Predictive Modeling of Recycled Aggregate Concrete Beam Shear Strength Using Explainable Ensemble Learning Methods

Abstract

Construction and demolition waste (CDW) together with the pollution caused by the production of new concrete are increasingly becoming a burden on the environment. An appealing strategy from both an ecological and a financial point of view is to use construction and demolition waste in the production of recycled aggregate concrete (RAC). However, past studies have shown that the currently available code provisions can be unconservative in their predictions of the shear strength of RAC beams. The current study develops accurate predictive models for the shear strength of RAC beams based on a dataset of experimental results collected from the literature. The experimental database used in this study consists of full-scale four-point flexural tests. The recycled coarse aggregate (RCA) percentage, compressive strength (fc′), effective depth (d), width of the cross-section (b), ratio of shear span to effective depth (a/d), and ratio of longitudinal reinforcement (ρw) are the input features used in the model training. It is demonstrated that the proposed machine learning models outperform the existing code equations in the prediction of shear strength. State-of-the-art metrics of accuracy, such as the coefficient of determination (R2), mean absolute error, and root mean squared error, have been utilized to quantify the performances of the ensemble machine learning models. The most accurate predictions could be obtained from the XGBoost model, with an R2 score of 0.94 on the test set. Moreover, the impact of different input features on the machine learning model predictions is explained using the SHAP algorithm. Using individual conditional expectation plots, the variation of the model predictions with respect to different input features has been visualized.

Calculation Method for the Cracking Resistance and Bearing Performance of SFRAC Beams

“…(5) Considering the influence of the recycled aggregate replacement rate and fiber volume ratio, the calculation formula of the cracking moment of SFRAC beams is established, and the prediction accuracy is better than ACI318 and Eurocode 2. (6) The calculated values of the ultimate bending moment bearing capacity based on ACI 318 and ACI 544 agree with the experimental values, which can reasonably predict the bending bearing capacity of SFRAC beams. (7) Steel fiber recycled concrete is a material with good performance, and the performance of SFRAC beams with 100% recycled aggregate replacement rate is still higher than that of ordinary concrete benchmark beams, so SFRAC can be used for general loadbearing beam structural members.…”

“…Due to the presence of microcracks and holes, recycled aggregate concrete (RAC) exhibits weaker performance compared to ordinary concrete [ 6 ]. Recycled concrete beams have lower bearing capacity [ 7 ], larger crack width [ 8 ], smaller crack spacing [ 9 ], lower stiffness [ 8 , 10 ], greater deflection under both short-term load [ 11 ] and long-term load [ 12 , 13 , 14 , 15 , 16 ], and shorter fatigue life [ 17 ] when compared to ordinary concrete beams.…”

Prediction of Cooling Load of Tropical Buildings with Machine Learning

“…Machine learning methods have gained importance in today's world [44]. Machine learning algorithms are used in many fields today [45][46][47][48][49][50][51][52]. Supervised learning, which is a type of machine learning, refers to the implementation of classification and regression algorithms where a dependent variable is known in advance.…”