International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020


IJSTR >> Volume 9 - Issue 1, January 2020 Edition

International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616

Modeling And Artificial Neural Network Based Prediction Of Wear Rate Of AA7075/Al2O3 Particulate Metal Matrix Composites

[Full Text]



Raghavendra.N, D.Shivalingappa



Artificial Neural Network, Al7075, Bayesian Regularization, Levenberg Marquardt, Particulate Metal Matrix composite, Stir casting, Wear rate



Particulate Metal Matrix Composites (PMMC) offers light weight, high wear resistance and high strength, which are attractive for automobile applications. Much of the earlier works on Aluminium 7075 (Al7075) based composite are either contains Silicon Carbide (SiC) as reinforcement or Alumina (Al2O3) in the fiber form. The Al7075/Al2O3 Particulate composite developed by liquid processing route needs to be studies with respect to its Mechanical and Tribological behavior in the context of processing route, volume fraction, particle size, compatibility of matrix and reinforcement for composite materials desired property. Further larger scope is available to establish the wear behavior of composite materials with mathematical models to evaluate its suitability for various applications. Al 7075/Al2O3 particulate MMC has been developed by stir casting process demonstrates improved Mechanical and Tribological property. Oxidative wear, delamination wear, adhesive wear, and small amount of Abrasive wear mechanisms are found to occur during the wear of MMCs. In the present work wear data and different wear mechanisms at various speed and load for the speed range of 0-1400 rpm and 1- 14kg load were evaluated. The nonlinear behavior of wear rate of composite controlled by more than 100 controlling parameter, but in the present work effect of limited parameters (13 parameters) are studied. Thirteen input parameter and eight output parameters are used and the ANN model with single hidden layer using feed forward back propagation neural network was developed. Based on the literature two algorithm are selected for the present work 1.Levenberg Marquardt 2.Bayesian Regularization The corresponding transfer functions are Trainlm and Trainbr are used for the network models. The Developed ANN model can be effectively extended to predict the nonlinear behavior of wear for any particulate MMC. Large amount of time, money and materials invested for the experiments can be reduced due to development of ANN models.



[1] Prashant Karandikar, Eric M. Klier, Matthew Watkins, Brandon McWilliams, and Michael Aghajanian, Al/Al2O3 Metal Matrix Composites (MMCs) and Macrocomposites for Armor Applications, Proceedings of the 37th International Conference and Exposition on Advanced Ceramics and Composites (ICACC), Daytona Beach, FL, 27 January–1 February 2013.
[2] Yanqiang Liu, Zhong Han, Hongtao Cong, Effects of sliding velocity and normal load on the Tribological behavior of nanocrystallineAluminium based Composite, wear, Elsevier, 268 (2010) 976–983.
[3] A.Ahmed1, A.J.Neely1 and K.Shankar1, Effect of Ceramic Reinforcements on the Mechanical Behaviour of 7xxx series Aluminium Matrix Composites, 5th Australasian Congress on Applied Mechanics, ACAM 2007.
[4] Koji Kato, Koshi Adachi, Modern tribology hand Book, CRC press 2001.
[5] T AStolarski, Tribology in machine design, Butter worth Heinemann, Wildwood Avenue, Woburn, MA 01801-2041 A division of Reed Educational and Professional Publishing, reprint 2000.
[6] Serdar Osman Yılmaz E SonerBuytoz, Relationship between thermal and sliding wear behavior of Al6061/Al2O3 metal matrix composites, J Mater Science Springer, Science Business Media (2007) 42:4485–4493.
[7] S.B. Venkata Siva, K.L. Sahoo, R.I. Ganguly, And R.R. Dash, Effect of Hot Working on Structure and Tribological Properties of Aluminium Reinforced with Aluminium Oxide Particulates, JMEPEG _ASM International, Volume 21(7) July 2012, 1226–1231.
[8] J. Corrochano, C. Cerecedo, V. Valcárcel, M. Lieblich, F. Guitián, Whiskers of Al2O3 As Reinforcement Of A Powder Metallurgical 6061 Aluminium Matrix Composite, Materials Letters , Elsevier B.V., 62 (2008) 103–105.
[9] AleksandarVencl, IlijaBobic Milan, T. JovanovicMiroslavBabic, Slobodan Mitrovic, Microstructural and Tribological Properties of A356 Al–Si Alloy Reinforced with Al2O3 Particles, Tribology Lett Springer Science- Media, LLC (2008) 32:159–170.
[10] WANG Yi-qi, SONG Jung-il, Dry sliding wear behavior of Al2O3 fiber and SiC particle reinforced aluminium based MMCs fabricated by squeeze casting method, Trans. Nonferrous Met. Soc. China 21(2011) 1441−1448.
[11] M.R.Dashtbayazi (2007) Characterization of Al/SiC Nanocomposite Prepared by Mechanical Alloying Process Using Artificial Neural Network Model, Materials and Manufacturing Processes, 23:1, 37-45.
[12] Fathy & A. A. Megahed, Prediction of abrasive wear rate of in situ Cu-Al2O3nanocomposite using artificial neural networks, International Journal of Advanced Manufacturing Technology, Springer (2012) 62:953–963.
[13] Necat Altinkok, Rasit Koker,Use of artificial neural network for prediction of physical properties and tensile strengths in particle reinforced aluminium matrix composites, Journal Of Materials Science Springer Science + Business Media, Inc.40 (2005) 1767 – 1770.
[14] H. K. D. H. Bhadeshia, Neural Networks in Materials Science, ISIJ International, 1999.
[15] A. Canakci1, T. Varol 1, S. Ozsahin2 , S. Ozkaya1, Artificial Neural Network Approach to Predict the Abrasive Wear of AA2024-B4C Composites, Universal Journal of Materials Science Horizon Research Publishing 2(6): 111-118, 2014.