Prediction of Weld Strength in Power Ultrasonic Spot Welding Process using Artificial Neural Network (ANN) and Backpropagation Method
DOI:
https://doi.org/10.37255/jme.v17i4pp119-126Keywords:
ultrasonic seam welding process, artificial neural network, back propagation method, process parameters, prediction strengthAbstract
In this presented work, an Artificial Neural Network (ANN) connected with the backpropagation method was employed to predict the strength of joining materials that were carried out by using an ultrasonic spot welding process. The models created in this study were investigated, and their process parameters were analyzed. These parameters were classified and set as input variables like applying pressure, time of duration weld and trigger of vibrating amplitude. In contrast, the weld strength of joining dissimilar materials (Al-Cu) is set as output parameters. The identification from the process parameters is obtained using several experiments and finite element analyses based on prediction. The results of actual and numerical are accurate and reliable; however, their complexity has a significant effect due to being sensitivity to the condition variation of welding processes. Therefore, an efficient technique like an artificial neural network coupled with the backpropagation method is required to use the experiments as input data in the simulation of the ultrasonic welding process, finding the adequacy of the modeling process in the prediction of weld strength and to confirm the performance of using mathematical methods. The results of the selecting non-linear models show a noticeable potency when using ANN with a backpropagation method in providing high accuracy compared with other results obtained by conventional models.
Downloads
References
M. Lucas, A. Cardoni, E. McCulloach, G. Hunter, and A. MacBeath, “Applications of power ultrasonics in engineering,” Applied Mechanics and Materials, vol. 13-14,pp. 11-20, 2008
Ziad Shakeeb Al Sarraf, Majid Midhat Saeed, “Design and analysis of slotted block horn used for ultrasonic power applications” Journal of southwest jiaotong university 54:1–10. https:// doi.org/10.35741/issn.0258-2724.54.5.28.
An, S. Elangovan and C. Rathinasuriyan. “Modeling and prediction of weld strength in ultrasonic metal welding process using artificial neural network and multiple regression method.” 2018
P.G. Mongan, E.P. Hinchy, N.P. O’Dowd, C.T. McCarthy, “Optimization of Ultrasonically Welded Joints through Machine Learning”, Procedia CIRP, Vol. 93, p.p 527-531, ISSN 2212-8271, https://doi.org/10.1016/j.procir.2020
Göricka, D., L. E. Larsena, M. Engelschalla and A. Schustera. “Quality Prediction of Continuous Ultrasonic Welded Seams of High- Performance Thermoplastic Composites by means of Artificial Intelligence.” 2021
Watanabe T, Sakuyama H, Yanagisawa A Ultrasonic welding between mild steel sheet and Al–Mg alloy sheet. J Mater Process Technol 34:1107–1111, 2009
Shin Ichi Matsuokaa, Hisashi Imai, “Direct welding of different metals used ultrasonic vibration” Journal of materials processing technology. Vol. 209, No. 2, P.P 954–960, 2009
Yang WH, Tarng YS, “Design optimization of cutting parameters for turning operations based on the Taguchi method” Journal of Materials Processing Technology. Vol. 84, No. 3, pp. 122–129, 1998
Saeed, M.M., Al Sarraf, Z.S, “Using artificial neural networks to predict the effect of input parameters on weld bead geometry for SAW process”, Journal Européen des Systèmes Automatisés, Vol. 54, No. 2, pp. 309-315, 2021 https://doi.org/ 10. 18 280 / jesa.540213
Dewang Zhao, Daxin Ren, Kunmin Zhao, Sun Pan, Xinglin Guo, “Effect of welding parameters on tensile strength of ultrasonic spot welded joints of aluminum to steel – By experimentation and artificial neural network”,Journal of Manufacturing Processes, Vol. 30, pp. 63-74, ISSN 1526-6125, https://doi.org/10.1016 / j .jmapro.2017
Meran C, “Prediction of the optimized welding parameters for the joined brass plates using genetic algorithm”, J Mater, pp. 356–363, 2006
Canyurt OE, Kim HR, Lee KY, “Estimation of laser hybrid welded joint strength by using genetic algorithm approach”, Mech Mater Vol. 40, pp. 825–831, 2008
Khdoudi, Abdelmoula, Tawfik Masrour, “ Prediction of Industrial Process Parameters using Artificial Intelligence Algorithms”, Advanced Intelligent Systems for Sustainable Development (AI2SD’2019), 728–749. https://doi.org/10.1007/978-3-030-36671-1_67, 2020.
ASTM International Codes, 2009, Standard Test Methods for Tension Testing of Metallic Materials, 1-24.
British Standard Codes, 2009, Test Pieces and Test Methods for Metallic Materials for Aircraft, Metric units 1-7.
Refinery NP, Braimah MN. Utilization of response surface methodology (RSM) in the optimization of crude oil refinery. Journal of Multidisciplinary Engineering Science and Technology (JMEST). 2016;3:4361-4369
Montgomery DC. Design and Analysis of Experiments: Response Surface Method and Designs. New Jersey: John Wiley and Sons, Inc; 2005
C.S. Wu, J.Q. Gao and Y.H. Zhao; A neural network for weld penetration control in gas tungsten arc welding; Source: Acta Metallurgica Sinica (English Letters), Volume 19, Issue 1, February 2006, Pages 27-33
Kim, I.S., Lee, S.H., Yarlagadda, P.K.D.V. (2003). Weld Quality Prediction of Mild Steel Pipe Joint during Shielded Metal Arc Welding through ANN. Volume 3, Issue 20, International Journal of Engineering Research & Technology (Ijert), 2018.
Dehabadi, V.M., Ghorbanpour, S. & Azimi, G. J. Cent. South Univ. (2016) 23: 2146. https://doi.org/10.1007/s 117 71-016-3271-1
Downloads
Published
Issue
Section
How to Cite
