Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression
This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic f...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Fang, Zhiyuan [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021transfer abstract |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Transmission of feto-placental metabolic anomalies through paternal lineage - Capobianco, Evangelina ELSEVIER, 2022, Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:166 ; year:2021 ; pages:0 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.tws.2021.108076 |
|---|
| Katalog-ID: |
ELV054684420 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV054684420 | ||
| 003 | DE-627 | ||
| 005 | 20230626040617.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 210910s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.tws.2021.108076 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001524.pica |
| 035 | |a (DE-627)ELV054684420 | ||
| 035 | |a (ELSEVIER)S0263-8231(21)00388-8 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 610 |q VZ |
| 084 | |a 44.92 |2 bkl | ||
| 100 | 1 | |a Fang, Zhiyuan |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression |
| 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 This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. | ||
| 520 | |a This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. | ||
| 650 | 7 | |a Deep learning |2 Elsevier | |
| 650 | 7 | |a Cold-formed steel |2 Elsevier | |
| 650 | 7 | |a Un-stiffened holes |2 Elsevier | |
| 650 | 7 | |a Finite element analysis |2 Elsevier | |
| 650 | 7 | |a Axial compression |2 Elsevier | |
| 650 | 7 | |a Hole effect |2 Elsevier | |
| 650 | 7 | |a Edge-stiffened holes |2 Elsevier | |
| 700 | 1 | |a Roy, Krishanu |4 oth | |
| 700 | 1 | |a Chen, Boshan |4 oth | |
| 700 | 1 | |a Sham, Chiu-Wing |4 oth | |
| 700 | 1 | |a Hajirasouliha, Iman |4 oth | |
| 700 | 1 | |a Lim, James B.P. |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a Capobianco, Evangelina ELSEVIER |t Transmission of feto-placental metabolic anomalies through paternal lineage |d 2022 |g Amsterdam [u.a.] |w (DE-627)ELV007893337 |
| 773 | 1 | 8 | |g volume:166 |g year:2021 |g pages:0 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.tws.2021.108076 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a SSG-OLC-PHA | ||
| 936 | b | k | |a 44.92 |j Gynäkologie |q VZ |
| 951 | |a AR | ||
| 952 | |d 166 |j 2021 |h 0 | ||
| author_variant |
z f zf |
|---|---|
| matchkey_str |
fangzhiyuanroykrishanuchenboshanshamchiu:2021----:eperigaepoeueosrcuadsgoclfreselhnescinwtegsifndnu |
| hierarchy_sort_str |
2021transfer abstract |
| bklnumber |
44.92 |
| publishDate |
2021 |
| allfields |
10.1016/j.tws.2021.108076 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001524.pica (DE-627)ELV054684420 (ELSEVIER)S0263-8231(21)00388-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.92 bkl Fang, Zhiyuan verfasserin aut Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes Elsevier Roy, Krishanu oth Chen, Boshan oth Sham, Chiu-Wing oth Hajirasouliha, Iman oth Lim, James B.P. oth Enthalten in Elsevier Science Capobianco, Evangelina ELSEVIER Transmission of feto-placental metabolic anomalies through paternal lineage 2022 Amsterdam [u.a.] (DE-627)ELV007893337 volume:166 year:2021 pages:0 https://doi.org/10.1016/j.tws.2021.108076 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.92 Gynäkologie VZ AR 166 2021 0 |
| spelling |
10.1016/j.tws.2021.108076 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001524.pica (DE-627)ELV054684420 (ELSEVIER)S0263-8231(21)00388-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.92 bkl Fang, Zhiyuan verfasserin aut Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes Elsevier Roy, Krishanu oth Chen, Boshan oth Sham, Chiu-Wing oth Hajirasouliha, Iman oth Lim, James B.P. oth Enthalten in Elsevier Science Capobianco, Evangelina ELSEVIER Transmission of feto-placental metabolic anomalies through paternal lineage 2022 Amsterdam [u.a.] (DE-627)ELV007893337 volume:166 year:2021 pages:0 https://doi.org/10.1016/j.tws.2021.108076 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.92 Gynäkologie VZ AR 166 2021 0 |
| allfields_unstemmed |
10.1016/j.tws.2021.108076 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001524.pica (DE-627)ELV054684420 (ELSEVIER)S0263-8231(21)00388-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.92 bkl Fang, Zhiyuan verfasserin aut Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes Elsevier Roy, Krishanu oth Chen, Boshan oth Sham, Chiu-Wing oth Hajirasouliha, Iman oth Lim, James B.P. oth Enthalten in Elsevier Science Capobianco, Evangelina ELSEVIER Transmission of feto-placental metabolic anomalies through paternal lineage 2022 Amsterdam [u.a.] (DE-627)ELV007893337 volume:166 year:2021 pages:0 https://doi.org/10.1016/j.tws.2021.108076 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.92 Gynäkologie VZ AR 166 2021 0 |
| allfieldsGer |
10.1016/j.tws.2021.108076 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001524.pica (DE-627)ELV054684420 (ELSEVIER)S0263-8231(21)00388-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.92 bkl Fang, Zhiyuan verfasserin aut Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes Elsevier Roy, Krishanu oth Chen, Boshan oth Sham, Chiu-Wing oth Hajirasouliha, Iman oth Lim, James B.P. oth Enthalten in Elsevier Science Capobianco, Evangelina ELSEVIER Transmission of feto-placental metabolic anomalies through paternal lineage 2022 Amsterdam [u.a.] (DE-627)ELV007893337 volume:166 year:2021 pages:0 https://doi.org/10.1016/j.tws.2021.108076 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.92 Gynäkologie VZ AR 166 2021 0 |
| allfieldsSound |
10.1016/j.tws.2021.108076 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001524.pica (DE-627)ELV054684420 (ELSEVIER)S0263-8231(21)00388-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.92 bkl Fang, Zhiyuan verfasserin aut Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes Elsevier Roy, Krishanu oth Chen, Boshan oth Sham, Chiu-Wing oth Hajirasouliha, Iman oth Lim, James B.P. oth Enthalten in Elsevier Science Capobianco, Evangelina ELSEVIER Transmission of feto-placental metabolic anomalies through paternal lineage 2022 Amsterdam [u.a.] (DE-627)ELV007893337 volume:166 year:2021 pages:0 https://doi.org/10.1016/j.tws.2021.108076 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.92 Gynäkologie VZ AR 166 2021 0 |
| language |
English |
| source |
Enthalten in Transmission of feto-placental metabolic anomalies through paternal lineage Amsterdam [u.a.] volume:166 year:2021 pages:0 |
| sourceStr |
Enthalten in Transmission of feto-placental metabolic anomalies through paternal lineage Amsterdam [u.a.] volume:166 year:2021 pages:0 |
| format_phy_str_mv |
Article |
| bklname |
Gynäkologie |
| institution |
findex.gbv.de |
| topic_facet |
Deep learning Cold-formed steel Un-stiffened holes Finite element analysis Axial compression Hole effect Edge-stiffened holes |
| dewey-raw |
610 |
| isfreeaccess_bool |
false |
| container_title |
Transmission of feto-placental metabolic anomalies through paternal lineage |
| authorswithroles_txt_mv |
Fang, Zhiyuan @@aut@@ Roy, Krishanu @@oth@@ Chen, Boshan @@oth@@ Sham, Chiu-Wing @@oth@@ Hajirasouliha, Iman @@oth@@ Lim, James B.P. @@oth@@ |
| publishDateDaySort_date |
2021-01-01T00:00:00Z |
| hierarchy_top_id |
ELV007893337 |
| dewey-sort |
3610 |
| id |
ELV054684420 |
| 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">ELV054684420</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626040617.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.tws.2021.108076</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/GBV00000000001524.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV054684420</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0263-8231(21)00388-8</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">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.92</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Fang, Zhiyuan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression</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">This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Deep learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Cold-formed steel</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Un-stiffened holes</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Finite element analysis</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Axial compression</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Hole effect</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Edge-stiffened holes</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Roy, Krishanu</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Boshan</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Sham, Chiu-Wing</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hajirasouliha, Iman</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lim, James B.P.</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">Capobianco, Evangelina ELSEVIER</subfield><subfield code="t">Transmission of feto-placental metabolic anomalies through paternal lineage</subfield><subfield code="d">2022</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV007893337</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:166</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.tws.2021.108076</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">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.92</subfield><subfield code="j">Gynäkologie</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">166</subfield><subfield code="j">2021</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| author |
Fang, Zhiyuan |
| spellingShingle |
Fang, Zhiyuan ddc 610 bkl 44.92 Elsevier Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression |
| authorStr |
Fang, Zhiyuan |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV007893337 |
| format |
electronic Article |
| dewey-ones |
610 - Medicine & health |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
610 VZ 44.92 bkl Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes Elsevier |
| topic |
ddc 610 bkl 44.92 Elsevier Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes |
| topic_unstemmed |
ddc 610 bkl 44.92 Elsevier Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes |
| topic_browse |
ddc 610 bkl 44.92 Elsevier Deep learning Elsevier Cold-formed steel Elsevier Un-stiffened holes Elsevier Finite element analysis Elsevier Axial compression Elsevier Hole effect Elsevier Edge-stiffened holes |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
k r kr b c bc c w s cws i h ih j b l jb jbl |
| hierarchy_parent_title |
Transmission of feto-placental metabolic anomalies through paternal lineage |
| hierarchy_parent_id |
ELV007893337 |
| dewey-tens |
610 - Medicine & health |
| hierarchy_top_title |
Transmission of feto-placental metabolic anomalies through paternal lineage |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV007893337 |
| title |
Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression |
| ctrlnum |
(DE-627)ELV054684420 (ELSEVIER)S0263-8231(21)00388-8 |
| title_full |
Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression |
| author_sort |
Fang, Zhiyuan |
| journal |
Transmission of feto-placental metabolic anomalies through paternal lineage |
| journalStr |
Transmission of feto-placental metabolic anomalies through paternal lineage |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
zzz |
| container_start_page |
0 |
| author_browse |
Fang, Zhiyuan |
| container_volume |
166 |
| class |
610 VZ 44.92 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Fang, Zhiyuan |
| doi_str_mv |
10.1016/j.tws.2021.108076 |
| dewey-full |
610 |
| title_sort |
deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression |
| title_auth |
Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression |
| abstract |
This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. |
| abstractGer |
This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. |
| abstract_unstemmed |
This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA |
| title_short |
Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression |
| url |
https://doi.org/10.1016/j.tws.2021.108076 |
| remote_bool |
true |
| author2 |
Roy, Krishanu Chen, Boshan Sham, Chiu-Wing Hajirasouliha, Iman Lim, James B.P. |
| author2Str |
Roy, Krishanu Chen, Boshan Sham, Chiu-Wing Hajirasouliha, Iman Lim, James B.P. |
| ppnlink |
ELV007893337 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth oth oth |
| doi_str |
10.1016/j.tws.2021.108076 |
| up_date |
2024-07-06T22:24:50.303Z |
| _version_ |
1803870210941255680 |
| 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">ELV054684420</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626040617.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.tws.2021.108076</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/GBV00000000001524.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV054684420</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0263-8231(21)00388-8</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">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.92</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Fang, Zhiyuan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep learning-based procedure for structural design of cold-formed steel channel sections with edge-stiffened and un-stiffened holes under axial compression</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">This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This paper proposes a framework of deep belief network (DBN) for studying the structural performance of cold-formed steel (CFS) channel sections with edge-stiffened/un-stiffened web holes, under axial compression. A total of 50,000 data points for training the DBN are generated from elasto plastic finite element analysis, which incorporates both initial geometric imperfections and residual stresses. A comparison against 23 experimental results was conducted, and it was found that the DBN predictions were conservative by 3% for columns with un-stiffened web holes, and 8% for columns with edge-stiffened web holes. When compared with Backpropagation Neural Network (a typical shallow artificial neural network) and linear regression model based on PaddlePaddle, it was found that the proposed DBN outperformed better than both the methods, using the same big training data used in this paper. When the same comparison was made for Effective Width Method and Direct Strength Method, the results from them were conservative by 5% and 12% against the experimental results, respectively for columns with un-stiffened web holes. Hole effects on the structural performance of channel sections under axial compression were also investigated. Based on the DBN output data, design recommendations of axial capacity enhancement/reduction factors were given for columns (stub, intermediate and slender) with edge-stiffened/un-stiffened web holes. Based on DBN prediction data, a comprehensive reliability analysis was conducted, which shows the proposed equations can predict the enhanced and reduced axial capacity of CFS channel sections with edge-stiffened/un-stiffened web holes accurately.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Deep learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Cold-formed steel</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Un-stiffened holes</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Finite element analysis</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Axial compression</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Hole effect</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Edge-stiffened holes</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Roy, Krishanu</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Boshan</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Sham, Chiu-Wing</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hajirasouliha, Iman</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lim, James B.P.</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">Capobianco, Evangelina ELSEVIER</subfield><subfield code="t">Transmission of feto-placental metabolic anomalies through paternal lineage</subfield><subfield code="d">2022</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV007893337</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:166</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.tws.2021.108076</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">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.92</subfield><subfield code="j">Gynäkologie</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">166</subfield><subfield code="j">2021</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| score |
7.3980484 |