Title: Comparison of RSM and ANN model in the prediction of the tensile shear failure load of spot welded AISI 304/316 L dissimilar sheets

Authors: Murugesan Vigneshkumar; Perumal Ashoka Varthanan

Addresses: Department of Mechanical Engineering, Sri Krishna College of Engineering and Technology, Coimbatore, India ' Department of Mechanical Engineering, Sri Krishna College of Engineering and Technology, Coimbatore, India

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%).

Keywords: resistance spot welding; RSW; response surface methodology; RSM; artificial neural network; ANN; tensile shear failure load; TSFL; dissimilar metals; optimisation techniques; austenitic stainless steel; failure mode; microstructures; macrostructures.

DOI: 10.1504/IJCMSSE.2019.102292

International Journal of Computational Materials Science and Surface Engineering, 2019 Vol.8 No.2, pp.114 - 130

Received: 16 Jan 2018
Accepted: 06 Dec 2018
Published online: 16 Sep 2019 *

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