International Journal of Vehicle Structures and Systems

Open Access Open Access  Restricted Access Subscription Access

Comparison of ANN Training Algorithms for Predicting the Tensile Strength of Friction Stir Welded Aluminium Alloy AA1100


Affiliations
1 Dept. of Mech. Engg., Amrita School of Engg., Amrita Vishwa Vidyapeetham, Amrita University, Coimbatore, India
 

   Subscribe/Renew Journal


Aluminium alloy AA1100 finds application in light weight structures due to its high strength to weight ratio. Friction stir welding is a solid state welding process, in which the materials are joined in the plasticized state. The quality of the friction stir welded joints depends on the process parameters used and tool parameters. In this study, four process parameters were varied at five levels and experimental trials were performed as per face centered central composite design. Artificial neural network model was developed with cascade forward propagation network architecture and trained with LM algorithm and BFGS QN algorithm. The models were used to predict the tensile strength of the joints and the error in prediction was used to judge the accuracy of the developed models. It is observed that BFGS QN algorithm trains the ANN efficiently and results in accurate predictions.

Keywords

Aluminium Alloy, Friction Stir Welding, Friction Stir Welding, Artificial Neural Network, Tensile Strength.
User
Subscription Login to verify subscription
Notifications
Font Size

  • K.J. Colligan. 2010. The friction stir welding process: an overview, Friction Stir Welding, Woodhead Publishing, 15-41.

  • R.S. Mishra and H. Sidhar. 2017. Friction stir welding, Friction Stir Welding of 2XXX Aluminum Alloys Including Al-Li Alloys, Butterworth-Heinemann, 1-13.

  • L.E. Murr, G. Liu and J.C. McClure. 1997. Dynamic recrystallization in friction-stir welding of aluminium alloy 1100, J. Materials Sci. Letters, 16, 1801-1803. https://doi.org/10.1023/A:1018556332357.

  • R. Padmanaban, V. Balusamy and V.R. Kishore. 2012. Effect of axial pressure and tool rotation speed on temperature distribution during dissimilar friction stir welding, Advanced Materials Research, 418-420, 1934-1938. https://doi.org/10.4028/www.scientific.net/AMR.418-420.1934.

  • R. Padmanaban, V. Balusamy and K.N. Nouranga. 2015. Effect of process parameters on the tensile strength of friction stir welded dissimilar aluminum joints, J. Engg. Sci. and Tech., 10, 790-801.

  • R.V. Vignesh, R. Padmanaban, M. Arivarasu, K.P. Karthick, A.A. Sundar and J. Gokulachandran. 2016. Analysing the strength of friction stir spot welded joints of aluminium alloy by fuzzy logic, IOP Conf. Series: Materials Sci. and Engg., 149.

  • R. Zettler. 2010. Material deformation and joint formation in friction stir welding, Friction Stir Welding, Woodhead Publishing, 42-72.

  • R. Zettler, T. Vugrin and M. Schmücker. 2010. Effects and defects of friction stir welds, Friction Stir Welding, Woodhead Publishing, 245-276.

  • Y.S. Sato, Y. Kurihara, S.H.C. Park, H. Kokawa and N. Tsuji. 2004. Friction stir welding of ultrafine grained Al alloy 1100 produced by accumulative roll-bonding, Scripta Materialia, 50, 57-60. https://doi.org/10.1016/j.scriptamat.2003.09.037.

  • M.S. Khorrami, M. Kazeminezhad and A.H. Kokabi. 2012. Mechanical properties of severely plastic deformed aluminum sheets joined by friction stir welding, Materials Sci. and Engg.: A, 543, 243-248. https://doi.org/10.1016/j.msea.2012.02.082.

  • S.A. Hussein, A.S.M. Tahir and A.B. Hadzley. 2015. Characteristics of aluminum-to-steel joint made by friction stir welding: A review, Materials Today Communications, 5, 32-49. https://doi.org/10.1016/j.mtcomm.2015.09.004.

  • I.A. Kartsonakis, D.A. Dragatogiannis, E.P. Koumoulos, A. Karantonis and C.A. Charitidis. 2016. Corrosion behaviour of dissimilar friction stir welded aluminium alloys reinforced with nanoadditives, Materials & Design, 102, 56-67. https://doi.org/10.1016/j.matdes.2016.04.027.

  • M. Sajed. 2016. Parametric study of two-stage refilled friction stir spot welding: Part 1, J. Mfg. Processes, 24, 307-317. https://doi.org/10.1016/j.jmapro.2016.09.011.

  • J.M. Zurada. 1992. Introduction to Artificial Neural Systems, 8, West St. Paul.

  • B. Krose, B. Krose, P. Van der Smagt and P. Smagt. 1993. An Introduction to Neural Networks.

  • N.D. Ghetiya and K.M. Patel. 2014. Prediction of tensile strength in friction stir welded aluminium alloy using artificial neural network, Proc. Tech., 14, 274-281. https://doi.org/10.1016/j.protcy.2014.08.036.

  • A.K. Lakshminarayanan and V. Balasubramanian. 2009. Comparison of RSM with ANN in predicting tensile strength of friction stir welded AA7039 aluminium alloy joints, Trans. of Nonferrous Metals Society of China, 19, 9-18. https://doi.org/10.1016/S1003-6326(08)60221-6.

  • H. Okuyucu, A. Kurt and E. Arcaklioglu. 2007. Artificial neural network application to the friction stir welding of aluminum plates, Materials & Design, 28, 78-84. https://doi.org/10.1016/j.matdes.2005.06.003.

  • R.V. Vignesh and R. Padmanaban. 2017. Modelling tensile strength of friction stir welded aluminium alloy 1100 using fuzzy logic, Proc. 11th Int. Conf. Intelligent Systems and Control, 449-456.


Abstract Views: 436

PDF Views: 161




  • Comparison of ANN Training Algorithms for Predicting the Tensile Strength of Friction Stir Welded Aluminium Alloy AA1100

Abstract Views: 436  |  PDF Views: 161

Authors

R. V. Vignesh
Dept. of Mech. Engg., Amrita School of Engg., Amrita Vishwa Vidyapeetham, Amrita University, Coimbatore, India
R. Padmanaban
Dept. of Mech. Engg., Amrita School of Engg., Amrita Vishwa Vidyapeetham, Amrita University, Coimbatore, India

Abstract


Aluminium alloy AA1100 finds application in light weight structures due to its high strength to weight ratio. Friction stir welding is a solid state welding process, in which the materials are joined in the plasticized state. The quality of the friction stir welded joints depends on the process parameters used and tool parameters. In this study, four process parameters were varied at five levels and experimental trials were performed as per face centered central composite design. Artificial neural network model was developed with cascade forward propagation network architecture and trained with LM algorithm and BFGS QN algorithm. The models were used to predict the tensile strength of the joints and the error in prediction was used to judge the accuracy of the developed models. It is observed that BFGS QN algorithm trains the ANN efficiently and results in accurate predictions.

Keywords


Aluminium Alloy, Friction Stir Welding, Friction Stir Welding, Artificial Neural Network, Tensile Strength.

References





DOI: https://doi.org/10.4273/ijvss.10.2.05