Engineering and Technology in India

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Comparison of RSM and RA with ANN in Predicting Mechanical Properties of Friction Stir Welded Aluminum Pipes


Affiliations
1 Tanta University, Egypt
     

   Subscribe/Renew Journal


Aluminum can’t successfully be arc welded in an air environment, due to the affinity for oxygen. If fusion welded in normal atmosphere oxidization readily happens and this outcome in both slag inclusion and porosity in the weld, greatly reducing its mechanical properties. This work presents a systematic approach to develop the suggestion model by three (ANN), response surface methodology (RSM) and regression analysis (RA) for predicting the ultimate tensile strength, percentage of elongation and hardness of 6061 aluminum alloy which is widely used in automotive, aircraft and defense industries by incorporating (FSW) friction stir welding process parameter such as tool rotation speed, welding speed and material thickness. The results obtained through regression analysis and response surface methodology were compared with those through artificial neural networks.

Keywords

Friction Stir Welding, Aluminium Pipe, Regression Analysis, Response Surface Methodology, Artificial Neural Network.
Subscription Login to verify subscription
User
Notifications
Font Size


  • Ambrogio, G., Fratini, L. and Micari, F. (2006). Incremental forming of friction stir welded tailored sheets, In : Proceedings of the 8th Biennial ASME Conference on Engineering Systems Design and Analysis, ESDA2006.

  • Arcakhoglu, E., Cavusoglu, A. and Risen, A. (2004). Thermodynamic analyses of refrigerant mixtures using artificial neural networks. J. Appl. Energy, 78 : 219-230.

  • Davies, R.W.S., Diamond, P. S., Sklad, S., Wazny, L., Kaunitz, B., Fulbright, D., Waldron and McTernan, K. (2005).

  • Friction-stir-joined aluminum sheet materials for heavy vehicle cab structures, In: Annual Progress Report: High Strength Weight Reduction Materials, 2005.

  • Grant, G.J., Davies, R.W., Stephens, E.V., Wazny, S., Kaunitz, L. and Waldron, D.J. (2006). The formability of Friction Stir Welds in automotive stamping environments. SAE Transactions J. Materials & Manufact., 114 (5) :619-629.

  • Kanakaraja, D. and Hema, P. (2013). Comparative study on different pin geometries of tool profile in friction stir welding using artificial neural networks. Internat. J. Mechanical Engg. & Technol., 4 (2): ISSN 0976 – 6340 (Print), ISSN 0976-6359 online.

  • Khourshid, A.M., Bousaif, T. and Sabry, I. (2011). Welding of cylindrical parts by using Friction Stir Technique. Monufia University.

  • Khourshid, A. M. and Sabry, I. (2013). Friction stir welding study on aluminum pipe. Internat. J. Mechanical Engg. & Robotics Res., 2013.

  • Khourshid, A.M., Ahmed, M. El-Kassas and Sabry, Ibraheem (2015). Integration between artificial neural network and responses surfaces methodology for modeling of Friction Stir Welding, Internat. J. Adv. Engg. Res. & Sci., 2 (3): 67-73.

  • Kim, I. S., Son, K.J., Yang, Y.S. and Karaganda, P. K. D. V. (2003). Sensitivity analysis for process parameter parameters in GMA welding process using factorial design method. Internat. J. Machine Tools & Manufact.,43 : 763-776.

  • Klingensmith, S., DuPont, J.N. and Marder, A.R. (2005). Microstructural characterization of a double-sided Friction Stir Weld on a superaustenitic stainless steel, Welding J., 84 (5): 77–85.

  • Plaintively, R., Koshy Mathews, P. and Murugan, N. (2011). Development of mathematical models to predict the mechanical properties of friction stir welded AA6351 aluminum alloy. J. Engg. Sci. & Technol. Rev., 4 (1) : 25-31.

  • Ramasamy, S., Gould, D. and Workman (2002). Design of experiments study to examine the effect of polarity on stud welding. Welding J., 81 : 19- 26.

  • Su, J.Q., Nelson,T.W., Mishra,R. and Mahoney, M.(2003). Mi-crostructural investigation of friction stir welded 7050- T654 aluminium.Act Mater., 51 (3) : 713- 729, doi:10.1016/S1359-6454(02)00449-4.

  • Zeng, W. M., Wu, H. L. and Zhang, J. (2006). Effect of tool wear on mechanical properties and acoustic emission of friction stir welded 6061 Al alloy. Acta. Metallurgica. Sinica., 19 (1): 9-19.

  • Zhang, Z. and Friedrich, K. (2003). Artificial neural networks applied to polymer composites: A review. J. Composit. Sci.& Technol., 63: 2029-2044.

  • Zhou, C., Yang, X. and Luan, G. (2006). Effect of ischolar_main flaws in the fatigue property offriction stirs welds in 2024-T3 aluminum alloys. Mater Sci.Engg., 418 : 155–160.


Abstract Views: 751

PDF Views: 9




  • Comparison of RSM and RA with ANN in Predicting Mechanical Properties of Friction Stir Welded Aluminum Pipes

Abstract Views: 751  |  PDF Views: 9

Authors

Ibraheem Sabry
Tanta University, Egypt
Ahmed M. El-Kassas
Tanta University, Egypt
A. M. Khourshid
Tanta University, Egypt
H. M. Hidawy
Tanta University, Egypt

Abstract


Aluminum can’t successfully be arc welded in an air environment, due to the affinity for oxygen. If fusion welded in normal atmosphere oxidization readily happens and this outcome in both slag inclusion and porosity in the weld, greatly reducing its mechanical properties. This work presents a systematic approach to develop the suggestion model by three (ANN), response surface methodology (RSM) and regression analysis (RA) for predicting the ultimate tensile strength, percentage of elongation and hardness of 6061 aluminum alloy which is widely used in automotive, aircraft and defense industries by incorporating (FSW) friction stir welding process parameter such as tool rotation speed, welding speed and material thickness. The results obtained through regression analysis and response surface methodology were compared with those through artificial neural networks.

Keywords


Friction Stir Welding, Aluminium Pipe, Regression Analysis, Response Surface Methodology, Artificial Neural Network.

References