Utilising Artificial Neural Networks for Assessing Seismic Demands of Buckling Restrained Braces Due to Pulse-like Motions
Buckling restrained brace frames (BRBFs) exhibit exceptional lateral stiffness, load-bearing capacity, and energy dissipation properties, rendering them a highly promising choice for regions susceptible to seismic activity. The precise and expeditious prediction of seismic demands on BRBFs is a cruc...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/13/10/2542 |
| _version_ | 1797574427096907776 |
|---|---|
| author | Amirhossein Mohammadi Shaghayegh Karimzadeh Saman Yaghmaei-Sabegh Maryam Ranjbari Paulo B. Lourenço |
| author_facet | Amirhossein Mohammadi Shaghayegh Karimzadeh Saman Yaghmaei-Sabegh Maryam Ranjbari Paulo B. Lourenço |
| author_sort | Amirhossein Mohammadi |
| collection | DOAJ |
| description | Buckling restrained brace frames (BRBFs) exhibit exceptional lateral stiffness, load-bearing capacity, and energy dissipation properties, rendering them a highly promising choice for regions susceptible to seismic activity. The precise and expeditious prediction of seismic demands on BRBFs is a crucial and challenging task. In this paper, the potential of artificial neural networks (ANNs) to predict the seismic demands of BRBFs is explored. The study presents the characteristics and modelling of prototype BRBFs with different numbers of stories and material properties, utilising the OpenSees software (Version 2.5.0) for numerical simulations. The seismic performance of the BRBFs is evaluated using 91 near-fault pulse-like ground motions, and the maximum inter-storey drift ratio (<i>MIDR</i>) and global drift ratio (<i>GDR</i>) are recorded as a measure of seismic demand. ANNs are then trained to predict the <i>MIDR</i> and <i>GDR</i> of the selected prototypes. The model’s performance is assessed by analysing the residuals and error metrics and then comparing the trend of the results with the real dataset. Feature selection is utilised to decrease the complexity of the problem, with spectral acceleration at the fundamental period (<i>T</i>) of the structure (<i>S<sub>a</sub></i>), peak ground acceleration (<i>PGA</i>), peak ground velocity (<i>PGV</i>), and <i>T</i> being the primary factors impacting seismic demand estimation. The findings demonstrate the effectiveness of the proposed ANN approach in accurately predicting the seismic demands of BRBFs. |
| first_indexed | 2024-03-10T21:22:27Z |
| format | Article |
| id | doaj.art-53f5060faa87476e945d3a2d01342c37 |
| institution | Directory Open Access Journal |
| issn | 2075-5309 |
| language | English |
| last_indexed | 2024-03-10T21:22:27Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj.art-53f5060faa87476e945d3a2d01342c372023-11-19T15:55:51ZengMDPI AGBuildings2075-53092023-10-011310254210.3390/buildings13102542Utilising Artificial Neural Networks for Assessing Seismic Demands of Buckling Restrained Braces Due to Pulse-like MotionsAmirhossein Mohammadi0Shaghayegh Karimzadeh1Saman Yaghmaei-Sabegh2Maryam Ranjbari3Paulo B. Lourenço4Department of Civil Engineering, ARISE, Institute for Sustainability and Innovation in Structural Engineering (ISISE), University of Minho, 4800-058 Guimarães, PortugalDepartment of Civil Engineering, ARISE, Institute for Sustainability and Innovation in Structural Engineering (ISISE), University of Minho, 4800-058 Guimarães, PortugalDepartment of Civil Engineering, University of Tabriz, Tabriz 5166616471, IranDepartment of Civil Engineering, University of Tabriz, Tabriz 5166616471, IranDepartment of Civil Engineering, ARISE, Institute for Sustainability and Innovation in Structural Engineering (ISISE), University of Minho, 4800-058 Guimarães, PortugalBuckling restrained brace frames (BRBFs) exhibit exceptional lateral stiffness, load-bearing capacity, and energy dissipation properties, rendering them a highly promising choice for regions susceptible to seismic activity. The precise and expeditious prediction of seismic demands on BRBFs is a crucial and challenging task. In this paper, the potential of artificial neural networks (ANNs) to predict the seismic demands of BRBFs is explored. The study presents the characteristics and modelling of prototype BRBFs with different numbers of stories and material properties, utilising the OpenSees software (Version 2.5.0) for numerical simulations. The seismic performance of the BRBFs is evaluated using 91 near-fault pulse-like ground motions, and the maximum inter-storey drift ratio (<i>MIDR</i>) and global drift ratio (<i>GDR</i>) are recorded as a measure of seismic demand. ANNs are then trained to predict the <i>MIDR</i> and <i>GDR</i> of the selected prototypes. The model’s performance is assessed by analysing the residuals and error metrics and then comparing the trend of the results with the real dataset. Feature selection is utilised to decrease the complexity of the problem, with spectral acceleration at the fundamental period (<i>T</i>) of the structure (<i>S<sub>a</sub></i>), peak ground acceleration (<i>PGA</i>), peak ground velocity (<i>PGV</i>), and <i>T</i> being the primary factors impacting seismic demand estimation. The findings demonstrate the effectiveness of the proposed ANN approach in accurately predicting the seismic demands of BRBFs.https://www.mdpi.com/2075-5309/13/10/2542pulse-wise real ground motion recordsbuckling restrained brace frame (BRBF)maximum inter-storey drift ratio (<i>MIDR</i>)global drift ratio (<i>GDR</i>)feature selectionartificial neural network (ANN) |
| spellingShingle | Amirhossein Mohammadi Shaghayegh Karimzadeh Saman Yaghmaei-Sabegh Maryam Ranjbari Paulo B. Lourenço Utilising Artificial Neural Networks for Assessing Seismic Demands of Buckling Restrained Braces Due to Pulse-like Motions Buildings pulse-wise real ground motion records buckling restrained brace frame (BRBF) maximum inter-storey drift ratio (<i>MIDR</i>) global drift ratio (<i>GDR</i>) feature selection artificial neural network (ANN) |
| title | Utilising Artificial Neural Networks for Assessing Seismic Demands of Buckling Restrained Braces Due to Pulse-like Motions |
| title_full | Utilising Artificial Neural Networks for Assessing Seismic Demands of Buckling Restrained Braces Due to Pulse-like Motions |
| title_fullStr | Utilising Artificial Neural Networks for Assessing Seismic Demands of Buckling Restrained Braces Due to Pulse-like Motions |
| title_full_unstemmed | Utilising Artificial Neural Networks for Assessing Seismic Demands of Buckling Restrained Braces Due to Pulse-like Motions |
| title_short | Utilising Artificial Neural Networks for Assessing Seismic Demands of Buckling Restrained Braces Due to Pulse-like Motions |
| title_sort | utilising artificial neural networks for assessing seismic demands of buckling restrained braces due to pulse like motions |
| topic | pulse-wise real ground motion records buckling restrained brace frame (BRBF) maximum inter-storey drift ratio (<i>MIDR</i>) global drift ratio (<i>GDR</i>) feature selection artificial neural network (ANN) |
| url | https://www.mdpi.com/2075-5309/13/10/2542 |
| work_keys_str_mv | AT amirhosseinmohammadi utilisingartificialneuralnetworksforassessingseismicdemandsofbucklingrestrainedbracesduetopulselikemotions AT shaghayeghkarimzadeh utilisingartificialneuralnetworksforassessingseismicdemandsofbucklingrestrainedbracesduetopulselikemotions AT samanyaghmaeisabegh utilisingartificialneuralnetworksforassessingseismicdemandsofbucklingrestrainedbracesduetopulselikemotions AT maryamranjbari utilisingartificialneuralnetworksforassessingseismicdemandsofbucklingrestrainedbracesduetopulselikemotions AT pauloblourenco utilisingartificialneuralnetworksforassessingseismicdemandsofbucklingrestrainedbracesduetopulselikemotions |