Optimization and Prediction of Ultimate Tensile of TIG Mild Steel Welds Using ANN

Pondi Pius, Achebo .J, Obahiagbon .K


TIG welding, is about the most popular welding method, which finds its applications in  the fabrication industry. The integrity and service life of engineering structures is a very important factor in the welding technology sector, one of the problem facing the fabrication industry is the control of the process input parameters to obtain a good welded joint . Research has shown that one of the practical ways to improving on weld qualities is to optimize the input process parameters. The aim of this study is to predict the ultimate tensile strength of TIG mild steel welds using ANN.In this study, twenty experimental runs were carried out, each experimental run comprising the current, voltage and gas flow rate, the TIG welding process was used to join two pieces of mild steel plates measuring 60 x40 x10 mm , the tensile strength was measured respectively. Thereafter the data collected from the experimental results was analysed with the ANN. The experimental results for the ultimate tensile strength was analyzed with the Artificial Neural Networks. The best validation performance is 0.48429 and occurred at epoch five (5). The R-value (coefficient of correlation ) for training shows of 99.9%closeness ,99.4% for validation and 89.8% for  testing respectively. The overall R-value is shown to be 98.7%. For ultimate tensile strength, both the artificial neural network and the Response surface methodology models fit well. However the RSM model Provided a better overall fit to the experimental data than the ANN.


Full Text: PDF
Download the IISTE publication guideline!

To list your conference here. Please contact the administrator of this platform.

Paper submission email: IEL@iiste.org

ISSN (Paper)2224-6096 ISSN (Online)2225-0581

Please add our address "contact@iiste.org" into your email contact list.

This journal follows ISO 9001 management standard and licensed under a Creative Commons Attribution 3.0 License.

Copyright © www.iiste.org