Practical machine learning-based prediction model for axial capacity of square CFST columns

In this paper, a surrogate Machine-Learning (ML) model based on Gaussian Process Regression (GPR) was developed to predict the axial load of square concrete-filled steel tubular (CFST) columns under compression. For this purpose, an experimental database was extracted from the available literature and used for the development and training of the GPR model. The GPR model's performance is superior to that of existing models in relation to the axial load of square CFST columns. For practical application, a Graphical User Interface (GUI) was developed for researchers, engineers to support the teaching and interpretation of the axial behavior of CFST columns.

Automated summary

This paper develops a surrogate Machine-Learning model based on Gaussian Process Regression to predict the axial load of square CFST columns under compression. Through the extraction and utilization of experimental data, the performance of the GPR model surpasses that of existing models in predicting the axial load of square CFST columns. A Graphical User Interface is also developed for practical application, which assists researchers and engineers in teaching and interpreting the axial behavior of CFST columns.