Development of Closed-Form Equations for Estimating Mechanical Properties of Weld Metals according to Chemical Composition

Abstract

In this study, data analysis was performed using an artificial neural network (ANN) approach to investigate the effect of the chemical composition of welds on their mechanical properties (yield strength, tensile strength, and impact toughness). Based on the data collected from previously performed experiments, correlations between related variables and results were analyzed and predictive models were developed. Sufficient datasets were prepared using data augmentation techniques to solve problems caused by insufficient data and to make better predictions. Finally, closed-form equations were developed based on the predictive models to evaluate the mechanical properties according to the chemical composition.

Modelling, Test and Practice of Steel Structures

“…Three papers focused on the material properties of structural steel, which presented investigations on the chemical composition of weld metals [1]; the fracture performances of SBHS500, SM570, and SM490 steel [2]; and the cyclic performance of structural steels after exposure to various heating-cooling treatments [3].…”