JMS_V3_N1_RP2 Davood Afshari H. Talebi Journal on Material Science 2347–615X 3 1 8 13 Artificial Neural Network, Finite Element Model, Mg Alloy, Nugget Size, Resistance Spot Weld In this study, a finite element model and an artificial neural network model have been used to predict nugget size for resistance spot weld of AZ31 Mg alloy. The quality and strength of spot welds determine the integrity of the structure, which depends thoroughly on the nugget size. Different spot welding parameters such as the welding current, the welding time and electrode force were selected to be used for the FE (Finite Element) model. Although, the use of a finite-element analysis decreases the main costs associated with the nugget-size measurement tests; due to high complexity of a spot weld, its FE models are very time-consuming and requiring high-speed computers. So in this study, a FE model along with an Artificial Neural Network (ANN) has been adopted to predict the nugget size. The results obtained with the FE analysis were used to build up a back-propagation ANN model for the nugget-size prediction. The results revealed that a combination of these two developed models can accurately and rapidly predict the nugget size for a resistance spot weld of AZ31 Mg alloy. April - June 2015 Copyright © 2015 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=3366