Stacking Ensemble-Based Machine Learning Model for Predicting Deterioration Components of Steel W-Section Beams
The collapse evaluation of the structural systems under seismic loading necessitates identifying and quantifying deterioration components (DCs). In the case of steel w-section beams (SWSB), three distinct types of DCs have been derived. These deterioration components for steel beams comprise the fol...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/14/1/240 |
| _version_ | 1797339961104531456 |
|---|---|
| author | A. Khoshkroodi H. Parvini Sani M. Aajami |
| author_facet | A. Khoshkroodi H. Parvini Sani M. Aajami |
| author_sort | A. Khoshkroodi |
| collection | DOAJ |
| description | The collapse evaluation of the structural systems under seismic loading necessitates identifying and quantifying deterioration components (DCs). In the case of steel w-section beams (SWSB), three distinct types of DCs have been derived. These deterioration components for steel beams comprise the following: pre-capping plastic rotation (θ<sub>p</sub>), post-capping plastic rotation (θ<sub>pc</sub>), and cumulative rotation capacity (Λ). The primary objective of this research is to employ a machine learning (ML) model for accurate determination of these deterioration components. The stacking model is a powerful combination of meta-learners, which is used for better learning and performance of base learners. The base learners consist of AdaBoost, Random Forest (RF), and XGBoost. Among various machine learning algorithms, the stacking model exhibited superior functioning. The evaluation metrics of the stacking model were as follows: R<sup>2</sup> = 0.9 and RMSE = 0.003 for θ<sub>p</sub>, R<sup>2</sup> = 0.97 and RMSE = 0.012 for θ<sub>pc</sub>, and R<sup>2</sup> = 0.98 and RMSE = 0.09 for Λ. The significance of input variables, specifically the web-depth-over-web-thickness ratio (h/t<sub>w</sub>) and the flange width-to-thickness ratio (b<sub>f</sub>/2t<sub>f</sub>), in determining the deterioration components was assessed using the Shapley Additive Explanations model. These parameters emerged as the most crucial factors in the evaluation. |
| first_indexed | 2024-03-08T09:56:06Z |
| format | Article |
| id | doaj.art-b637c20ca09c45b0aeb4b528d015e447 |
| institution | Directory Open Access Journal |
| issn | 2075-5309 |
| language | English |
| last_indexed | 2024-03-08T09:56:06Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj.art-b637c20ca09c45b0aeb4b528d015e4472024-01-29T13:49:26ZengMDPI AGBuildings2075-53092024-01-0114124010.3390/buildings14010240Stacking Ensemble-Based Machine Learning Model for Predicting Deterioration Components of Steel W-Section BeamsA. Khoshkroodi0H. Parvini Sani1M. Aajami2Department of Civil Engineering, Zanjan Branch, Islamic Azad University, Zanjan 45156-58145, IranDepartment of Civil Engineering, Zanjan Branch, Islamic Azad University, Zanjan 45156-58145, IranDepartment of Computer Engineering, Zanjan Branch, Islamic Azad University, Zanjan 45156-58145, IranThe collapse evaluation of the structural systems under seismic loading necessitates identifying and quantifying deterioration components (DCs). In the case of steel w-section beams (SWSB), three distinct types of DCs have been derived. These deterioration components for steel beams comprise the following: pre-capping plastic rotation (θ<sub>p</sub>), post-capping plastic rotation (θ<sub>pc</sub>), and cumulative rotation capacity (Λ). The primary objective of this research is to employ a machine learning (ML) model for accurate determination of these deterioration components. The stacking model is a powerful combination of meta-learners, which is used for better learning and performance of base learners. The base learners consist of AdaBoost, Random Forest (RF), and XGBoost. Among various machine learning algorithms, the stacking model exhibited superior functioning. The evaluation metrics of the stacking model were as follows: R<sup>2</sup> = 0.9 and RMSE = 0.003 for θ<sub>p</sub>, R<sup>2</sup> = 0.97 and RMSE = 0.012 for θ<sub>pc</sub>, and R<sup>2</sup> = 0.98 and RMSE = 0.09 for Λ. The significance of input variables, specifically the web-depth-over-web-thickness ratio (h/t<sub>w</sub>) and the flange width-to-thickness ratio (b<sub>f</sub>/2t<sub>f</sub>), in determining the deterioration components was assessed using the Shapley Additive Explanations model. These parameters emerged as the most crucial factors in the evaluation.https://www.mdpi.com/2075-5309/14/1/240deterioration componentsmachine learningAdaBoostrandom forestXGBooststacking |
| spellingShingle | A. Khoshkroodi H. Parvini Sani M. Aajami Stacking Ensemble-Based Machine Learning Model for Predicting Deterioration Components of Steel W-Section Beams Buildings deterioration components machine learning AdaBoost random forest XGBoost stacking |
| title | Stacking Ensemble-Based Machine Learning Model for Predicting Deterioration Components of Steel W-Section Beams |
| title_full | Stacking Ensemble-Based Machine Learning Model for Predicting Deterioration Components of Steel W-Section Beams |
| title_fullStr | Stacking Ensemble-Based Machine Learning Model for Predicting Deterioration Components of Steel W-Section Beams |
| title_full_unstemmed | Stacking Ensemble-Based Machine Learning Model for Predicting Deterioration Components of Steel W-Section Beams |
| title_short | Stacking Ensemble-Based Machine Learning Model for Predicting Deterioration Components of Steel W-Section Beams |
| title_sort | stacking ensemble based machine learning model for predicting deterioration components of steel w section beams |
| topic | deterioration components machine learning AdaBoost random forest XGBoost stacking |
| url | https://www.mdpi.com/2075-5309/14/1/240 |
| work_keys_str_mv | AT akhoshkroodi stackingensemblebasedmachinelearningmodelforpredictingdeteriorationcomponentsofsteelwsectionbeams AT hparvinisani stackingensemblebasedmachinelearningmodelforpredictingdeteriorationcomponentsofsteelwsectionbeams AT maajami stackingensemblebasedmachinelearningmodelforpredictingdeteriorationcomponentsofsteelwsectionbeams |