Neural Computing and Applications

, Volume 31, Supplement 2, pp 1145–1154 | Cite as

Evolution of the size distribution of Al–B4C nano-composite powders during mechanical milling: a comparison of experimental results with artificial neural networks and multiple linear regression models

  • F. AkhlaghiEmail author
  • M. Khakbiz
  • A. Rezaii Bazazz
Original Article


In the present study, two three-layer feed-forward artificial neural networks (ANNs) and multiple linear regression (MLR) models were developed for modeling the effects of material and process parameters on the powder particle size characteristics generated during high-energy ball milling of Al and B4C powders. The investigated process parameters included aluminum particle size, B4C size and its content as well as milling time. The median particle size (D50) and the extent of size distribution (D90D10) were considered as target values for modeling. The developed ANN and MLR models could reasonably predict the experimentally determined characteristics of powders during mechanical milling.


Al–B4C nano-composite powders Mechanical milling Artificial neural networks Multiple linear regression 



Authors sincerely acknowledge Iranian Nanotechnology initiative (INI) for finical support of the research work. The help of Dr. H. Baharvandi in experimental work is also appreciated.

Compliance with ethical standards

Conflict of interest

The authors declare that there is no conflict of interest.


  1. 1.
    Ma ZY, Li YL, Liang Y, Zheng F, Bi J, Tjong SC (1996) Nanometric Si3N4 particulate-reinforced aluminum composite, dispersion strengthened superalloys by mechanical alloying. Mater Sci Eng A 219:229–231CrossRefGoogle Scholar
  2. 2.
    Ferkel H, Mordike BL (2001) Magnesium strengthened by SiC nanoparticles. Mater Sci Eng A 298:193–199CrossRefGoogle Scholar
  3. 3.
    Naser J, Ferkel H, Riehemann W (1997) Grain stabilisation of copper with nanoscaled Al2O3-powder. Mater Sci Eng A 470:234–236Google Scholar
  4. 4.
    Ying DY, Zhang DL (2000) Processing of Cu–Al2O3 metal matrix nanocomposite materials by using high energy ball milling. Mater Sci Eng A 286:152–156CrossRefGoogle Scholar
  5. 5.
    Karimzadeh F, Enayati MH, Tavoosi M (2008) Synthesis and characterization of Zn/Al2O3 nanocomposite by mechanical alloying. Mater Sci Eng A 486:45–48CrossRefGoogle Scholar
  6. 6.
    Yamasaki T, Zheng YJ, Ogino Y, Terasawa M, Mitamura T, Fukami T (2003) Formation of metal/TiN/TiC nanocomposite powders by mechanical alloying and their consolidation. Mater Sci Eng A 350:168–172CrossRefGoogle Scholar
  7. 7.
    Chung KH, He JD, Shin HJ, Schoenung M (2003) Mechanisms of microstructure evolution during cryomilling in the presence of hard particles. Mater Sci Eng A 356:23–31CrossRefGoogle Scholar
  8. 8.
    Prabhu B, Suryanarayana C, An L, Vaidyanathan R (2006) Synthesis and characterization of high volume fraction Al–Al2O3 nanocomposite powders by high-energy milling. Mater Sci Eng A 425:192–200CrossRefGoogle Scholar
  9. 9.
    Razavi-Hesabi Z, Simchi A, Seyed Reihani SM (2006) Structural evolution during mechanical milling of nanometric and micrometric Al2O3 reinforced Al matrix composites. Mater Sci Eng A 428:159–168CrossRefGoogle Scholar
  10. 10.
    Woo KD, Zhang DL (2004) Fabrication of Al–7 wt%Si–0.4 wt%Mg/SiC nanocomposite powders and bulk nano composites by high energy ball milling and powder metallurgy. Curr Appl Phys 4:175–178CrossRefGoogle Scholar
  11. 11.
    Goujon C, Goeuriot P (2003) Influence of the content of ceramic phase on the precipitation hardening of Al alloy 7000/AlN nanocomposites. Mater Sci Eng A 356:399–404CrossRefGoogle Scholar
  12. 12.
    Dobrzanski LA, Sitek W (1999) The modelling of hardenability using neural networks. J Mater Process Technol 92:8–14CrossRefGoogle Scholar
  13. 13.
    Dobrzanski LA, Sitek W (1998) Application of a neural network in modelling of hardenability of constructional steels. J Mater Process Technol 78:59–66CrossRefGoogle Scholar
  14. 14.
    Guo Z, Sha W (2004) Modelling the correlation between processing parameters and properties of maraging steels using artificial neural network. Comput Mater Sci 29:12–28CrossRefGoogle Scholar
  15. 15.
    Bruni C, Forcellese A, Gabrielli F, Simoncini M (2006) Modelling of the rheological behaviour of aluminium alloys in multistep hot deformation using the multiple regression analysis and artificial neural network techniques. J Mater Process Technol 177:323–326CrossRefGoogle Scholar
  16. 16.
    Sheikh H, Serajzadeh S (2008) Estimation of flow stress behavior of AA5083 using artificial neural networks with regard to dynamic strain ageing effect. J Mater Process Technol 196:115–119CrossRefGoogle Scholar
  17. 17.
    Malinov S, Sha W (2003) Software products for modelling and simulation in materials science. Comput Mater Sci 28:179–198CrossRefGoogle Scholar
  18. 18.
    Malinov S, Sha W (2004) Application of artificial neural networks for modelling correlations in titanium alloys. Mater Sci Eng A 365:202–2011CrossRefGoogle Scholar
  19. 19.
    Zhang YF, Lu L, Yap SM (1999) Prediction of the amount of PCA for mechanical milling. J Mater Process Technol 89–90:260–265CrossRefGoogle Scholar
  20. 20.
    Dashtbayazi MR, Shokuhfar A, Simchi A (2007) Artificial neural network modeling of mechanical alloying process for synthesizing of metal matrix nanocomposite powders. Mater Sci Eng A 466:274–279CrossRefGoogle Scholar
  21. 21.
    Qingbin L, Zhong J, Mabao L, Shichun W (1996) Acquiring the constitutive relationship for a thermal viscoplastic material using an artificial neural network. J Mater Process Technol 62:206–210CrossRefGoogle Scholar
  22. 22.
    Khakbiz M, Akhlaghi F (2009) Synthesis and structural characterization of Al–B4C nano-composite powders by mechanical alloying. J Alloy Compd 479:334–341CrossRefGoogle Scholar
  23. 23.
    Arik H (2004) Production and characterization of in situ Al4C3 reinforced aluminum-based composite produced by mechanical alloying technique. Mater Des 25:31–40CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  1. 1.School of Metallurgy and Materials Engineering, Center of Excellence for High Performance Materials, College of EngineeringUniversity of TehranTehranIran
  2. 2.Division of Biomedical Engineering, Department of Life Science Engineering, Faculty of New Sciences and TechnologiesUniversity of TehranTehranIran
  3. 3.Department of Materials Science and Engineering, Faculty of EngineeringFerdowsi University of MashhadMashhadIran

Personalised recommendations