Evolutionary computing-based models for predicting seismic shear strength of RC columns

Abstract

A number of regression-based models have been proposed to quantify the seismic shear strength of reinforced concrete (RC) columns. However, most of these models suffer from a high degree of uncertainty as a result of the limited datasets used in their development and/or the classic approaches used to capture the non-linear interrelationships between the shear strength and influencing factors. To address these issues, in this work, the power of multi-gene genetic programming (MGGP), guided by mechanics, was harnessed to identify the primary influencing factors and subsequently develop efficient shear capacity prediction models for rectangular and circular RC columns. Comprehensive published datasets for the shear strength of cyclically loaded RC columns were compiled and employed to develop the MGGP-based models. The efficiency of the developed models was assessed and their performance was also compared with that of other relevant prediction models. The results showed that the developed mechanics-guided MGGP approach produced more accurate and consistent prediction models to describe the complex shear behaviour of RC columns under cyclic loading than the models available in the relevant design standards and literature.