Empirical modeling of torsional strength in reinforced concrete beams using iterated local search with semantic cluster operator

This study conducted a data-based analysis on the impact of a feature and empirical modeling to increase the accuracy of analytical models related to torsional strength. The torsional strength data of 324 plain and reinforced concrete beams were collected from previous studies, which included data from specimens with various cross-sectional sizes, material strengths, reinforcement ratios, and cover thicknesses. The data was clustered to analyze the effect of each feature, and the importance of each feature was derived using the Shapley additive explanations technique. An iterated local search using a semantic cluster operator was used to derive simple and highly accurate empirical models to predict the torsional strength. The proposed models predicted the ultimate strength by multiplying the contribution of concrete and transverse reinforcement, contrary to the current codes, and showed better accuracy than the existing models.