Modelling of Friction Stir Extrusion using Artificial Neural Network (ANN)

In the present study, an artificial neural network (ANN) model is developed to predict the correlation between the friction stir extrusion (FSE) parameters and the recycled wires’ average grain sizes. FSE is a solid–state synthesis technique, in which machining chips are firstly loaded into the container, and then a rotating tool with a central hole is plunged into the chips at a selected rotational speed and feed rate to achieve indirect extrusion. Selecting rotational speed (RS), vertical speed (VS), and extrusion hole size (HS) as the input and average grain size as the output of the system, the 3–6–1 ANN is used to show the correlation between the input and output parameters. Checking the accuracy of the neural network, R squared value and Root– Mean–Square–Error (RMSE) of the developed model (0.94438 and 0.75794, respectively) have shown that there is a good agreement between experimental and predicted results. A sensitivity analysis has been conducted on the ANN model to determine the impact of each input parameter on the average grain size. The results showed that the rotational speed has more effect on average grain size during the FSE process in comparison to other input parameters.

[1]  V. S. Kumar,et al.  An experimental analysis and optimization of process parameter on friction stir welding of AA 6061-T6 aluminum alloy using RSM , 2013 .

[2]  Zhongrong Zhou,et al.  Fretting wear behavior of AZ91D and AM60B magnesium alloys , 2006 .

[3]  M. Narvan,et al.  Experimental Analysis and Microstructure Modeling of Friction Stir Extrusion of Magnesium Chips , 2016 .

[4]  M. Gevrey,et al.  Review and comparison of methods to study the contribution of variables in artificial neural network models , 2003 .

[5]  R. Tuntas,et al.  An investigation on the aging responses and corrosion behaviour of A356/SiC composites by neural network: The effect of cold working ratio , 2016 .

[6]  J. H. Lee,et al.  Effect of grain refinement of magnesium alloy AZ31 by severe plastic deformation on material characteristics , 2008 .

[7]  V. Balasubramanian,et al.  Comparison of RSM with ANN in predicting tensile strength of friction stir welded AA7039 aluminium alloy joints , 2009 .

[8]  Michael R. Zinn,et al.  Measurement of Tool-Workpiece Interface Temperature Distribution in Friction Stir Welding , 2014 .

[9]  Shivangi Nigam,et al.  Vehicular traffic noise modeling using artificial neural network approach , 2014 .

[10]  Qudong Wang,et al.  Solid-state recycling of AZ91D magnesium alloy chips , 2012 .

[11]  E. Nicholas.  Friction Processing Technologies , 2003 .

[12]  Sarit Dutta,et al.  PVT correlations for Indian crude using artificial neural networks , 2010 .

[13]  Hakan Ates,et al.  Prediction of gas metal arc welding parameters based on artificial neural networks , 2007 .

[14]  N. D. Ghetiya,et al.  Prediction of Tensile Strength in Friction Stir Welded Aluminium Alloy Using Artificial Neural Network , 2014 .

[15]  J. Grum,et al.  The use of factorial design and response surface methodology for fast determination of optimal heat treatment conditions of different Ni–Co–Mo surfaced layers , 2004 .

[16]  Bahaa I. Kazem,et al.  Prediction of Friction Stir Welding Characteristic Using Neural Network , 2008 .

[17]  J. Paulo Davim,et al.  Optimization of machining parameters of Al/SiC-MMC with ANOVA and ANN analysis , 2009 .

[18]  Ren-Guo Song,et al.  The application of artificial neural networks to the investigation of aging dynamics in 7175 aluminium alloys , 1995 .

[19]  Alfonso Palmer,et al.  Numeric sensitivity analysis applied to feedforward neural networks , 2003, Neural Computing & Applications.

[20]  Shuyan Wu,et al.  Effect of extrusion ratio on mechanical and corrosion properties of AZ31B alloys prepared by a solid recycling process , 2011 .

[21]  C. Muralidharan,et al.  Establishing Empirical Relationships to Predict Grain Size and Tensile Strength of Friction Stir Welded AA 6061-T6 Aluminium Alloy Joints , 2010 .

[22]  M. Narvan,et al.  Evaluation of wear and corrosion resistance of pure Mg wire produced by friction stir extrusion , 2015 .

[23]  Joan Pellegrino,et al.  Energy Use, Loss, and Opportunities Analysis for U.S. Manufacturing and Mining , 2004 .

[24]  Phisut Apichayakul,et al.  Resistance Spot Welding Optimization Based on Artificial Neural Network , 2014 .

[25]  H Schmidli,et al.  Advantages of Artificial Neural Networks (ANNs) as alternative modelling technique for data sets showing non-linear relationships using data from a galenical study on a solid dosage form. , 1998, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[26]  N. Murugan,et al.  Development of mathematical model to predict the mechanical properties of friction stir welded AA6351 aluminum alloy , 2011 .

[27]  Lehua Qi,et al.  Neural network modeling and optimization of semi-solid extrusion for aluminum matrix composites , 2004 .

[28]  Z. Ji,et al.  Mechanical properties and fracture behavior of Mg-2.4Nd-0.6Zn-0.6Zr alloys fabricated by solid recycling process , 2009 .

[29]  V. Balasubramanian,et al.  Predicting tensile strength of friction stir welded AA6061 aluminium alloy joints by a mathematical model , 2009 .

[30]  Zesheng Ji,et al.  Effect of extrusion ratio on microstructure and mechanical properties of Mg–Nd–Zn–Zr alloys prepared by a solid recycling process , 2008 .

[31]  M. Narvan,et al.  Optimization of Friction Stir Extrusion (FSE) Parameters Through Taguchi Technique , 2016, Transactions of the Indian Institute of Metals.

[32]  Subodh K. Das,et al.  Aluminum recycling—An integrated, industrywide approach , 2010 .

[33]  Derek Partridge,et al.  Assessing the Impact of Input Features in a Feedforward Neural Network , 2000, Neural Computing & Applications.

[34]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[35]  M. Ansari,et al.  Theoretical and Experimental Investigation of the Effective Parameters on the Microstructure of Magnesium Wire Produced by Friction Stir Extrusion , 2015 .

[36]  Anthony P. Reynolds,et al.  Production of wire via friction extrusion of aluminum alloy machining chips , 2010 .

[37]  Mostafa Akbari,et al.  Predicting the grain size and hardness of AZ91/SiC nanocomposite by artificial neural networks , 2012 .

[38]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .

[39]  Fernando Morgado Dias,et al.  A high bit resolution FPGA implementation of a FNN with a new algorithm for the activation function , 2007, Neurocomputing.

[40]  Yasuo Yamada,et al.  Superplasticity and cavitation of recycled AZ31 magnesium alloy fabricated by solid recycling process , 2002 .

[41]  Erol Arcaklioğlu,et al.  Artificial neural network application to the friction stir welding of aluminum plates , 2007 .