Integrated machine learning for modeling bearing capacity of shallow foundations
Abstract Analyzing the stability of footings is a significant step in civil/geotechnical engineering projects. In this work, two novel predictive tools are suggested based on an artificial neural network (ANN) to analyze the bearing capacity of a footing installed on a two-layered soil mass. To this...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-58534-5 |
| _version_ | 1797209368661327872 |
|---|---|
| author | Yuzhen Liu Yan Liang |
| author_facet | Yuzhen Liu Yan Liang |
| author_sort | Yuzhen Liu |
| collection | DOAJ |
| description | Abstract Analyzing the stability of footings is a significant step in civil/geotechnical engineering projects. In this work, two novel predictive tools are suggested based on an artificial neural network (ANN) to analyze the bearing capacity of a footing installed on a two-layered soil mass. To this end, backtracking search algorithm (BSA) and equilibrium optimizer (EO) are employed to train the ANN for approximating the stability value (SV) of the system. After executing a set of finite element analyses, the settlement values lower/higher than 5 cm are considered to indicate the stability/failure of the system. The results demonstrated the efficiency of these algorithms in fulfilling the assigned task. In detail, the training error of the ANN (in terms of root mean square error—RMSE)) dropped from 0.3585 to 0.3165 (11.72%) and 0.2959 (17.46%) by applying the BSA and EO, respectively. Moreover, the prediction accuracy of the ANN climbed from 93.7 to 94.3% and 94.1% (in terms of area under the receiving operating characteristics curve—AUROC). A comparison between the elite complexities of these algorithms showed that the EO enjoys a larger accuracy, while BSA is a more time-effective optimizer. Lastly, an explicit mathematical formula is derived from the EO-ANN model to be conveniently used in predicting the SV. |
| first_indexed | 2024-04-24T09:53:36Z |
| format | Article |
| id | doaj.art-c21d795a13cc48559506bd8566291845 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T09:53:36Z |
| publishDate | 2024-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-c21d795a13cc48559506bd85662918452024-04-14T11:16:47ZengNature PortfolioScientific Reports2045-23222024-04-0114111510.1038/s41598-024-58534-5Integrated machine learning for modeling bearing capacity of shallow foundationsYuzhen Liu0Yan Liang1Bim School of Technology and Industry, Changchun Institute of TechnologyInfrastructure Logistics Office, Jilin Engineering Normal UniversityAbstract Analyzing the stability of footings is a significant step in civil/geotechnical engineering projects. In this work, two novel predictive tools are suggested based on an artificial neural network (ANN) to analyze the bearing capacity of a footing installed on a two-layered soil mass. To this end, backtracking search algorithm (BSA) and equilibrium optimizer (EO) are employed to train the ANN for approximating the stability value (SV) of the system. After executing a set of finite element analyses, the settlement values lower/higher than 5 cm are considered to indicate the stability/failure of the system. The results demonstrated the efficiency of these algorithms in fulfilling the assigned task. In detail, the training error of the ANN (in terms of root mean square error—RMSE)) dropped from 0.3585 to 0.3165 (11.72%) and 0.2959 (17.46%) by applying the BSA and EO, respectively. Moreover, the prediction accuracy of the ANN climbed from 93.7 to 94.3% and 94.1% (in terms of area under the receiving operating characteristics curve—AUROC). A comparison between the elite complexities of these algorithms showed that the EO enjoys a larger accuracy, while BSA is a more time-effective optimizer. Lastly, an explicit mathematical formula is derived from the EO-ANN model to be conveniently used in predicting the SV.https://doi.org/10.1038/s41598-024-58534-5Geotechnical engineeringBearing capacity analysisMachine learningMetaheuristic algorithms |
| spellingShingle | Yuzhen Liu Yan Liang Integrated machine learning for modeling bearing capacity of shallow foundations Scientific Reports Geotechnical engineering Bearing capacity analysis Machine learning Metaheuristic algorithms |
| title | Integrated machine learning for modeling bearing capacity of shallow foundations |
| title_full | Integrated machine learning for modeling bearing capacity of shallow foundations |
| title_fullStr | Integrated machine learning for modeling bearing capacity of shallow foundations |
| title_full_unstemmed | Integrated machine learning for modeling bearing capacity of shallow foundations |
| title_short | Integrated machine learning for modeling bearing capacity of shallow foundations |
| title_sort | integrated machine learning for modeling bearing capacity of shallow foundations |
| topic | Geotechnical engineering Bearing capacity analysis Machine learning Metaheuristic algorithms |
| url | https://doi.org/10.1038/s41598-024-58534-5 |
| work_keys_str_mv | AT yuzhenliu integratedmachinelearningformodelingbearingcapacityofshallowfoundations AT yanliang integratedmachinelearningformodelingbearingcapacityofshallowfoundations |