Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems
For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach...
Ausführliche Beschreibung
Autor*in: |
Garg, Shailesh [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2022transfer abstract |
---|
Schlagwörter: |
---|
Übergeordnetes Werk: |
Enthalten in: Species loss from land use of oil palm plantations in Thailand - Jaroenkietkajorn, Ukrit ELSEVIER, 2021, mssp, Amsterdam [u.a.] |
---|---|
Übergeordnetes Werk: |
volume:173 ; year:2022 ; day:1 ; month:07 ; pages:0 |
Links: |
---|
DOI / URN: |
10.1016/j.ymssp.2022.109039 |
---|
Katalog-ID: |
ELV057464707 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | ELV057464707 | ||
003 | DE-627 | ||
005 | 20230626045149.0 | ||
007 | cr uuu---uuuuu | ||
008 | 220808s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.ymssp.2022.109039 |2 doi | |
028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001779.pica |
035 | |a (DE-627)ELV057464707 | ||
035 | |a (ELSEVIER)S0888-3270(22)00212-6 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 570 |a 630 |q VZ |
084 | |a BIODIV |q DE-30 |2 fid | ||
100 | 1 | |a Garg, Shailesh |e verfasserin |4 aut | |
245 | 1 | 0 | |a Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems |
264 | 1 | |c 2022transfer abstract | |
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 For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. | ||
520 | |a For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. | ||
650 | 7 | |a Dual Bayesian filters |2 Elsevier | |
650 | 7 | |a Gaussian process |2 Elsevier | |
650 | 7 | |a Model form error |2 Elsevier | |
650 | 7 | |a Gray-box modeling |2 Elsevier | |
700 | 1 | |a Chakraborty, Souvik |4 oth | |
700 | 1 | |a Hazra, Budhaditya |4 oth | |
773 | 0 | 8 | |i Enthalten in |n Elsevier |a Jaroenkietkajorn, Ukrit ELSEVIER |t Species loss from land use of oil palm plantations in Thailand |d 2021 |d mssp |g Amsterdam [u.a.] |w (DE-627)ELV007151810 |
773 | 1 | 8 | |g volume:173 |g year:2022 |g day:1 |g month:07 |g pages:0 |
856 | 4 | 0 | |u https://doi.org/10.1016/j.ymssp.2022.109039 |3 Volltext |
912 | |a GBV_USEFLAG_U | ||
912 | |a GBV_ELV | ||
912 | |a SYSFLAG_U | ||
912 | |a FID-BIODIV | ||
912 | |a SSG-OLC-PHA | ||
951 | |a AR | ||
952 | |d 173 |j 2022 |b 1 |c 0701 |h 0 |
author_variant |
s g sg |
---|---|
matchkey_str |
gargshaileshchakrabortysouvikhazrabudhad:2022----:hscitgaehbifaeokomdlomroietfctoin |
hierarchy_sort_str |
2022transfer abstract |
publishDate |
2022 |
allfields |
10.1016/j.ymssp.2022.109039 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001779.pica (DE-627)ELV057464707 (ELSEVIER)S0888-3270(22)00212-6 DE-627 ger DE-627 rakwb eng 570 630 VZ BIODIV DE-30 fid Garg, Shailesh verfasserin aut Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling Elsevier Chakraborty, Souvik oth Hazra, Budhaditya oth Enthalten in Elsevier Jaroenkietkajorn, Ukrit ELSEVIER Species loss from land use of oil palm plantations in Thailand 2021 mssp Amsterdam [u.a.] (DE-627)ELV007151810 volume:173 year:2022 day:1 month:07 pages:0 https://doi.org/10.1016/j.ymssp.2022.109039 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA AR 173 2022 1 0701 0 |
spelling |
10.1016/j.ymssp.2022.109039 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001779.pica (DE-627)ELV057464707 (ELSEVIER)S0888-3270(22)00212-6 DE-627 ger DE-627 rakwb eng 570 630 VZ BIODIV DE-30 fid Garg, Shailesh verfasserin aut Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling Elsevier Chakraborty, Souvik oth Hazra, Budhaditya oth Enthalten in Elsevier Jaroenkietkajorn, Ukrit ELSEVIER Species loss from land use of oil palm plantations in Thailand 2021 mssp Amsterdam [u.a.] (DE-627)ELV007151810 volume:173 year:2022 day:1 month:07 pages:0 https://doi.org/10.1016/j.ymssp.2022.109039 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA AR 173 2022 1 0701 0 |
allfields_unstemmed |
10.1016/j.ymssp.2022.109039 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001779.pica (DE-627)ELV057464707 (ELSEVIER)S0888-3270(22)00212-6 DE-627 ger DE-627 rakwb eng 570 630 VZ BIODIV DE-30 fid Garg, Shailesh verfasserin aut Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling Elsevier Chakraborty, Souvik oth Hazra, Budhaditya oth Enthalten in Elsevier Jaroenkietkajorn, Ukrit ELSEVIER Species loss from land use of oil palm plantations in Thailand 2021 mssp Amsterdam [u.a.] (DE-627)ELV007151810 volume:173 year:2022 day:1 month:07 pages:0 https://doi.org/10.1016/j.ymssp.2022.109039 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA AR 173 2022 1 0701 0 |
allfieldsGer |
10.1016/j.ymssp.2022.109039 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001779.pica (DE-627)ELV057464707 (ELSEVIER)S0888-3270(22)00212-6 DE-627 ger DE-627 rakwb eng 570 630 VZ BIODIV DE-30 fid Garg, Shailesh verfasserin aut Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling Elsevier Chakraborty, Souvik oth Hazra, Budhaditya oth Enthalten in Elsevier Jaroenkietkajorn, Ukrit ELSEVIER Species loss from land use of oil palm plantations in Thailand 2021 mssp Amsterdam [u.a.] (DE-627)ELV007151810 volume:173 year:2022 day:1 month:07 pages:0 https://doi.org/10.1016/j.ymssp.2022.109039 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA AR 173 2022 1 0701 0 |
allfieldsSound |
10.1016/j.ymssp.2022.109039 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001779.pica (DE-627)ELV057464707 (ELSEVIER)S0888-3270(22)00212-6 DE-627 ger DE-627 rakwb eng 570 630 VZ BIODIV DE-30 fid Garg, Shailesh verfasserin aut Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling Elsevier Chakraborty, Souvik oth Hazra, Budhaditya oth Enthalten in Elsevier Jaroenkietkajorn, Ukrit ELSEVIER Species loss from land use of oil palm plantations in Thailand 2021 mssp Amsterdam [u.a.] (DE-627)ELV007151810 volume:173 year:2022 day:1 month:07 pages:0 https://doi.org/10.1016/j.ymssp.2022.109039 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA AR 173 2022 1 0701 0 |
language |
English |
source |
Enthalten in Species loss from land use of oil palm plantations in Thailand Amsterdam [u.a.] volume:173 year:2022 day:1 month:07 pages:0 |
sourceStr |
Enthalten in Species loss from land use of oil palm plantations in Thailand Amsterdam [u.a.] volume:173 year:2022 day:1 month:07 pages:0 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Dual Bayesian filters Gaussian process Model form error Gray-box modeling |
dewey-raw |
570 |
isfreeaccess_bool |
false |
container_title |
Species loss from land use of oil palm plantations in Thailand |
authorswithroles_txt_mv |
Garg, Shailesh @@aut@@ Chakraborty, Souvik @@oth@@ Hazra, Budhaditya @@oth@@ |
publishDateDaySort_date |
2022-01-01T00:00:00Z |
hierarchy_top_id |
ELV007151810 |
dewey-sort |
3570 |
id |
ELV057464707 |
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">ELV057464707</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626045149.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220808s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.ymssp.2022.109039</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001779.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV057464707</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0888-3270(22)00212-6</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="082" ind1="0" ind2="4"><subfield code="a">570</subfield><subfield code="a">630</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">BIODIV</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Garg, Shailesh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</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">For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Dual Bayesian filters</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Gaussian process</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Model form error</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Gray-box modeling</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chakraborty, Souvik</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hazra, Budhaditya</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Jaroenkietkajorn, Ukrit ELSEVIER</subfield><subfield code="t">Species loss from land use of oil palm plantations in Thailand</subfield><subfield code="d">2021</subfield><subfield code="d">mssp</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV007151810</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:173</subfield><subfield code="g">year:2022</subfield><subfield code="g">day:1</subfield><subfield code="g">month:07</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.ymssp.2022.109039</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-BIODIV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">173</subfield><subfield code="j">2022</subfield><subfield code="b">1</subfield><subfield code="c">0701</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
author |
Garg, Shailesh |
spellingShingle |
Garg, Shailesh ddc 570 fid BIODIV Elsevier Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems |
authorStr |
Garg, Shailesh |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV007151810 |
format |
electronic Article |
dewey-ones |
570 - Life sciences; biology 630 - Agriculture & related technologies |
delete_txt_mv |
keep |
author_role |
aut |
collection |
elsevier |
remote_str |
true |
illustrated |
Not Illustrated |
topic_title |
570 630 VZ BIODIV DE-30 fid Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling Elsevier |
topic |
ddc 570 fid BIODIV Elsevier Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling |
topic_unstemmed |
ddc 570 fid BIODIV Elsevier Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling |
topic_browse |
ddc 570 fid BIODIV Elsevier Dual Bayesian filters Elsevier Gaussian process Elsevier Model form error Elsevier Gray-box modeling |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
zu |
author2_variant |
s c sc b h bh |
hierarchy_parent_title |
Species loss from land use of oil palm plantations in Thailand |
hierarchy_parent_id |
ELV007151810 |
dewey-tens |
570 - Life sciences; biology 630 - Agriculture |
hierarchy_top_title |
Species loss from land use of oil palm plantations in Thailand |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)ELV007151810 |
title |
Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems |
ctrlnum |
(DE-627)ELV057464707 (ELSEVIER)S0888-3270(22)00212-6 |
title_full |
Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems |
author_sort |
Garg, Shailesh |
journal |
Species loss from land use of oil palm plantations in Thailand |
journalStr |
Species loss from land use of oil palm plantations in Thailand |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
500 - Science 600 - Technology |
recordtype |
marc |
publishDateSort |
2022 |
contenttype_str_mv |
zzz |
container_start_page |
0 |
author_browse |
Garg, Shailesh |
container_volume |
173 |
class |
570 630 VZ BIODIV DE-30 fid |
format_se |
Elektronische Aufsätze |
author-letter |
Garg, Shailesh |
doi_str_mv |
10.1016/j.ymssp.2022.109039 |
dewey-full |
570 630 |
title_sort |
physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems |
title_auth |
Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems |
abstract |
For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. |
abstractGer |
For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. |
abstract_unstemmed |
For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework. |
collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA |
title_short |
Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems |
url |
https://doi.org/10.1016/j.ymssp.2022.109039 |
remote_bool |
true |
author2 |
Chakraborty, Souvik Hazra, Budhaditya |
author2Str |
Chakraborty, Souvik Hazra, Budhaditya |
ppnlink |
ELV007151810 |
mediatype_str_mv |
z |
isOA_txt |
false |
hochschulschrift_bool |
false |
author2_role |
oth oth |
doi_str |
10.1016/j.ymssp.2022.109039 |
up_date |
2024-07-06T23:18:40.084Z |
_version_ |
1803873597611048960 |
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">ELV057464707</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626045149.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220808s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.ymssp.2022.109039</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001779.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV057464707</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0888-3270(22)00212-6</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="082" ind1="0" ind2="4"><subfield code="a">570</subfield><subfield code="a">630</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">BIODIV</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Garg, Shailesh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</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">For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations. Such representation introduce model-form error into the system. In this paper, we propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation. The primary idea is to treat the unknown model-form error as a residual force and estimate it using dual Bayesian filter based joint input-state estimation algorithms. For improving the predictive capability of the underlying physics, we first use machine learning algorithm to learn a mapping between the estimated state and the input (model-form error) and then introduce it into the governing equation as an additional term. This helps in improving the predictive capability of the governing physics and allows the model to generalize to unseen environment. Although in theory, any machine learning algorithm can be used within the proposed framework, we use Gaussian process in this work. To test the performance of proposed framework, case studies discussing four different dynamical systems are discussed; results for which indicate that the framework is applicable to a wide variety of systems and can produce reliable estimates of original system’s states. Apart from this, the algorithm has also been tested for a case where the data has been taken from an experimental setup (Silver box dataset). The results produced further showcase the efficacy of the proposed framework.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Dual Bayesian filters</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Gaussian process</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Model form error</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Gray-box modeling</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chakraborty, Souvik</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hazra, Budhaditya</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Jaroenkietkajorn, Ukrit ELSEVIER</subfield><subfield code="t">Species loss from land use of oil palm plantations in Thailand</subfield><subfield code="d">2021</subfield><subfield code="d">mssp</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV007151810</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:173</subfield><subfield code="g">year:2022</subfield><subfield code="g">day:1</subfield><subfield code="g">month:07</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.ymssp.2022.109039</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-BIODIV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">173</subfield><subfield code="j">2022</subfield><subfield code="b">1</subfield><subfield code="c">0701</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
score |
7.399913 |