Comparison of RSM and ANN model in the prediction of the tensile shear failure load of spot welded AISI 304/316 L dissimilar sheets
by Murugesan Vigneshkumar; Perumal Ashoka Varthanan
International Journal of Computational Materials Science and Surface Engineering (IJCMSSE), Vol. 8, No. 2, 2019

Abstract: Resistance spot welding process is broadly used for joining sheet metals in automobile, aerospace, chemical and biomedical industries. In this research work, mechanical property, macro and microstructure of resistance spot welded dissimilar steel sheets of grades AISI 304 and high corrosion resistance AISI 316 L are studied. Experiments are conducted by changing the process parameters such as welding current, electrode pressure, welding time and squeeze time using central composite design of response surface methodology. The empirical model predicted by the response surface methodology (RSM) is compared with back propagation algorithm model of artificial neural network (ANN). By numerical optimisation tool of design expert software, the optimal process parameters setting for attaining the maximum tensile shear failure load is identified. The results of the properly trained ANN model (R² value of 99.04%) proved that it is more accurate than RSM model (R² value of 96.33%).

Online publication date: Mon, 16-Sep-2019

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Materials Science and Surface Engineering (IJCMSSE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com