Abstract
The bi-directional prediction between processing parameters and weld penetration benefits electron beam welding (EBW) production by reducing costly trials. An artificial neural network (ANN) model was established for the bi-directional prediction between them in EBW. The main processing parameters consist of accelerating voltage, beam current and welding speed, while weld penetration indicates penetration depth and penetration width of weld. The training and test sets were collected through EBW experiments by using 1Cr18Ni9Ti stainless steel. Two-layer supervised neural networks were used with different number of hidden layer nodes. Comparison between experimental and predicted results show the maximum absolute-value error is 6.6% in forward prediction from the main processing parameters to weld penetration, while that is 23.6% in backward prediction reversely. Combined the higher accurate forward prediction with the easy-use backward prediction in EBW production, a flow chart is proposed for optimizing prediction of processing parameters.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Tian, Y.H., Wang, C.Q., Zhu, D.Y., Zhou, Y.: Finite Element Modeling of Electron Beam Welding of a Large Complex Al Alloy Structure by Parallel Computations. Journal of Materials Processing Technology 199, 41–48 (2008)
Wu, H.Q., Feng, J.C., He, J.S., Zhang, B.G.: Numerical Simulation of Deep Penetration in Electron Beam Welding of Ti3Al Intermetallic Compound. Transactions of the China Welding Institution 26, 1–4 (2005) (in Chinese)
Elena, K.: Statistical Modelling and Computer Programs for Optimization of the Electron Beam Welding of Stainless Steel. Vacuum 62, 151–157 (2001)
Koleva, E., Vuchkov, I.: Model-based Approach for Quality Improvement of Electron Beam Welding Applications in Mass Production. Vacuum 77, 423–428 (2005)
Kanti, M.K., Rao, S.P.: Prediction of Bead Geometry in Pulsed GMA Welding Using Back Propagation Neural Network. Journal of Materials Processing Technology 200, 300–305 (2008)
Bai, S.W., Tong, L.G., Liu, F.M., Wang, L.: Artificial Neural Network to Predict Toughness Parameter CVN of Welded Joint of High Strength Pipeline Steel. Transactions of the China Welding Institution 29, 106–108 (2008) (in Chinese)
Shi, Y., Li, J.J., Fan, D., Chen, J.H.: Predication of Properties of Welding Joints Based on Uniform Designed Neural Network. In: King, I., Wang, J., Chan, L.-W., Wang, D. (eds.) ICONIP 2006. LNCS, vol. 4234, pp. 572–580. Springer, Heidelberg (2006)
Hasan, O., Adem, K., Erol, A.: Artificial Neural Network Application to the Friction Stir Welding of Aluminum Plates. Materials and Design 28, 78–84 (2007)
Hakan, A.: Prediction of Gas Metal Arc Welding Parameters Based on Artificial Neural Networks. Materials and Design 28, 2015–2023 (2007)
Yilbas, B.S., Sami, M., Nickel, J., Coban, A., Said, S.A.M.: Introduction into the Electron Beam Welding of Austenitic 321-type Stainless Steel. Journal of Materials Processing Technology 82, 13–20 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shen, X., Huang, W., Xu, C., Wang, X. (2009). Bi-directional Prediction between Weld Penetration and Processing Parameters in Electron Beam Welding Using Artificial Neural Networks. In: Yu, W., He, H., Zhang, N. (eds) Advances in Neural Networks – ISNN 2009. ISNN 2009. Lecture Notes in Computer Science, vol 5553. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01513-7_121
Download citation
DOI: https://doi.org/10.1007/978-3-642-01513-7_121
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01512-0
Online ISBN: 978-3-642-01513-7
eBook Packages: Computer ScienceComputer Science (R0)