Title: Application of RSM and ANN to predict the tensile strength of Friction Stir Welded A319 cast aluminium alloy

Authors: M. Jayaraman, R. Sivasubramanian, V. Balasubramanian, A.K. Lakshminarayanan

Addresses: Department of Mechatronics Engineering, Kongu Engineering College, Perundurai, Erode 638 052, Tamil Nadu, India. ' Department of Mechanical Engineering, Coimbatore Institute of Technology, Coimbatore 641 014, Tamil Nadu, India. ' Centre for Materials Joining Research (CEMAJOR), Department of Manufacturing Engineering, Annamalai University, Annamalai Nagar 608 002, Tamil Nadu, India. ' Centre for Materials Joining Research (CEMAJOR), Department of Manufacturing Engineering, Annamalai University, Annamalai Nagar 608 002, Tamil Nadu, India

Abstract: Fusion welding of A319 aluminium cast alloys will lead to many problems such as porosity, micro-fissuring and hot cracking. However, Friction Stir Welding (FSW) can be used to weld these cast alloys without the above-mentioned defects. The FSW process parameters such as tool rotational speed, welding speed and axial force play a major role in deciding the weld quality. The experiments were conducted based on three factors, three-level and Central-Composite-Face-centred (CCF) design with full replications technique. Models were developed to predict tensile strength of FSW A319 alloy using Response Surface Methodology (RSM) and Artificial Neural Network (ANN). The results obtained through RSM were compared with ANN. It is found that the error rate predicted by the artificial network is smaller than predicted by the RSM. [Received 2 February 2008; Revised 15 July 2008; Accepted 10 August 2008]

Keywords: FSW; friction stir welding; A319 aluminium alloys; tensile strength; RSM; response surface methodology; ANNs; artificial neural networks; tool rotational speed; welding speed;axial force.

DOI: 10.1504/IJMR.2009.026576

International Journal of Manufacturing Research, 2009 Vol.4 No.3, pp.306 - 323

Available online: 19 Jun 2009 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article