Published Paper Details:

Abstract: It is crucial to study the axial compression behaviour of concrete-?lled steel tubular (CFST) columns to ensure the safe operation of engineering structures. The restriction between steel tubular and core concrete in CFST is complex and the relationship between geometric and material properties and axial compression behaviour is highly nonlinear. These challenges have prompted the use of soft computing methods to predict the ultimate bearing capacity (Nu) under axial compression. This study presents a new approach to simulate the capacity of circular CFST columns under axial loading condition, using a large database of experimental results by applying artificial neural network (ANN). A well trained ANN is established and is used to simulate the axial capacity of CFST columns. The validation and testing of the ANN is carried out. The current study can be used to propose a simplified equation that can predict the ultimate strength of the axially loaded columns with high level of accuracy. The result indicate ANN predict strength of CFST within short time and cost too.