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

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.

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

“…Previous studies in the area of optimal structural dimensioning mostly attempted to minimize structural cost or weight for a single load case [ 8 , 9 ]. More recent studies in the area attempted to develop general-purpose predictive models based on a dataset of structural configurations with known structural behavior [ 21 , 22 ]. However, the availability of experimental or numerical data describing the structural behavior is a major limiting factor in the training of robust predictive models since the size of the database used in the training of these predictive models is a decisive factor that effects to what extent these models could be used reliably.…”

“…Bekdaş et al [ 21 ] demonstrated the high accuracy of different Ensemble Learning Algorithms in predicting the optimal wall thickness of reinforced concrete cylindrical walls. Cakiroglu et al [ 22 ] developed predictive models using Ensemble Learning Algorithms to estimate the axial load-carrying capacity of FRP-reinforced concrete columns.…”

A Systematic Review of the Research Development on the Application of Machine Learning for Concrete

“…[63][64][65][66][67][68][69][70]. Estimations of various characteristics of conventional and advanced concretes, such as durability, thermal characteristics, and mechanical characteristics, have been extensively covered in previous studies [71][72][73][74].…”

Estimating the Axial Compression Capacity of Concrete-Filled Double-Skin Tubular Columns with Metallic and Non-Metallic Composite Materials

“…The other objective of the current study is to develop opensource, Python-based ML models to estimate the axial load-carrying capacity of CFDST columns to further help researchers utilise the developed models to improve the framework once additional experimental data are available [ 32 ].…”