBV_ILN_95 GBV_ILN_150 GBV_ILN_2004 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2336 GBV_ILN_4251 AR 39 4489-4499 |
allfieldsGer |
10.1016/j.proci.2022.07.020 doi (DE-627)ELV010206809 (ELSEVIER)S1540-7489(22)00049-9 DE-627 ger DE-627 rda eng 660 VZ Jigjid, Kherlen verfasserin (orcid)0000-0003-3814-9487 aut SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well. SGS Reaction rate modelling MILD Combustion Combustion mode Machine learning Direct numerical simulation (DNS) Minamoto, Yuki verfasserin (orcid)0000-0002-6157-8370 aut Doan, Nguyen Anh Khoa verfasserin (orcid)0000-0002-9890-3173 aut Tanahashi, Mamoru verfasserin aut Enthalten in Combustion Institute ; ID: gnd/1004025-0 Proceedings of the Combustion Institute Amsterdam [u.a.] : Elsevier, 2000 39, Seite 4489-4499 Online-Ressource (DE-627)495741140 (DE-600)2197968-6 (DE-576)259486582 1873-2704 nnns volume:39 pages:4489-4499 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OLC-PHA GBV_ILN_31 GBV_ILN_63 GBV_ILN_95 GBV_ILN_150 GBV_ILN_2004 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2336 GBV_ILN_4251 AR 39 4489-4499 |
allfieldsSound |
10.1016/j.proci.2022.07.020 doi (DE-627)ELV010206809 (ELSEVIER)S1540-7489(22)00049-9 DE-627 ger DE-627 rda eng 660 VZ Jigjid, Kherlen verfasserin (orcid)0000-0003-3814-9487 aut SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well. SGS Reaction rate modelling MILD Combustion Combustion mode Machine learning Direct numerical simulation (DNS) Minamoto, Yuki verfasserin (orcid)0000-0002-6157-8370 aut Doan, Nguyen Anh Khoa verfasserin (orcid)0000-0002-9890-3173 aut Tanahashi, Mamoru verfasserin aut Enthalten in Combustion Institute ; ID: gnd/1004025-0 Proceedings of the Combustion Institute Amsterdam [u.a.] : Elsevier, 2000 39, Seite 4489-4499 Online-Ressource (DE-627)495741140 (DE-600)2197968-6 (DE-576)259486582 1873-2704 nnns volume:39 pages:4489-4499 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OLC-PHA GBV_ILN_31 GBV_ILN_63 GBV_ILN_95 GBV_ILN_150 GBV_ILN_2004 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2336 GBV_ILN_4251 AR 39 4489-4499 |
language |
English |
source |
Enthalten in Proceedings of the Combustion Institute 39, Seite 4489-4499 volume:39 pages:4489-4499 |
sourceStr |
Enthalten in Proceedings of the Combustion Institute 39, Seite 4489-4499 volume:39 pages:4489-4499 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
SGS Reaction rate modelling MILD Combustion Combustion mode Machine learning Direct numerical simulation (DNS) |
dewey-raw |
660 |
isfreeaccess_bool |
false |
container_title |
Proceedings of the Combustion Institute |
authorswithroles_txt_mv |
Jigjid, Kherlen @@aut@@ Minamoto, Yuki @@aut@@ Doan, Nguyen Anh Khoa @@aut@@ Tanahashi, Mamoru @@aut@@ |
publishDateDaySort_date |
2022-01-01T00:00:00Z |
hierarchy_top_id |
495741140 |
dewey-sort |
3660 |
id |
ELV010206809 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">ELV010206809</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230609194900.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230609s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.proci.2022.07.020</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV010206809</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1540-7489(22)00049-9</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">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jigjid, Kherlen</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-3814-9487</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">SGS Reaction rate modelling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">MILD Combustion</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Combustion mode</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Direct numerical simulation (DNS)</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Minamoto, Yuki</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-6157-8370</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Doan, Nguyen Anh Khoa</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-9890-3173</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Tanahashi, Mamoru</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="a">Combustion Institute ; ID: gnd/1004025-0</subfield><subfield code="t">Proceedings of the Combustion Institute</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier, 2000</subfield><subfield code="g">39, Seite 4489-4499</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)495741140</subfield><subfield code="w">(DE-600)2197968-6</subfield><subfield code="w">(DE-576)259486582</subfield><subfield code="x">1873-2704</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:39</subfield><subfield code="g">pages:4489-4499</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">39</subfield><subfield code="h">4489-4499</subfield></datafield></record></collection>
|
author |
Jigjid, Kherlen |
spellingShingle |
Jigjid, Kherlen ddc 660 misc SGS Reaction rate modelling misc MILD Combustion misc Combustion mode misc Machine learning misc Direct numerical simulation (DNS) SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study |
authorStr |
Jigjid, Kherlen |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)495741140 |
format |
electronic Article |
dewey-ones |
660 - Chemical engineering |
delete_txt_mv |
keep |
author_role |
aut aut aut aut |
collection |
elsevier |
remote_str |
true |
illustrated |
Not Illustrated |
issn |
1873-2704 |
topic_title |
660 VZ SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study SGS Reaction rate modelling MILD Combustion Combustion mode Machine learning Direct numerical simulation (DNS) |
topic |
ddc 660 misc SGS Reaction rate modelling misc MILD Combustion misc Combustion mode misc Machine learning misc Direct numerical simulation (DNS) |
topic_unstemmed |
ddc 660 misc SGS Reaction rate modelling misc MILD Combustion misc Combustion mode misc Machine learning misc Direct numerical simulation (DNS) |
topic_browse |
ddc 660 misc SGS Reaction rate modelling misc MILD Combustion misc Combustion mode misc Machine learning misc Direct numerical simulation (DNS) |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
cr |
hierarchy_parent_title |
Proceedings of the Combustion Institute |
hierarchy_parent_id |
495741140 |
dewey-tens |
660 - Chemical engineering |
hierarchy_top_title |
Proceedings of the Combustion Institute |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)495741140 (DE-600)2197968-6 (DE-576)259486582 |
title |
SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study |
ctrlnum |
(DE-627)ELV010206809 (ELSEVIER)S1540-7489(22)00049-9 |
title_full |
SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study |
author_sort |
Jigjid, Kherlen |
journal |
Proceedings of the Combustion Institute |
journalStr |
Proceedings of the Combustion Institute |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
600 - Technology |
recordtype |
marc |
publishDateSort |
2022 |
contenttype_str_mv |
zzz |
container_start_page |
4489 |
author_browse |
Jigjid, Kherlen Minamoto, Yuki Doan, Nguyen Anh Khoa Tanahashi, Mamoru |
container_volume |
39 |
class |
660 VZ |
format_se |
Elektronische Aufsätze |
author-letter |
Jigjid, Kherlen |
doi_str_mv |
10.1016/j.proci.2022.07.020 |
normlink |
(ORCID)0000-0003-3814-9487 (ORCID)0000-0002-6157-8370 (ORCID)0000-0002-9890-3173 |
normlink_prefix_str_mv |
(orcid)0000-0003-3814-9487 (orcid)0000-0002-6157-8370 (orcid)0000-0002-9890-3173 |
dewey-full |
660 |
author2-role |
verfasserin |
title_sort |
sgs reaction rate modelling for mild combustion based on machine-learning combustion mode classification: development and a priori study |
title_auth |
SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study |
abstract |
A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well. |
abstractGer |
A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well. |
abstract_unstemmed |
A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well. |
collection_details |
GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OLC-PHA GBV_ILN_31 GBV_ILN_63 GBV_ILN_95 GBV_ILN_150 GBV_ILN_2004 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2336 GBV_ILN_4251 |
title_short |
SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study |
remote_bool |
true |
author2 |
Minamoto, Yuki Doan, Nguyen Anh Khoa Tanahashi, Mamoru |
author2Str |
Minamoto, Yuki Doan, Nguyen Anh Khoa Tanahashi, Mamoru |
ppnlink |
495741140 |
mediatype_str_mv |
c |
isOA_txt |
false |
hochschulschrift_bool |
false |
doi_str |
10.1016/j.proci.2022.07.020 |
up_date |
2024-07-06T17:11:29.463Z |
_version_ |
1803850496832700416 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">ELV010206809</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230609194900.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230609s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.proci.2022.07.020</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV010206809</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1540-7489(22)00049-9</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">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jigjid, Kherlen</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-3814-9487</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">SGS Reaction rate modelling for MILD combustion based on machine-learning combustion mode classification: Development and a priori study</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">A neural network (NN) aided model is proposed for the filtered reaction rate in moderate or intense low-oxygen dilution (MILD) combustion. The framework of the present model is based on the partially stirred reactor (PaSR) approach, and the fraction of the reactive structure appearing in the PaSR is predicted using different NN’s, to consider both premixed and non-premixed conditions while allowing the use of imbalanced training data between premixed and non-premixed combustion direct numerical simulation (DNS) data. The key ingredient in the present model is the use of local combustion mode prediction performed by using another NN, which is developed in a previous study. The trained model was then assessed by using two unknown combustion DNS cases, which yields much higher dilution level (more intense MILD condition) and higher Karlovitz number than the DNS cases used as training data. The model performance assessment has been carried out by means of the Pearson’s correlation coefficient and mean squared error. For both the present model and zeroth-order approximated reaction rate, the correlation coefficient with the target values shows relatively high values, suggesting that the trend of predicted field, by the present model and zeroth-order approximation, is well correlated with the actual reaction rate field. This suggests that the use of PaSR equation is promising if the fraction of the reactive structure is appropriately predicted, which is the objective in the present study. On the other hand, substantially lower mean squared error is observed for a range of filter sizes for the present model than that for the zeroth-order approximation. This suggests that the present filtered reaction rate model can account for the SGS contribution reasonably well.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">SGS Reaction rate modelling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">MILD Combustion</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Combustion mode</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Direct numerical simulation (DNS)</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Minamoto, Yuki</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-6157-8370</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Doan, Nguyen Anh Khoa</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-9890-3173</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Tanahashi, Mamoru</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="a">Combustion Institute ; ID: gnd/1004025-0</subfield><subfield code="t">Proceedings of the Combustion Institute</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier, 2000</subfield><subfield code="g">39, Seite 4489-4499</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)495741140</subfield><subfield code="w">(DE-600)2197968-6</subfield><subfield code="w">(DE-576)259486582</subfield><subfield code="x">1873-2704</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:39</subfield><subfield code="g">pages:4489-4499</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">39</subfield><subfield code="h">4489-4499</subfield></datafield></record></collection>
|
score |
7.400215 |