Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns
Fiber-reinforced polymer (FRP) rebars are increasingly being used as an alternative to steel rebars in reinforced concrete (RC) members due to their excellent corrosion resistance capability and enhanced mechanical properties. Extensive research works have been performed in the last two decades to d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/15/8/2742 |
| _version_ | 1797434443485413376 |
|---|---|
| author | Celal Cakiroglu Kamrul Islam Gebrail Bekdaş Sanghun Kim Zong Woo Geem |
| author_facet | Celal Cakiroglu Kamrul Islam Gebrail Bekdaş Sanghun Kim Zong Woo Geem |
| author_sort | Celal Cakiroglu |
| collection | DOAJ |
| description | Fiber-reinforced polymer (FRP) rebars are increasingly being used as an alternative to steel rebars in reinforced concrete (RC) members due to their excellent corrosion resistance capability and enhanced mechanical properties. Extensive research works have been performed in the last two decades to develop predictive models, codes, and guidelines to estimate the axial load-carrying capacity of FRP-RC columns. This study utilizes the power of artificial intelligence and develops an alternative approach to predict the axial capacity of FRP-RC columns more accurately using data-driven machine learning (ML) algorithms. A database of 117 tests of axially loaded FRP-RC columns is collected from the literature. The geometric and material properties, column shape and slenderness ratio, reinforcement details, and FRP types are used as the input variables, while the load-carrying capacity is used as the output response to develop the ML models. Furthermore, the input-output relationship of the ML model is explained through feature importance analysis and the SHapely Additive exPlanations (SHAP) approach. Eight ML models, namely, Kernel Ridge Regression, Lasso Regression, Support Vector Machine, Gradient Boosting Machine, Adaptive Boosting, Random Forest, Categorical Gradient Boosting, and Extreme Gradient Boosting, are used in this study for capacity prediction, and their relative performances are compared to identify the best-performing ML model. Finally, predictive equations are proposed using the harmony search optimization and the model interpretations obtained through the SHAP algorithm. |
| first_indexed | 2024-03-09T10:32:19Z |
| format | Article |
| id | doaj.art-abc2d731f3184b89a1128c121150d411 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-09T10:32:19Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-abc2d731f3184b89a1128c121150d4112023-12-01T21:10:33ZengMDPI AGMaterials1996-19442022-04-01158274210.3390/ma15082742Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete ColumnsCelal Cakiroglu0Kamrul Islam1Gebrail Bekdaş2Sanghun Kim3Zong Woo Geem4Department of Civil Engineering, Turkish-German University, Istanbul 34820, TurkeyDepartment of Civil, Geological and Mining Engineering, Polytechnique Montréal, Montreal, QC H3C 3A7, CanadaDepartment of Civil Engineering, Istanbul University—Cerrahpasa, Istanbul 34320, TurkeyDepartment of Civil and Environmental Engineering, Temple University, Philadelphia, PA 19122, USADepartment of Smart City & Energy, Gachon University, Seongnam 13120, KoreaFiber-reinforced polymer (FRP) rebars are increasingly being used as an alternative to steel rebars in reinforced concrete (RC) members due to their excellent corrosion resistance capability and enhanced mechanical properties. Extensive research works have been performed in the last two decades to develop predictive models, codes, and guidelines to estimate the axial load-carrying capacity of FRP-RC columns. This study utilizes the power of artificial intelligence and develops an alternative approach to predict the axial capacity of FRP-RC columns more accurately using data-driven machine learning (ML) algorithms. A database of 117 tests of axially loaded FRP-RC columns is collected from the literature. The geometric and material properties, column shape and slenderness ratio, reinforcement details, and FRP types are used as the input variables, while the load-carrying capacity is used as the output response to develop the ML models. Furthermore, the input-output relationship of the ML model is explained through feature importance analysis and the SHapely Additive exPlanations (SHAP) approach. Eight ML models, namely, Kernel Ridge Regression, Lasso Regression, Support Vector Machine, Gradient Boosting Machine, Adaptive Boosting, Random Forest, Categorical Gradient Boosting, and Extreme Gradient Boosting, are used in this study for capacity prediction, and their relative performances are compared to identify the best-performing ML model. Finally, predictive equations are proposed using the harmony search optimization and the model interpretations obtained through the SHAP algorithm.https://www.mdpi.com/1996-1944/15/8/2742fiber-reinforced polymer (FRP) rebarreinforced concrete columnsaxial capacitymachine learningensemble learningharmony search optimization |
| spellingShingle | Celal Cakiroglu Kamrul Islam Gebrail Bekdaş Sanghun Kim Zong Woo Geem Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns Materials fiber-reinforced polymer (FRP) rebar reinforced concrete columns axial capacity machine learning ensemble learning harmony search optimization |
| title | Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns |
| title_full | Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns |
| title_fullStr | Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns |
| title_full_unstemmed | Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns |
| title_short | Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns |
| title_sort | interpretable machine learning algorithms to predict the axial capacity of frp reinforced concrete columns |
| topic | fiber-reinforced polymer (FRP) rebar reinforced concrete columns axial capacity machine learning ensemble learning harmony search optimization |
| url | https://www.mdpi.com/1996-1944/15/8/2742 |
| work_keys_str_mv | AT celalcakiroglu interpretablemachinelearningalgorithmstopredicttheaxialcapacityoffrpreinforcedconcretecolumns AT kamrulislam interpretablemachinelearningalgorithmstopredicttheaxialcapacityoffrpreinforcedconcretecolumns AT gebrailbekdas interpretablemachinelearningalgorithmstopredicttheaxialcapacityoffrpreinforcedconcretecolumns AT sanghunkim interpretablemachinelearningalgorithmstopredicttheaxialcapacityoffrpreinforcedconcretecolumns AT zongwoogeem interpretablemachinelearningalgorithmstopredicttheaxialcapacityoffrpreinforcedconcretecolumns |