Predicting fire resistance of SRC columns through gene expression programming

Abstract

Purpose This paper aims to predict the fire resistance of steel-reinforced concrete columns by application of the genetic algorithm. Design/methodology/approach In total, 11 effective parameters are considered including mechanical and geometrical properties of columns and loading values as input parameters and the duration of concrete resistance at elevated temperatures as the output parameter. Then, experimental data of several studies – with extensive ranges – are collected and divided into two categories. Findings Using the first set of the data along with the gene expression programming (GEP), the fire resistance predictive model of steel-reinforced concrete (SRC) composite columns is presented. By application of the second category, evaluation and validation of the proposed model are investigated as well, and the correspondent time-temperature diagrams are derived. Originality/value The relative error of 10% and the R coefficient of 0.9 for the predicted model are among the highlighted results of this validation. Based on the statistical errors, a fair agreement exists between the experimental data and predicted values, indicating the appropriate performance of the proposed GEP model for fire resistance prediction of SRC columns.

Creep modeling of composite materials based on improved gene expression programming

“…Wei and Xue 23 proposed a new equation that could predict the permeability of tight carbonate rocks using gene expression programming. Hassani et al 24 presented fire resistance predictive model of steel-reinforced concrete composite columns by gene expression programming. Shahmansouri et al 25 studied gene expression programming to establish numerical models for compressive strength of GPC based on ground granulated blast-furnace slag, and validated the performance and predictability of proposed model by conducted sensitivity and parametric analysis.…”