Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition
Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-depe...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Im, Sunyoung [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021transfer abstract |
|---|
| Schlagwörter: |
Nonlinear model order reduction (MOR) |
|---|
| Übergeordnetes Werk: |
Enthalten in: Does enhanced hydration have impact on autogenous deformation of internally cued mortar? - Zou, Dinghua ELSEVIER, 2019, Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:385 ; year:2021 ; day:1 ; month:11 ; pages:0 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.cma.2021.114030 |
|---|
| Katalog-ID: |
ELV055093620 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV055093620 | ||
| 003 | DE-627 | ||
| 005 | 20230626041202.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 220105s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.cma.2021.114030 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001541.pica |
| 035 | |a (DE-627)ELV055093620 | ||
| 035 | |a (ELSEVIER)S0045-7825(21)00361-3 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 690 |q VZ |
| 084 | |a 56.45 |2 bkl | ||
| 100 | 1 | |a Im, Sunyoung |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition |
| 264 | 1 | |c 2021transfer 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 Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. | ||
| 520 | |a Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. | ||
| 650 | 7 | |a Elasto-plasticity |2 Elsevier | |
| 650 | 7 | |a Surrogate model |2 Elsevier | |
| 650 | 7 | |a Nonlinear model order reduction (MOR) |2 Elsevier | |
| 650 | 7 | |a Proper orthogonal decomposition (POD) |2 Elsevier | |
| 650 | 7 | |a Long short-term memory (LSTM) |2 Elsevier | |
| 700 | 1 | |a Lee, Jonggeon |4 oth | |
| 700 | 1 | |a Cho, Maenghyo |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a Zou, Dinghua ELSEVIER |t Does enhanced hydration have impact on autogenous deformation of internally cued mortar? |d 2019 |g Amsterdam [u.a.] |w (DE-627)ELV002113945 |
| 773 | 1 | 8 | |g volume:385 |g year:2021 |g day:1 |g month:11 |g pages:0 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.cma.2021.114030 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 936 | b | k | |a 56.45 |j Baustoffkunde |q VZ |
| 951 | |a AR | ||
| 952 | |d 385 |j 2021 |b 1 |c 1101 |h 0 | ||
| author_variant |
s i si |
|---|---|
| matchkey_str |
imsunyoungleejonggeonchomaenghyo:2021----:urgtmdlnoeatpatcrbesilnsotemeoyerlewrsnp |
| hierarchy_sort_str |
2021transfer abstract |
| bklnumber |
56.45 |
| publishDate |
2021 |
| allfields |
10.1016/j.cma.2021.114030 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001541.pica (DE-627)ELV055093620 (ELSEVIER)S0045-7825(21)00361-3 DE-627 ger DE-627 rakwb eng 690 VZ 56.45 bkl Im, Sunyoung verfasserin aut Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) Elsevier Lee, Jonggeon oth Cho, Maenghyo oth Enthalten in Elsevier Science Zou, Dinghua ELSEVIER Does enhanced hydration have impact on autogenous deformation of internally cued mortar? 2019 Amsterdam [u.a.] (DE-627)ELV002113945 volume:385 year:2021 day:1 month:11 pages:0 https://doi.org/10.1016/j.cma.2021.114030 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 56.45 Baustoffkunde VZ AR 385 2021 1 1101 0 |
| spelling |
10.1016/j.cma.2021.114030 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001541.pica (DE-627)ELV055093620 (ELSEVIER)S0045-7825(21)00361-3 DE-627 ger DE-627 rakwb eng 690 VZ 56.45 bkl Im, Sunyoung verfasserin aut Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) Elsevier Lee, Jonggeon oth Cho, Maenghyo oth Enthalten in Elsevier Science Zou, Dinghua ELSEVIER Does enhanced hydration have impact on autogenous deformation of internally cued mortar? 2019 Amsterdam [u.a.] (DE-627)ELV002113945 volume:385 year:2021 day:1 month:11 pages:0 https://doi.org/10.1016/j.cma.2021.114030 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 56.45 Baustoffkunde VZ AR 385 2021 1 1101 0 |
| allfields_unstemmed |
10.1016/j.cma.2021.114030 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001541.pica (DE-627)ELV055093620 (ELSEVIER)S0045-7825(21)00361-3 DE-627 ger DE-627 rakwb eng 690 VZ 56.45 bkl Im, Sunyoung verfasserin aut Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) Elsevier Lee, Jonggeon oth Cho, Maenghyo oth Enthalten in Elsevier Science Zou, Dinghua ELSEVIER Does enhanced hydration have impact on autogenous deformation of internally cued mortar? 2019 Amsterdam [u.a.] (DE-627)ELV002113945 volume:385 year:2021 day:1 month:11 pages:0 https://doi.org/10.1016/j.cma.2021.114030 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 56.45 Baustoffkunde VZ AR 385 2021 1 1101 0 |
| allfieldsGer |
10.1016/j.cma.2021.114030 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001541.pica (DE-627)ELV055093620 (ELSEVIER)S0045-7825(21)00361-3 DE-627 ger DE-627 rakwb eng 690 VZ 56.45 bkl Im, Sunyoung verfasserin aut Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) Elsevier Lee, Jonggeon oth Cho, Maenghyo oth Enthalten in Elsevier Science Zou, Dinghua ELSEVIER Does enhanced hydration have impact on autogenous deformation of internally cued mortar? 2019 Amsterdam [u.a.] (DE-627)ELV002113945 volume:385 year:2021 day:1 month:11 pages:0 https://doi.org/10.1016/j.cma.2021.114030 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 56.45 Baustoffkunde VZ AR 385 2021 1 1101 0 |
| allfieldsSound |
10.1016/j.cma.2021.114030 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001541.pica (DE-627)ELV055093620 (ELSEVIER)S0045-7825(21)00361-3 DE-627 ger DE-627 rakwb eng 690 VZ 56.45 bkl Im, Sunyoung verfasserin aut Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) Elsevier Lee, Jonggeon oth Cho, Maenghyo oth Enthalten in Elsevier Science Zou, Dinghua ELSEVIER Does enhanced hydration have impact on autogenous deformation of internally cued mortar? 2019 Amsterdam [u.a.] (DE-627)ELV002113945 volume:385 year:2021 day:1 month:11 pages:0 https://doi.org/10.1016/j.cma.2021.114030 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 56.45 Baustoffkunde VZ AR 385 2021 1 1101 0 |
| language |
English |
| source |
Enthalten in Does enhanced hydration have impact on autogenous deformation of internally cued mortar? Amsterdam [u.a.] volume:385 year:2021 day:1 month:11 pages:0 |
| sourceStr |
Enthalten in Does enhanced hydration have impact on autogenous deformation of internally cued mortar? Amsterdam [u.a.] volume:385 year:2021 day:1 month:11 pages:0 |
| format_phy_str_mv |
Article |
| bklname |
Baustoffkunde |
| institution |
findex.gbv.de |
| topic_facet |
Elasto-plasticity Surrogate model Nonlinear model order reduction (MOR) Proper orthogonal decomposition (POD) Long short-term memory (LSTM) |
| dewey-raw |
690 |
| isfreeaccess_bool |
false |
| container_title |
Does enhanced hydration have impact on autogenous deformation of internally cued mortar? |
| authorswithroles_txt_mv |
Im, Sunyoung @@aut@@ Lee, Jonggeon @@oth@@ Cho, Maenghyo @@oth@@ |
| publishDateDaySort_date |
2021-01-01T00:00:00Z |
| hierarchy_top_id |
ELV002113945 |
| dewey-sort |
3690 |
| id |
ELV055093620 |
| 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">ELV055093620</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626041202.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220105s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.cma.2021.114030</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/GBV00000000001541.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV055093620</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0045-7825(21)00361-3</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">690</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">56.45</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Im, Sunyoung</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer 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">Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Elasto-plasticity</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Surrogate model</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Nonlinear model order reduction (MOR)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Proper orthogonal decomposition (POD)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Long short-term memory (LSTM)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, Jonggeon</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Cho, Maenghyo</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Zou, Dinghua ELSEVIER</subfield><subfield code="t">Does enhanced hydration have impact on autogenous deformation of internally cued mortar?</subfield><subfield code="d">2019</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV002113945</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:385</subfield><subfield code="g">year:2021</subfield><subfield code="g">day:1</subfield><subfield code="g">month:11</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.cma.2021.114030</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="936" ind1="b" ind2="k"><subfield code="a">56.45</subfield><subfield code="j">Baustoffkunde</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">385</subfield><subfield code="j">2021</subfield><subfield code="b">1</subfield><subfield code="c">1101</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| author |
Im, Sunyoung |
| spellingShingle |
Im, Sunyoung ddc 690 bkl 56.45 Elsevier Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition |
| authorStr |
Im, Sunyoung |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV002113945 |
| format |
electronic Article |
| dewey-ones |
690 - Buildings |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
690 VZ 56.45 bkl Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) Elsevier |
| topic |
ddc 690 bkl 56.45 Elsevier Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) |
| topic_unstemmed |
ddc 690 bkl 56.45 Elsevier Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) |
| topic_browse |
ddc 690 bkl 56.45 Elsevier Elasto-plasticity Elsevier Surrogate model Elsevier Nonlinear model order reduction (MOR) Elsevier Proper orthogonal decomposition (POD) Elsevier Long short-term memory (LSTM) |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
j l jl m c mc |
| hierarchy_parent_title |
Does enhanced hydration have impact on autogenous deformation of internally cued mortar? |
| hierarchy_parent_id |
ELV002113945 |
| dewey-tens |
690 - Building & construction |
| hierarchy_top_title |
Does enhanced hydration have impact on autogenous deformation of internally cued mortar? |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV002113945 |
| title |
Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition |
| ctrlnum |
(DE-627)ELV055093620 (ELSEVIER)S0045-7825(21)00361-3 |
| title_full |
Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition |
| author_sort |
Im, Sunyoung |
| journal |
Does enhanced hydration have impact on autogenous deformation of internally cued mortar? |
| journalStr |
Does enhanced hydration have impact on autogenous deformation of internally cued mortar? |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
zzz |
| container_start_page |
0 |
| author_browse |
Im, Sunyoung |
| container_volume |
385 |
| class |
690 VZ 56.45 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Im, Sunyoung |
| doi_str_mv |
10.1016/j.cma.2021.114030 |
| dewey-full |
690 |
| title_sort |
surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition |
| title_auth |
Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition |
| abstract |
Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. |
| abstractGer |
Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. |
| abstract_unstemmed |
Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U |
| title_short |
Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition |
| url |
https://doi.org/10.1016/j.cma.2021.114030 |
| remote_bool |
true |
| author2 |
Lee, Jonggeon Cho, Maenghyo |
| author2Str |
Lee, Jonggeon Cho, Maenghyo |
| ppnlink |
ELV002113945 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth |
| doi_str |
10.1016/j.cma.2021.114030 |
| up_date |
2024-07-06T16:35:43.035Z |
| _version_ |
1803848246138765312 |
| 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">ELV055093620</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626041202.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220105s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.cma.2021.114030</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/GBV00000000001541.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV055093620</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0045-7825(21)00361-3</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">690</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">56.45</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Im, Sunyoung</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer 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">Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Because of its nonlinearity and path-dependency, analysis of the elasto-plastic behavior of the finite element (FE) model is computationally expensive. By directly learning sequential data, modeling plasticity via deep learning has shown successful performance in immediately predicting the path-dependent response. However, large-scale elasto-plastic FE models still have challenges in that they require numerous degrees of freedom and are accompanied by high-dimensional data. This study proposes a practical framework for the surrogate modeling of a large-scale elasto-plastic FE model by combining long short-term memory (LSTM) neural networks with proper orthogonal decomposition (POD). First, displacement, plastic strain magnitude, and von Mises stress are generated using commercial FE analysis software, and then, the high-dimensional data are reduced to low-dimensional POD coefficient data before being used for training. With the drastically reduced data, a neural network architecture can be introduced in the form of individual and ensemble structures to achieve accurate and robust prediction. As the proposed POD-LSTM surrogate model operates on the structural level, POD-LSTM surrogate models are constructed and implemented for each of the three large-scale elasto-plastic FE models. In all three examples, the proposed POD-LSTM surrogate models were found to be efficient and accurate for predicting elasto-plastic responses.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Elasto-plasticity</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Surrogate model</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Nonlinear model order reduction (MOR)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Proper orthogonal decomposition (POD)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Long short-term memory (LSTM)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, Jonggeon</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Cho, Maenghyo</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Zou, Dinghua ELSEVIER</subfield><subfield code="t">Does enhanced hydration have impact on autogenous deformation of internally cued mortar?</subfield><subfield code="d">2019</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV002113945</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:385</subfield><subfield code="g">year:2021</subfield><subfield code="g">day:1</subfield><subfield code="g">month:11</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.cma.2021.114030</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="936" ind1="b" ind2="k"><subfield code="a">56.45</subfield><subfield code="j">Baustoffkunde</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">385</subfield><subfield code="j">2021</subfield><subfield code="b">1</subfield><subfield code="c">1101</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| score |
7.401039 |