Application of optimization-based regression analysis for evaluation of frost durability of recycled aggregate concrete

Concrete constructed using recycled aggregates in place of natural aggregates is an efficient approach to increase the construction sector's sustainability. To improve recycled aggregate concrete (RAC$$ \mathrm{RAC} $$) technologies in permafrost, it is essential to certify the stability in frost-induced conditions. The main goal of this study was to use support vector regression (SVR$$ \mathrm{SVR} $$) methods to forecast the frost durability (DF$$ \mathrm{DF} $$) of RAC$$ \mathrm{RAC} $$ on the basis of durability agent value in cold climates. Herein, three optimization methods called Ant lion optimization (ALO$$ \mathrm{ALO} $$), Grey wolf optimization (GWO$$ \mathrm{GWO} $$), and Henry Gas Solubility Optimization (HGSO$$ \mathrm{HGSO} $$) were employed for indicating optimal values of SVR$$ \mathrm{SVR} $$ key parameters. The results depicted that all developed models have capability in predicting the DF$$ \mathrm{DF} $$ of RAC$$ \mathrm{RAC} $$ in cold regions. The values of OBJ$$ \mathrm{OBJ} $$ as a comprehensive index depicted that the GWO-SVR$$ \mathrm{GWO}-\mathrm{SVR} $$ model has the higher value at 0.0571 as the weakest model, then ALO-SVR$$ \mathrm{ALO}-\mathrm{SVR} $$ at 0.0312 recognized as the second-highest model, and finally the HGSO-SVR$$ \mathrm{HGSO}-\mathrm{SVR} $$ system at 0.0224 mentioned as outperformed model. ALO-SVR$$ \mathrm{ALO}-\mathrm{SVR} $$ and GWO-SVR$$ \mathrm{GWO}-\mathrm{SVR} $$ approaches were likewise capable of accurately forecasting the DF$$ \mathrm{DF} $$ of RAC$$ \mathrm{RAC} $$ in cold regions, but the created HGSO-SVR$$ \mathrm{HGSO}-\mathrm{SVR} $$ method outperformed them all when taking into account the explanations and justifications.