Friction stir welding (FSW) is an innovative solid state joining technique and has been employed in aerospace, rail, automotive and marine industries for joining aluminium, magnesium, zinc and copper alloys. The FSW process parameters such as tool rotational speed, welding speed, axial force etc., play a major role in deciding the weld quality. This paper focuses two innovative methods such as response surface methodology and artificial neural network are used to predict the tensile strength of friction stir welded RDE-40 aluminium alloy. The experiments were conducted based on three factors, three-level, and central composite face centered design with full replications technique and mathematical model is developed. The results obtained through response surface methodology were compared with artificial neural networks. It was found that the error rate predicted by the artificial network was smaller than predicted by the response surface methodology.

Key words: Friction stir welding, aluminium alloy, tensile strength, response surface methodology, artificial neural network