A novel integrated approach of augmented grey wolf optimizer and ANN for estimating axial load carrying-capacity of concrete-filled steel tube columns

Abstract

The purpose of this study is to offer a high-performance machine learning model for determining the ultimate load-carrying capability of concrete-filled steel tube (CFST) columns. The proposed approach is a novel hybrid machine learning model that combines artificial neural network (ANN) and augmented grey wolf optimizer (AGWO). AGWO is a simple and effective augmentation to the conventional grey wolf optimizer (GWO). In addition to AGWO, an enhanced version of grey wolf optimizer (EGWO) was employed in this study, and two hybrid models, namely ANN-AGWO and ANN-EGWO were created for estimating the load-carrying capacity of CFST columns. The suggested hybrid models were evaluated on two distinct datasets with a variety of input combinations. The proposed ANN-AGWO achieved the most precise prediction during the testing phase, outperforming support vector regression, extreme learning machine, group data handling method, and other hybrid ANNs constructed using particle swarm optimization, grey wolf optimizer, salp swarm algorithm, slime mould algorithm, and Harris hawks optimization algorithms. Based on the experimental findings, the suggested ANN-AGWO can be utilized as a high-performance tool to estimate the load-carrying capacity of CFST columns during the design and preparatory stages of civil engineering projects.