Journal
ENGINEERING STRUCTURES
Volume 245, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.engstruct.2021.112836
Keywords
Concrete; Columns; FRP bars; Machine learning; eXtreme gradient boosting; SHapley Additive exPlanations; Design codes
Categories
Funding
- Tier 1 Canada Research Chair in Advanced Composite Materials for Civil Structures
- Natural Sciences and Engineering Research Council of Canada
- Fonds de la recherche du Quebec en nature et technologies (FQR-NT)
- Canadian Foundation for Innovation (FCI)
Ask authors/readers for more resources
This study introduces a new method for predicting the load-carrying capacity of FRP-RC columns using the XGBoost algorithm, outperforming other numerical equations. Important input variables for predicting the maximum axial load-carrying capacity include eccentricity ratio, gross sectional area, compressive strength of concrete, etc.
This study presents a new approach for predicting the load-carrying capacity of reinforced concrete (RC) columns reinforced with fiber-reinforced polymer (FRP) bars with an eXtreme Gradient Boosting (XGBoost) algorithm. The proposed XGBoost model was developed based on a comprehensive database containing experimental data for 283 FRP-RC columns collected from the literature. The SHapley Additive exPlanations (SHAP) framework was used to interpret the output of the model. Furthermore, the efficiency and accuracy of the XGBoost model were evaluated and compared with design codes and equations in the literature. The results show that the proposed prediction model performed extremely well and was suitable for predicting the load-carrying capacity of FRP-RC columns. Moreover, the XGBoost model outperformed other numerical equations. For short columns, the mean R-2 and MAPE values for the XGBoost model were 0.98% and 5.3%, respectively. In addition, the most significant input variables for predicting the maximum axial load-carrying capacity of FRP-RC columns were the eccentricity ratio, gross sectional area, compressive strength of concrete, slenderness ratio, and spacing or pitch of transversal reinforcement. Lastly, this study demonstrates the capability of machine learning models to predict the axial load-carrying capacity of FRP-RC columns. The proposed XGBoost model can provide an alternative method to existing mechanics-based models for design practice.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available