M Mokhtari - School of Metallurgy and Materials Engineering, College of Engineering, University of Tehran, Tehran, Iran
S. F. Kashani-Bozorg - School of Metallurgy and Materials Engineering, College of Engineering, University of Tehran, Tehran, Iran
M Sharififar - School of Metallurgy and Materials Engineering, College of Engineering, University of Tehran, Tehran, Iran

Genetic algorithm in prediction of the defect volume fraction in Friction Stir Processing (FSP) of AZ31 magnesium alloy has been studied in the present work. Genetic algorithm is a method of prediction that reduces testing time and cost. This study employed experimental data from FSP that is a branch of Friction Stir Welding (FSW). The input parameters are defined by the rotational speed (three parameters), traverse speed (three parameters) and number of passes (four parameters). The quality of prediction has been evaluated by comparison of the real results obtained during testing and predicted ones. On comparing the experimental data, it was found out that the genetic algorithm model is capable of predicting defect volume fraction in friction stir processing technique.

Friction stir processing, Genetic algorithm, defect volume fraction