Analysis of artificial intelligence approaches to predict the wall deflection induced by deep excavation
The geological condition of Ho Chi Minh (HCM) City is soft soil and high groundwater and includes two main structural layers such as Pleistocene and Holocene sediments. Therefore, deep excavation of all the high-rise buildings in the city is usually supported by concrete retaining walls such as the...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2023-08-01
|
| Series: | Open Geosciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/geo-2022-0503 |
| _version_ | 1797693246906826752 |
|---|---|
| author | Tran DinhHieu Nguyen HongGiang Wang YuRen Phan KhacHai Phu ThiTuyetNga Le DuyPhuong Nguyen TienThinh |
| author_facet | Tran DinhHieu Nguyen HongGiang Wang YuRen Phan KhacHai Phu ThiTuyetNga Le DuyPhuong Nguyen TienThinh |
| author_sort | Tran DinhHieu |
| collection | DOAJ |
| description | The geological condition of Ho Chi Minh (HCM) City is soft soil and high groundwater and includes two main structural layers such as Pleistocene and Holocene sediments. Therefore, deep excavation of all the high-rise buildings in the city is usually supported by concrete retaining walls such as the diaphragm or bored pile retaining walls. The system limits the excavation wall deflection during the construction process which could pose a potential risk to the construction and neighborhood areas. To estimate wall deformation at a highly accurate and efficient level, this study presents several machine learning models including feed-forward neural network back-propagation (FFNN-BP), long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), and support vector regression (SVR). The database for the experiment was obtained from a high building in HCM City, Vietnam. The database is deployed to implement the proposed algorithms in walk-forward validation technique. As a result, the Bi-LSTM model reduced prediction errors and improved robustness than the LSTM, FFNN-BP, and SVR models. Bi-LSTM, LSTM, and FFNN-PB could be used for predicting deep excavation wall deflection. In the meantime, not only could the estimated results support safety monitoring and early warning during the construction stages but also could contribute to legal guidelines for the architecture of deep excavations in the city’s soft ground. |
| first_indexed | 2024-03-12T02:40:46Z |
| format | Article |
| id | doaj.art-f06dd7e238f64cc1a2b8e2252c3ed95c |
| institution | Directory Open Access Journal |
| issn | 2391-5447 |
| language | English |
| last_indexed | 2024-03-12T02:40:46Z |
| publishDate | 2023-08-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Open Geosciences |
| spelling | doaj.art-f06dd7e238f64cc1a2b8e2252c3ed95c2023-09-04T07:09:42ZengDe GruyterOpen Geosciences2391-54472023-08-0115159461910.1515/geo-2022-0503Analysis of artificial intelligence approaches to predict the wall deflection induced by deep excavationTran DinhHieu0Nguyen HongGiang1Wang YuRen2Phan KhacHai3Phu ThiTuyetNga4Le DuyPhuong5Nguyen TienThinh6Faculty of Architecture, Thu Dau Mot University, ThuDauMot820000, VietnamDepartment of Academic and Students' Affairs, Hue University, Hue City 49000, VietnamDepartment of Civil Engineering, National Kaohsiung University of Science and Technology, Kaohsiung80778, TaiwanGeotech Science Co., Ltd, New Taipei City22103, TaiwanFaculty of Architecture, Thu Dau Mot University, ThuDauMot820000, VietnamDepartment of Planning and Investment of Tay Ninh Province, Tay Ninh, 840000, VietnamDepartment of International Business, National Kaohsiung University of Science and Technology, Kaohsiung82445, TaiwanThe geological condition of Ho Chi Minh (HCM) City is soft soil and high groundwater and includes two main structural layers such as Pleistocene and Holocene sediments. Therefore, deep excavation of all the high-rise buildings in the city is usually supported by concrete retaining walls such as the diaphragm or bored pile retaining walls. The system limits the excavation wall deflection during the construction process which could pose a potential risk to the construction and neighborhood areas. To estimate wall deformation at a highly accurate and efficient level, this study presents several machine learning models including feed-forward neural network back-propagation (FFNN-BP), long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), and support vector regression (SVR). The database for the experiment was obtained from a high building in HCM City, Vietnam. The database is deployed to implement the proposed algorithms in walk-forward validation technique. As a result, the Bi-LSTM model reduced prediction errors and improved robustness than the LSTM, FFNN-BP, and SVR models. Bi-LSTM, LSTM, and FFNN-PB could be used for predicting deep excavation wall deflection. In the meantime, not only could the estimated results support safety monitoring and early warning during the construction stages but also could contribute to legal guidelines for the architecture of deep excavations in the city’s soft ground.https://doi.org/10.1515/geo-2022-0503excavationdeformationretaining wallmachine learning and deep learning prediction |
| spellingShingle | Tran DinhHieu Nguyen HongGiang Wang YuRen Phan KhacHai Phu ThiTuyetNga Le DuyPhuong Nguyen TienThinh Analysis of artificial intelligence approaches to predict the wall deflection induced by deep excavation Open Geosciences excavation deformation retaining wall machine learning and deep learning prediction |
| title | Analysis of artificial intelligence approaches to predict the wall deflection induced by deep excavation |
| title_full | Analysis of artificial intelligence approaches to predict the wall deflection induced by deep excavation |
| title_fullStr | Analysis of artificial intelligence approaches to predict the wall deflection induced by deep excavation |
| title_full_unstemmed | Analysis of artificial intelligence approaches to predict the wall deflection induced by deep excavation |
| title_short | Analysis of artificial intelligence approaches to predict the wall deflection induced by deep excavation |
| title_sort | analysis of artificial intelligence approaches to predict the wall deflection induced by deep excavation |
| topic | excavation deformation retaining wall machine learning and deep learning prediction |
| url | https://doi.org/10.1515/geo-2022-0503 |
| work_keys_str_mv | AT trandinhhieu analysisofartificialintelligenceapproachestopredictthewalldeflectioninducedbydeepexcavation AT nguyenhonggiang analysisofartificialintelligenceapproachestopredictthewalldeflectioninducedbydeepexcavation AT wangyuren analysisofartificialintelligenceapproachestopredictthewalldeflectioninducedbydeepexcavation AT phankhachai analysisofartificialintelligenceapproachestopredictthewalldeflectioninducedbydeepexcavation AT phuthituyetnga analysisofartificialintelligenceapproachestopredictthewalldeflectioninducedbydeepexcavation AT leduyphuong analysisofartificialintelligenceapproachestopredictthewalldeflectioninducedbydeepexcavation AT nguyentienthinh analysisofartificialintelligenceapproachestopredictthewalldeflectioninducedbydeepexcavation |