Multi-output machine learning for predicting the mechanical properties of BFRC
This investigation delves into the mechanical characteristics of Basalt Fiber Reinforced Concrete (BFRC), with a specific focus on compressive, flexural, and splitting tensile strengths. Employing a Multi-Output approach, six Machine Learning (ML) algorithms, namely Adaptive Boosting (AdaBoost), Lig...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-07-01
|
| Series: | Case Studies in Construction Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214509523009993 |
| _version_ | 1797377877690286080 |
|---|---|
| author | Alireza Najmoddin Hossein Etemadfard Amirhossein Hosseini.S Mansour Ghalehnovi |
| author_facet | Alireza Najmoddin Hossein Etemadfard Amirhossein Hosseini.S Mansour Ghalehnovi |
| author_sort | Alireza Najmoddin |
| collection | DOAJ |
| description | This investigation delves into the mechanical characteristics of Basalt Fiber Reinforced Concrete (BFRC), with a specific focus on compressive, flexural, and splitting tensile strengths. Employing a Multi-Output approach, six Machine Learning (ML) algorithms, namely Adaptive Boosting (AdaBoost), Light Gradient-Boosting Machine (LightGBM), Gradient Boosting, Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), and Random Forest, were used to predict the three output variables concurrently. The SHapley Additive exPlanations method facilitated sensitivity analysis, identifying influential factors, while Partial Dependence Plots (PDP) enhanced the comprehension of input impacts on the output values. The study revealed that the XGBoost algorithm exhibited superior performance, achieving an impressive R-squared value of 0.94 in predicting BFRC mechanical properties. Key parameters affecting compressive, flexural, and tensile strengths were pinpointed, emphasizing the critical roles of the water-to-cement ratio and coarse aggregates. PDP diagrams further unveiled optimal parameter ranges. The innovation of this research lies in its simultaneous prediction of multiple outputs, an approach that enhances the comprehensive assessment of BFRC mechanical properties. Furthermore, the utilization of SHapley Additive Explanations offers a robust method for interpreting results, enhancing transparency in model predictions. Lastly, the identification of critical parameters using PDP contributes valuable insights into the nuanced relationships governing BFRC behavior. Together, these innovations propel the field towards more accurate, interpretable, and insightful predictions in the realm of concrete technology. |
| first_indexed | 2024-03-08T19:59:41Z |
| format | Article |
| id | doaj.art-f9375917cc794f9ab8bac768f4f3195a |
| institution | Directory Open Access Journal |
| issn | 2214-5095 |
| language | English |
| last_indexed | 2024-03-08T19:59:41Z |
| publishDate | 2024-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Construction Materials |
| spelling | doaj.art-f9375917cc794f9ab8bac768f4f3195a2023-12-24T04:45:31ZengElsevierCase Studies in Construction Materials2214-50952024-07-0120e02818Multi-output machine learning for predicting the mechanical properties of BFRCAlireza Najmoddin0Hossein Etemadfard1Amirhossein Hosseini.S2Mansour Ghalehnovi3Dept. of Civil Engineering, Ferdowsi Univ. of Mashhad, Mashhad 93, IranCorresponding author.; Dept. of Civil Engineering, Ferdowsi Univ. of Mashhad, Mashhad 93, IranDept. of Civil Engineering, Ferdowsi Univ. of Mashhad, Mashhad 93, IranDept. of Civil Engineering, Ferdowsi Univ. of Mashhad, Mashhad 93, IranThis investigation delves into the mechanical characteristics of Basalt Fiber Reinforced Concrete (BFRC), with a specific focus on compressive, flexural, and splitting tensile strengths. Employing a Multi-Output approach, six Machine Learning (ML) algorithms, namely Adaptive Boosting (AdaBoost), Light Gradient-Boosting Machine (LightGBM), Gradient Boosting, Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), and Random Forest, were used to predict the three output variables concurrently. The SHapley Additive exPlanations method facilitated sensitivity analysis, identifying influential factors, while Partial Dependence Plots (PDP) enhanced the comprehension of input impacts on the output values. The study revealed that the XGBoost algorithm exhibited superior performance, achieving an impressive R-squared value of 0.94 in predicting BFRC mechanical properties. Key parameters affecting compressive, flexural, and tensile strengths were pinpointed, emphasizing the critical roles of the water-to-cement ratio and coarse aggregates. PDP diagrams further unveiled optimal parameter ranges. The innovation of this research lies in its simultaneous prediction of multiple outputs, an approach that enhances the comprehensive assessment of BFRC mechanical properties. Furthermore, the utilization of SHapley Additive Explanations offers a robust method for interpreting results, enhancing transparency in model predictions. Lastly, the identification of critical parameters using PDP contributes valuable insights into the nuanced relationships governing BFRC behavior. Together, these innovations propel the field towards more accurate, interpretable, and insightful predictions in the realm of concrete technology.http://www.sciencedirect.com/science/article/pii/S2214509523009993Eco-friendly ConcreteEnsemble LearningSensitivity AnalysisCompressive StrengthSplit Tensile StrengthFlexure Strength |
| spellingShingle | Alireza Najmoddin Hossein Etemadfard Amirhossein Hosseini.S Mansour Ghalehnovi Multi-output machine learning for predicting the mechanical properties of BFRC Case Studies in Construction Materials Eco-friendly Concrete Ensemble Learning Sensitivity Analysis Compressive Strength Split Tensile Strength Flexure Strength |
| title | Multi-output machine learning for predicting the mechanical properties of BFRC |
| title_full | Multi-output machine learning for predicting the mechanical properties of BFRC |
| title_fullStr | Multi-output machine learning for predicting the mechanical properties of BFRC |
| title_full_unstemmed | Multi-output machine learning for predicting the mechanical properties of BFRC |
| title_short | Multi-output machine learning for predicting the mechanical properties of BFRC |
| title_sort | multi output machine learning for predicting the mechanical properties of bfrc |
| topic | Eco-friendly Concrete Ensemble Learning Sensitivity Analysis Compressive Strength Split Tensile Strength Flexure Strength |
| url | http://www.sciencedirect.com/science/article/pii/S2214509523009993 |
| work_keys_str_mv | AT alirezanajmoddin multioutputmachinelearningforpredictingthemechanicalpropertiesofbfrc AT hosseinetemadfard multioutputmachinelearningforpredictingthemechanicalpropertiesofbfrc AT amirhosseinhosseinis multioutputmachinelearningforpredictingthemechanicalpropertiesofbfrc AT mansourghalehnovi multioutputmachinelearningforpredictingthemechanicalpropertiesofbfrc |