Prediction of Tensile Strength in Friction Stir Welded Aluminium Alloy Using Artificial Neural Network

Abstract

Abstract This paper presents a systematic approach to optimizing friction stir welding process parameters for the aluminium alloy. Friction stir welding (FSW) is solid state joining process widely used for the difficult welding joints of aluminum alloys. Weld quality is predominantly affected by welding input parameters. The welding parameters such as tool shoulder diameter, tool rotational speed, welding speed and axial force play a major role in deciding the joint strength. In present work an attempt has been made to join the aluminium alloy AA8014 by FSW using the conventional milling machine. Friction stir welding have been carried out on the 4 mm thick AA8014 plate. ANN has been developed based on back propagation (BP) of error for prediction of the tensile strength in FSW. The input parameters of the model consist of tool shoulder diameter, tool rotational speed, welding speed and axial force whereas the output of the model is the tensile strength of joint. The ANN was subsequently trained with experimental data. Testing of the ANN is carried out using experimental data not used during training. The results showed that the outcomes of the ANN are in good agreement with the experimental data; this indicates that the developed neural network can be used as an alternative way for calculating tensile strength for given process parameters.