Article citationsMore>>

K. Brahma Raju, N. Harsha and V. K. Viswanadha Raju, “Prediction of Tensile Strength of Friction Steer Welded Joints Using Artificial Neural Networks,” International Journal of Engineering Research & Technology, Vol. 1, No. 1, 2012, pp. 1-5.

has been cited by the following article:

• TITLE: Predictive Models for the Ultimate Tensile and Yield Stresses Occurring in Joints of Untreated Friction Stir Welded 2017AA (ENAW-AlCu4MgSi) Plates

  AUTHORS: Mohamed-Ali Rezgui, Ali-Chedli Trabelsi, Hassen Bouzaiene, Mahfoudh Ayadi

  KEYWORDS: Friction Stir Welding; Response Surface Methodology; ANOVA; Sensitivity Analysis; Yield Stress; 2017AA

  JOURNAL NAME: Open Journal of Metal, Vol.3 No.2, June 8, 2013

  ABSTRACT: Friction Stir Welding (FSW) processes have been applied in numerous industrial fields and broadly embraced by the research community. In this paper, given three FSW process parameters, namely, the tool rotation speed N (rpm), the tool traverse feed F(mm/min) and the tool pin/shoulder diameters ratio (r%), we purpose to ascertain their impact on joints Ultimate Tensile Stress (UTS) and joints Yield Stress (YS). The FSW has been executed using 6 mm thick rolled plate in 2017AA. For the design of experiments strategy, we conducted a face centered central composite strategy through which 18 trials have been executed. Then, we utilized the RSM technique to formulate the predictive models which are relevant to the (UTS) and (YS) outputs. Accordingly, the study has pointed out the prevalence of the tool rotation speed and the tool diameters ratio factors; however, the tool traverse feed (F) was found trivial and statistically insignificant. Likewise, the sensitivity analysis regarding factors N, F and r% on both (UTS) and (YS) has exhibited the dominance of the tool diameters ratio (r%), indistinctively.