Using an optimized RBF neural network to predict the out-of-plane welding distortions based on the 3-2-1 locating scheme

Document Type : Article


Department of Mechanical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.


This study deals with the effect of locator positioning in 3-2-1 locating scheme to control the out-of-plane distortion in gas tungsten arc welding of sheet metals. To apply this locating scheme on the sheet metals, a suitable fixture is designed. The distortion of the welded plates has been predicted using the radial basis function (RBF) neural network. To gather the experimental data employed in the RBF modeling process, a set of welding tests is performed on the sheet specimens by varying the positions of the three locators. The parameters of the network are optimally selected using the simulated annealing (SA) optimization algorithm. The average and maximum error computed for the test dataset were respectively 2.43% and 5.30% while in some cases the error falls below 1%. The results of the RBF network show very good agreement with the experiments and it can be concluded that this modeling technique can be utilized successfully in predicting the welding distortions when the 3-2-1 locating scheme is used.


Main Subjects

1.Ates, H., Dursun, B., and Kurt, E. Estimation of mechanical properties of welded S355J2+ N steel via the arti_cial neural network", Scientia Iranica Transaction B: Mechanical Engineering, 23(2), p. 609 (2016).
2. Zhang, W.W., Cong, S., Huang, Y., and Tian, Y.H. Micro structure and mechanical properties of vacuum brazed martensitic stainless steel/tin bronze by Agbased alloy", Journal of Materials Processing Technology, 248 (Supplement C), pp. 64-71 (2017).
3. Narang, H., Mahapatra, M., Jha, P., and Biswas, P. Optimization and prediction of angular distortion and weldment characteristics of TIG square butt joints", Journal of Materials Engineering and Performance, 23(5), pp. 1750-1758 (2014). 4. Ma, N., Wang, J., and Okumoto, Y. Out-of-plane welding distortion prediction and mitigation in sti_- ened welded structures", The International Journal of Advanced Manufacturing Technology, 84(5-8), pp. 1371-1389 (2016). 5. Pazooki, A., Hermans, M., and Richardson, I. Control of welding distortion during gas metal arc welding of AH36 plates by stress engineering", The International Journal of Advanced Manufacturing Technology, 88(5- 8), pp. 1439-1457 (2017). 6. Michaleris, P., Minimization of Welding Distortion and Buckling: Modelling and Implementation, Michaleris, P., Ed., 1st, Edn., pp. 3-4, Woodhead Publishing, Cambridge CB22 3HJ, UK (2011). 7. Deng, D., Liu, X., He, J., and Liang, W. Investigating the inuence of external restraint on welding distortion in thin-plate bead-on joint by means of numerical simulation and experiment", The International Journal of Advanced Manufacturing Technology, 82(5-8), pp. 1049-1062 (2016). 8. Li, Y., Zhao, Y., Li, Q., et al. E_ects of welding condition on weld shape and distortion in electron beam welded Ti2AlNb alloy joints", Materials & Design, 114, pp. 226-233 (2017). 9. Lightfoot, M., McPherson, N., Woods, K., and Bruce, G.D. Arti_cial neural networks as an aid to steel plate distortion reduction", Journal of Materials Processing Technology, 172(2), pp. 238-242 (2006). 10. Bruce, G. and Lightfoot, M. The use of arti_cial neural networks to model distortion caused by welding", International Journal of Modelling and Simulation, 27(1), pp. 32-37 (2007). 11. Yang, H. and Shao, H. Distortion-oriented welding path optimization based on elastic net method and genetic algorithm", Journal of Materials Processing Technology, 209(9), pp. 4407-4412 (2009). 12. Choobi, M.S., Haghpanahi, M., and Sedighi, M. Prediction of welding-induced angular distortions in thin butt-welded plates using arti_cial neural networks", Computational Materials Science, 62, pp. 152-159 (2012). 13. Barclay, C., Campbell, S., Galloway, A., and McPherson, N. Arti_cial neural network prediction of weld distortion recti_cation using a travelling induction coil", The International Journal of Advanced Manufacturing Technology, 68(1-4), pp. 127-140 (2013). 14. Tian, L., Luo, Y.,Wang, Y., andWu, X. Prediction of transverse and angular distortions of gas tungsten arc bead-on-plate welding using arti_cial neural network", Materials & Design (1980-2015), 54, pp. 458-472 (2014). 878 M.M. Tafarroj and F. Kolahan/Scientia Iranica, Transactions B: Mechanical Engineering 26 (2019) 869{878 15. Narayanareddy, V., Chandrasekhar, N., Vasudevan, M., Muthukumaran, S., and Vasantharaja, P. Numerical simulation and arti_cial neural network modeling for predicting welding-induced distortion in buttwelded 304L stainless steel plates", Metallurgical and Materials Transactions B, 47(1), pp. 702-713 (2016). 16. Ma, N., Huang, H., and Murakawa, H. E_ect of jig constraint position and pitch on welding deformation", Journal of Materials Processing Technology, 221, pp. 154-162 (2015). 17. Choobi, M.S., Haghpanahi, M., and Sedighi, M. Investigation of the e_ect of clamping on residual stresses and distortions in butt-welded plates", Scientia Iranica Transaction B: Mechanical Engineering, 17(5), p. 387 (2010). 18. Ma, N. and Huang, H. E_cient simulation of welding distortion in large structures and its reduction by jig constraints", Journal of Materials Engineering and Performance, 26(11), pp. 5206-5216 (2017). 19. Lorin, S., Cromvik, C., Edelvik, F., Lindkvist, L., and Soderberg, R. Variation simulation of welded assemblies using a thermo-elastic _nite element model", Journal of Computing and Information Science in Engineering, 14(3), p. 031003 (2014). 20. Cai, W., Hu, S.J., and Yuan, J. Deformable sheet metal _xturing: principles, algorithms, and simulations", Journal of Manufacturing Science and Engineering, 118(3), pp. 318-324 (1996). 21. Liu, G., Jia, L., Kong, B., Guan, K., and Zhang, H. Arti_cial neural network application to study quantitative relationship between silicide and fracture toughness of Nb-Si alloys", Materials & Design, 129, pp. 210-218 (2017). 22. Santos, R.B., Ruppb, M., Bonzi, S.J., and Filetia, A.M.F. Comparison between multilayer feed forward neural networks and a radial basis function network to detect and locate leaks in pipelines transporting gas", Chem. Eng. Trans, 32(1375), p. e1380 (2013). 23. Yu, H., Xie, T., Paszczynski, S., and Wilamowski, B.M. Advantages of radial basis function networks for dynamic system design", IEEE Transactions on Industrial Electronics, 58(12), pp. 5438-5450 (2011). 24. Azadi Moghaddam, M., Golmezerji, R., and Kolahan, F. Simultaneous optimization of joint edge geometry and process parameters in gas metal arc welding using integrated ANN-PSO approach", Scientia Iranica Transaction B: Mechanical Engineering, 24(1), pp. 260-273 (2017). 25. Kirkpatrick, S., Gelatt, C.D., and Vecchi, M.P. Optimization by simulated annealing", science, 220(4598), pp. 671-680 (1983).