Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns

Celal Cakiroglu; Kamrul Islam; Gebrail Bekdaş; Sanghun Kim; Zong Woo Geem

doi:10.3390/ma15082742

Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns

Materials (Basel). 2022 Apr 8;15(8):2742. doi: 10.3390/ma15082742.

Authors

Celal Cakiroglu¹, Kamrul Islam², Gebrail Bekdaş³, Sanghun Kim⁴, Zong Woo Geem⁵

Affiliations

¹ Department of Civil Engineering, Turkish-German University, Istanbul 34820, Turkey.
² Department of Civil, Geological and Mining Engineering, Polytechnique Montréal, Montreal, QC H3C 3A7, Canada.
³ Department of Civil Engineering, Istanbul University-Cerrahpasa, Istanbul 34320, Turkey.
⁴ Department of Civil and Environmental Engineering, Temple University, Philadelphia, PA 19122, USA.
⁵ Department of Smart City & Energy, Gachon University, Seongnam 13120, Korea.

Abstract

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.

Keywords: axial capacity; ensemble learning; fiber-reinforced polymer (FRP) rebar; harmony search optimization; machine learning; reinforced concrete columns.