The chloride ion permeability resistance of recycled aggregate concrete (RAC) is influenced by multiple factors, and the prediction model for this resistance based on machine learning is still limited. In the paper, six impact factors (IFs), including the carbonation of recycled coarse aggregates (YN), the replacement ratio of recycled coarse aggregates (r), the bending load level (L), the carbonation time (t) and temperature (T) of RAC, and the replacement ratio of carbonated recycled fine aggregates (f), were considered to conduct a chloride penetration test on RAC. Based on the experimental data, four algorithms, including artificial neural network (ANN), support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGBoost), were adopted to establish the machine learning prediction models and study the relationships between the electric flux of RAC and the IFs. The results showed that the predicted values of all four models were in good agreement with the experimental values, and the XGBoost model had the best prediction performance on the testing set. Based on the XGBoost model, the LIME method was adopted to solve the interpretability problem in the prediction process. The importance ranking of IFs on the electric flux was r > t > f > T > L > YN. A graphical user interface (GUI) was developed based on Python 3.8 software to facilitate the use of machine learning models for the chloride ion permeability resistance of RAC. The research results can provide an accurate prediction of the electric flux of RAC.

The influence of the carbonation of recycled coarse aggregates on the durability performance of the recycled aggregate concrete beams is still unclear. In this study, the corrosion characteristics and flexural performance of the carbonated recycled aggregate concrete (C-RAC) beams in corrosive environments were investigated. The results illustrated that the mass loss of the longitudinal tensile steel bars (LTSBs) in the corroded C-RAC beams decreased when the replacement ratio of the carbonated recycled coarse aggregate (CRCA) increased. Compared to the corroded non-carbonated recycled aggregate concrete (NC-RAC) beam, the mass loss of LTSBs in the corroded C-RAC beam was reduced by 37.91% when the CRCA replacement ratio was 100%. The average mass loss of the short limbs of the stirrups on the tensile side of the corroded C-RAC beam was lower than that of the corroded NC-RAC beam. As the CRCA replacement ratio increased, the flexural performance of the corroded C-RAC beams was enhanced. When the CRCA replacement ratio was 100%, the ultimate load and the displacement ductility coefficient of the corroded C-RAC beam increased by 14.04% and 25.82% compared to the corroded NC-RAC beam, respectively. During the service life, the concrete strains of the cross-section at the mid-span of the corroded C-RAC beams satisfied the assumption of plane section. The research results of this study can provide some reference for the durability design and engineering application of C-RAC beams.

The durability of carbonated recycled aggregate concrete (C-RAC) beams is still unclear at present. In this paper, the characteristics of corrosion-induced cracks and the steel corrosion depth of C-RAC beams were investigated through the accelerated corrosion test. The results showed that when accelerating corrosion to the 40th day, compared to the non-carbonated recycled aggregate concrete (NC-RAC) beam, the corrosion-induced cracking area of the C-RAC beam with a 100% carbonated recycled coarse aggregate (C-RCA) replacement ratio decreased by 40.00%, while the total length of the corrosion-induced cracks (CCs) increased by 51.82%. The type of probability distribution for the width of the CCs on the tension side of the C-RAC beams was a lognormal distribution. Compared with the NC-RAC beam, the mean value of the width of the CCs of the C-RAC beam with a 100% C-RCA replacement ratio decreased by 66.67%, the crack width distribution was more concentrated, and the quartiles and median were all reduced. With an increase in the C-RCA replacement ratio, the fractal dimension and the scale coefficient of CCs on the tension side of the beams showed an approximate trend of first increasing and then decreasing. The distribution of the corrosion depth of longitudinal tensile steel bars in the C-RAC beams was a mainly normal distribution. When the C-RCA replacement ratio increased from 30% to 100%, the mean value of the corrosion depth of the longitudinal tensile steel bars decreased by 33.46%, and the trend of changes in the quartiles and medians was basically the same as the trend of changes in the mean value. The research results can provide some reference for promoting the engineering application of C-RAC beams.