Shear strength estimation of reinforced concrete walls using support vector regression improved by Teaching–learning-based optimization, Particle Swarm optimization, and Harris Hawks Optimization algorithms

Abstract

Peak shear strength estimation of RC shear walls is one of the influential parameters on the design of RC shear walls. Considering all models and equations provided by researchers and building design codes, it is still not possible to estimate the peak shear strength of shear walls with high level of accuracy. Therefore, the authors proposed three innovative models to estimate the peak shear strength based on combination of the Support Vector Regression with meta-heuristic optimization algorithms such as Teaching–learning-based optimization (TLBO), Particle swarm optimization (PSO), and Harris Hawks Optimization (HHO). The authors collected a large database containing 228 experimental data of RC shear walls and eight input parameters. One of the best features of this research is providing models for prediction of shear strength for three categories including, squat, cylinder, and thin RC shear walls.Finally, all three models have been compared with each other and with the equations proposed by the design codes and the researchers. The results indicate that the proposed models have good accuracy. As a result, researchers can use these models to estimate the shear strength of RC shear walls, which could increase the accuracy in predicting the behavior of the structure and would reduce the construction costs.