Machine Learning-Based Prediction of the Seismic Bearing Capacity of a Shallow Strip Footing over a Void in Heterogeneous Soils
The seismic bearing capacity of a shallow strip footing above a void displays a complex dependence on several characteristics, linked to geometric problems and to the soil properties. Hence, setting analytical models to estimate such bearing capacity is extremely challenging. In this work, machine l...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/14/10/288 |
| _version_ | 1797515544883101696 |
|---|---|
| author | Mohammad Sadegh Es-haghi Mohsen Abbaspour Hamidreza Abbasianjahromi Stefano Mariani |
| author_facet | Mohammad Sadegh Es-haghi Mohsen Abbaspour Hamidreza Abbasianjahromi Stefano Mariani |
| author_sort | Mohammad Sadegh Es-haghi |
| collection | DOAJ |
| description | The seismic bearing capacity of a shallow strip footing above a void displays a complex dependence on several characteristics, linked to geometric problems and to the soil properties. Hence, setting analytical models to estimate such bearing capacity is extremely challenging. In this work, machine learning (ML) techniques have been employed to predict the seismic bearing capacity of a shallow strip footing located over a single unsupported rectangular void in heterogeneous soil. A dataset consisting of 38,000 finite element limit analysis simulations has been created, and the mean value between the upper and lower bounds of the bearing capacity has been computed at the varying undrained shear strength and internal friction angle of the soil, horizontal earthquake accelerations, and position, shape, and size of the void. Three machine learning techniques have been adopted to learn the link between the aforementioned parameters and the bearing capacity: multilayer perceptron neural networks; a group method of data handling; and a combined adaptive-network-based fuzzy inference system and particle swarm optimization. The performances of these ML techniques have been compared with each other, in terms of the following statistical performance indices: coefficient of determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi mathvariant="normal">R</mi><mn>2</mn></msup></mrow></semantics></math></inline-formula>); root mean square error (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RMSE</mi></mrow></semantics></math></inline-formula>); mean absolute percentage error; scatter index; and standard bias. Results have shown that all the ML techniques perform well, though the multilayer perceptron has a slightly superior accuracy featuring noteworthy results (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi mathvariant="normal">R</mi><mn>2</mn></msup><mo>=</mo></mrow></semantics></math></inline-formula> 0.9955 and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RMSE</mi><mo>=</mo></mrow></semantics></math></inline-formula> 0.0158). |
| first_indexed | 2024-03-10T06:46:54Z |
| format | Article |
| id | doaj.art-0ec11176897d4cb2ab1f2a57f2ace245 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-10T06:46:54Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-0ec11176897d4cb2ab1f2a57f2ace2452023-11-22T17:08:23ZengMDPI AGAlgorithms1999-48932021-09-01141028810.3390/a14100288Machine Learning-Based Prediction of the Seismic Bearing Capacity of a Shallow Strip Footing over a Void in Heterogeneous SoilsMohammad Sadegh Es-haghi0Mohsen Abbaspour1Hamidreza Abbasianjahromi2Stefano Mariani3School of Civil Engineering, K.N. Toosi University of Technology, Tehran 19697-64499, IranDepartment of Civil & Environmental Engineering, Amirkabir University of Technology, Tehran 56131–56491, IranDepartment of Civil and Environmental Engineering, K.N. Toosi University of Technology, Tehran 19697-64499, IranDepartment of Civil and Environmental Engineering, Politecnico di Milano, Piazza L. da Vinci 32, 20133 Milan, ItalyThe seismic bearing capacity of a shallow strip footing above a void displays a complex dependence on several characteristics, linked to geometric problems and to the soil properties. Hence, setting analytical models to estimate such bearing capacity is extremely challenging. In this work, machine learning (ML) techniques have been employed to predict the seismic bearing capacity of a shallow strip footing located over a single unsupported rectangular void in heterogeneous soil. A dataset consisting of 38,000 finite element limit analysis simulations has been created, and the mean value between the upper and lower bounds of the bearing capacity has been computed at the varying undrained shear strength and internal friction angle of the soil, horizontal earthquake accelerations, and position, shape, and size of the void. Three machine learning techniques have been adopted to learn the link between the aforementioned parameters and the bearing capacity: multilayer perceptron neural networks; a group method of data handling; and a combined adaptive-network-based fuzzy inference system and particle swarm optimization. The performances of these ML techniques have been compared with each other, in terms of the following statistical performance indices: coefficient of determination (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi mathvariant="normal">R</mi><mn>2</mn></msup></mrow></semantics></math></inline-formula>); root mean square error (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RMSE</mi></mrow></semantics></math></inline-formula>); mean absolute percentage error; scatter index; and standard bias. Results have shown that all the ML techniques perform well, though the multilayer perceptron has a slightly superior accuracy featuring noteworthy results (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi mathvariant="normal">R</mi><mn>2</mn></msup><mo>=</mo></mrow></semantics></math></inline-formula> 0.9955 and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>RMSE</mi><mo>=</mo></mrow></semantics></math></inline-formula> 0.0158).https://www.mdpi.com/1999-4893/14/10/288shallow strip footingseismic bearing capacityfinite element limit analysisheterogeneous soilmachine learning |
| spellingShingle | Mohammad Sadegh Es-haghi Mohsen Abbaspour Hamidreza Abbasianjahromi Stefano Mariani Machine Learning-Based Prediction of the Seismic Bearing Capacity of a Shallow Strip Footing over a Void in Heterogeneous Soils Algorithms shallow strip footing seismic bearing capacity finite element limit analysis heterogeneous soil machine learning |
| title | Machine Learning-Based Prediction of the Seismic Bearing Capacity of a Shallow Strip Footing over a Void in Heterogeneous Soils |
| title_full | Machine Learning-Based Prediction of the Seismic Bearing Capacity of a Shallow Strip Footing over a Void in Heterogeneous Soils |
| title_fullStr | Machine Learning-Based Prediction of the Seismic Bearing Capacity of a Shallow Strip Footing over a Void in Heterogeneous Soils |
| title_full_unstemmed | Machine Learning-Based Prediction of the Seismic Bearing Capacity of a Shallow Strip Footing over a Void in Heterogeneous Soils |
| title_short | Machine Learning-Based Prediction of the Seismic Bearing Capacity of a Shallow Strip Footing over a Void in Heterogeneous Soils |
| title_sort | machine learning based prediction of the seismic bearing capacity of a shallow strip footing over a void in heterogeneous soils |
| topic | shallow strip footing seismic bearing capacity finite element limit analysis heterogeneous soil machine learning |
| url | https://www.mdpi.com/1999-4893/14/10/288 |
| work_keys_str_mv | AT mohammadsadegheshaghi machinelearningbasedpredictionoftheseismicbearingcapacityofashallowstripfootingoveravoidinheterogeneoussoils AT mohsenabbaspour machinelearningbasedpredictionoftheseismicbearingcapacityofashallowstripfootingoveravoidinheterogeneoussoils AT hamidrezaabbasianjahromi machinelearningbasedpredictionoftheseismicbearingcapacityofashallowstripfootingoveravoidinheterogeneoussoils AT stefanomariani machinelearningbasedpredictionoftheseismicbearingcapacityofashallowstripfootingoveravoidinheterogeneoussoils |