Abstract
The present work aims at demonstrating the different avenue for indirect monitoring of friction stir welding process which is hardly attempted. Information contained in the current signal of the main spindle motor is extracted in terms of four statistical features. These features along with tool rotational speed, welding speed and shoulder diameter are combined with support vector machine for the prediction of ultimate tensile strength of the joints. The parameters of the support vector machine are optimized using grid search method. The prediction performance of the model is tested for inputs which contain process parameters with and without signal features. The performance of the developed support vector regression models are compared with well accepted multi-layer feed forward neural network trained with back propagation algorithm and radial basis function neural network developed for the prediction of ultimate tensile strength of the welded joints. The analysis leads to the observations that inclusion of signal features to these models improve the prediction accuracy by an appreciable amount. Among the developed models, support vector machine outperform in modeling ultimate tensile strength of the welds compared to neural network models.
Similar content being viewed by others
References
R.S. Mishra, Z.Y. Ma, Mater. Sci. Eng., R 50, 1 (1995)
B.T. Gibson, D.H. Lammlein, T.J. Prater, W.R. Longhurst, C.D. Cox, M.C. Ballun, K.J. Dharmaraj, G.E. Cook, A.M. Strauss, J. Manuf. Processes 16(1), 56 (2014)
B. Das, S. Bag, S. Pal, Manuf. Lett. 7, 6 (2016)
M. Mehta, K. Chatterjee, A. De, Sci. Technol. Weld. Join. 18, 191 (2013)
S. Subramanian, S. Narayan, A.S. Denis, Proc. IMechE Part B J. Eng. Manuf. 227(3), 407 (2013)
M.G. Na, J.W. Kim, D.H. Lim, Y.J. Kang, Nucl. Eng. Des. 238, 1503 (2008)
Y. Wang, Y. Sun, P. Lv, H. Wang, NDT&E Int. 41, 517 (2008)
W.C. Lu, X.B. Ji, M.J. Li, L. Liu, B.H. Yue, L.M. Zhang, Adv. Manuf. 1, 151 (2013)
G. Buffa, L. Fratini, F. Micari, J. Manuf. Processes 14, 289 (2012)
M.H. Shojaeefard, R.A. Behnagh, M. Akbari, M.K.B. Givi, F. Zarhani, Mater. Des. 44, 190 (2013)
L. Fratini, G. Buffa, D. Palmeri, Comput. Struct. 87, 1166 (2012)
C. Cortes, V. Vapnik, Mach. Learn. 20, 273 (1995)
Y. Bao, Z. Hu, T. Xiong, Neurocomputing 117, 98 (2013)
B. Das, S. Pal, S. Bag, J. Manuf. Processes 22, 260 (2016)
S. Pal, S.K. Pal, A.K. Samantaray, Int. J. Comp. Integ. Manuf. 23, 453 (2010)
B. Das, S. Pal, S. Bag, Int. J. Adv. Manuf. Technol. (2016). doi:10.1007/s00170-016-9140-0
X. Wang, W. Wang, Y. Huang, N. Nguyen, K. Krishnakumar, J. Intell. Manuf. 19, 383 (2008)
S. Haykin, Neural Networks: a comprehensive foundation (Pearson Education, Delhi, 2003)
J.S.R. Jang, C.T. Sun, E. Mizutani, Neuro-fuzzy and soft computing (Pearson Education, Delhi, 2004)
M. Taghi, N. Pavesic, Neurocomputing 62, 39 (2004)
Acknowledgements
The authors gratefully acknowledge the financial support provided by SERB (Science and Engineering Research Board), INDIA (Grant No. SERB/F/2767/2012-13) to carry out this research work.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Das, B., Pal, S. & Bag, S. Monitoring of Friction Stir Welding Process using Main Spindle Motor Current. J. Inst. Eng. India Ser. C 99, 711–716 (2018). https://doi.org/10.1007/s40032-017-0371-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40032-017-0371-0