ARTIFICIAL NEURAL NETWORK MODELLING OF THE MECHANICAL CHARACTERISTICS OF FRICTION STIR WELDED AA7020-T6 ALUMINUM ALLOY

Document Type : Research articles

Authors

Mechanical Engineering Department, Shoubra Faculty of Engineering, Benha University, Cairo, Egypt.

Abstract

In the current work, lap joints of the AA7020-T6 aluminum sheets of 3 mm thickness were welded using friction stir welding (FSW). Tensile-shear tests were conducted to evaluate the mechanical characteristics of the AA7020-T6 lap joints. A statistical analysis of variance (ANOVA) was performed to find which FSW process parameters (i.e. the tool rotational and welding speeds) are statistically significant. With the signal to noise (S/N) ratio and ANOVA analyses, the optimal levels of the FSW process parameters could be determined. Also, an artificial neural network (ANN) model was developed to predict the tensile-shear load of the AA7020-T6 Al alloy lap joints. It has been found that the reduction of the tool rotational speed and/or increasing the welding speeds increase(s) the tensile-shear load of the AA7020-T6 aluminum friction stir welded lap joints. The welding speed showed the highest statistical significance on the tensile-shear load of the AA7020-T6 aluminum lap friction stir (FS) welded joints when compared with the tool rotational speed. The developed ANN model showed a good agreement between the predicted and experimental results.

Keywords

Files

Share

How to cite

Statistics