Holistic design of pre-tensioned concrete beams based on Artificial Intelligence
This research demonstrates how pre-tensioned concrete beams (PT beams) are designed holistically using artificial neural networks (ANNs). To establish reverse design scenarios, large input and output data are generated using the mechanics-based software AutoPTbeam. ANN-trained reverse-forward networ...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-05-01
|
| Series: | Journal of Asian Architecture and Building Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/13467581.2022.2097909 |
| _version_ | 1797803648026148864 |
|---|---|
| author | Won-Kee Hong Manh Cuong Nguyen Tien Dat Pham Thuc Anh Le |
| author_facet | Won-Kee Hong Manh Cuong Nguyen Tien Dat Pham Thuc Anh Le |
| author_sort | Won-Kee Hong |
| collection | DOAJ |
| description | This research demonstrates how pre-tensioned concrete beams (PT beams) are designed holistically using artificial neural networks (ANNs). To establish reverse design scenarios, large input and output data are generated using the mechanics-based software AutoPTbeam. ANN-trained reverse-forward networks are proposed to solve reverse designs with 15 input and 18 output parameters for engineers. ANNs for reverse designs pre-tensioned concrete beams are formulated based on 15 input structural parameters to investigate the performances of PT beams with pin-pin boundaries. Useful reverse designs based on neural networks can be established by relocating preferable control parameters on an input-side, such as when four output parameters ($${q_{L/250, }} {q_{0.2mm, }} {q_{str, }} {\mu _{\rm{\Delta }}}$$) (reverse scenario) are reversely pre-assigned on an input-side, all associated design parameters, including crack width, rebar strains at transfer load stage, rebar strains, and displacement ductility ratio at ultimate load stage are computed on an output-side. Deep neural networks trained by chained training scheme with revised sequence (CRS) for the reverse network of Step 1 show the better design accuracies when compared to those obtained based on ANNs trained by parallel training method (PTM) and based on shallow neural networks trained by CRS when the deflection ductility ratios (μΔ) within generated big datasets are reversely pre-assigned on an input-side. |
| first_indexed | 2024-03-13T05:24:00Z |
| format | Article |
| id | doaj.art-242c0899b5ba4fde8d83590d8a97a129 |
| institution | Directory Open Access Journal |
| issn | 1347-2852 |
| language | English |
| last_indexed | 2024-03-13T05:24:00Z |
| publishDate | 2023-05-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Journal of Asian Architecture and Building Engineering |
| spelling | doaj.art-242c0899b5ba4fde8d83590d8a97a1292023-06-15T09:22:31ZengTaylor & Francis GroupJournal of Asian Architecture and Building Engineering1347-28522023-05-012231714174510.1080/13467581.2022.20979092097909Holistic design of pre-tensioned concrete beams based on Artificial IntelligenceWon-Kee Hong0Manh Cuong Nguyen1Tien Dat Pham2Thuc Anh Le3Kyung Hee UniversityKyung Hee UniversityKyung Hee UniversityKyung Hee UniversityThis research demonstrates how pre-tensioned concrete beams (PT beams) are designed holistically using artificial neural networks (ANNs). To establish reverse design scenarios, large input and output data are generated using the mechanics-based software AutoPTbeam. ANN-trained reverse-forward networks are proposed to solve reverse designs with 15 input and 18 output parameters for engineers. ANNs for reverse designs pre-tensioned concrete beams are formulated based on 15 input structural parameters to investigate the performances of PT beams with pin-pin boundaries. Useful reverse designs based on neural networks can be established by relocating preferable control parameters on an input-side, such as when four output parameters ($${q_{L/250, }} {q_{0.2mm, }} {q_{str, }} {\mu _{\rm{\Delta }}}$$) (reverse scenario) are reversely pre-assigned on an input-side, all associated design parameters, including crack width, rebar strains at transfer load stage, rebar strains, and displacement ductility ratio at ultimate load stage are computed on an output-side. Deep neural networks trained by chained training scheme with revised sequence (CRS) for the reverse network of Step 1 show the better design accuracies when compared to those obtained based on ANNs trained by parallel training method (PTM) and based on shallow neural networks trained by CRS when the deflection ductility ratios (μΔ) within generated big datasets are reversely pre-assigned on an input-side.http://dx.doi.org/10.1080/13467581.2022.2097909artificial intelligencepre-tensioned beamsreverse designsdesign chartcurvature ductility |
| spellingShingle | Won-Kee Hong Manh Cuong Nguyen Tien Dat Pham Thuc Anh Le Holistic design of pre-tensioned concrete beams based on Artificial Intelligence Journal of Asian Architecture and Building Engineering artificial intelligence pre-tensioned beams reverse designs design chart curvature ductility |
| title | Holistic design of pre-tensioned concrete beams based on Artificial Intelligence |
| title_full | Holistic design of pre-tensioned concrete beams based on Artificial Intelligence |
| title_fullStr | Holistic design of pre-tensioned concrete beams based on Artificial Intelligence |
| title_full_unstemmed | Holistic design of pre-tensioned concrete beams based on Artificial Intelligence |
| title_short | Holistic design of pre-tensioned concrete beams based on Artificial Intelligence |
| title_sort | holistic design of pre tensioned concrete beams based on artificial intelligence |
| topic | artificial intelligence pre-tensioned beams reverse designs design chart curvature ductility |
| url | http://dx.doi.org/10.1080/13467581.2022.2097909 |
| work_keys_str_mv | AT wonkeehong holisticdesignofpretensionedconcretebeamsbasedonartificialintelligence AT manhcuongnguyen holisticdesignofpretensionedconcretebeamsbasedonartificialintelligence AT tiendatpham holisticdesignofpretensionedconcretebeamsbasedonartificialintelligence AT thucanhle holisticdesignofpretensionedconcretebeamsbasedonartificialintelligence |