Advertisement

Modeling of the mechanical and physical properties of hybrid composites produced by gas pressure infiltration

  • Necat Altinkök
Technical Paper
  • 30 Downloads

Abstract

In this study, mechanical and physical properties of hybrid composites were analyzed by using a data acquisition technique like artificial neural networks. Matlab software was used to examine the effects of test parameters on infiltration temperature and pressure. Bending strength, hardness and density of hybrid composite were affected in neural network training and test. Firstly, training set was prepared for the MMCs. In this set, three various training algorithms were used with artificial neural network. At the end of the each learning, the accuracy of the each training algorithm was checked by using test set. As a result, the predicted results which were closest to the experimental results were obtained with the Levenberg–Marquardt training algorithm for bending strength, hardness and density of hybrid composites. These trained values had an average error of 0.376%, 2.969% and 2.648% for bending strength, density and hardness values, respectively.

Keywords

Hybrid metal matrix composites Mechanical properties Infiltration technique Artificial neural network (ANN) modeling 

Abbreviations

MMCs

Metal matrix composites

α-Al2O3

α-Alumina

ANN

Artificial neural network

AlSi10Mg

Aluminum code

μm

Micron meter

EDS

Energy-dispersive spectroscopy

SEM

Scanning electron microscope

MPa

Mega Pascal

HB

Hardness Brinell

List of symbols

i, j, k

Different neurons in the network (in different layers)

wi

Weight associated with xi signal

xi

Input (I = 1, 2, …, n)

y

The output

t

The threshold level given by user

n

nth training pattern(example) presented to the network

\( w_{i} \)

The weight associated with xi signal

\( w_{i} ({\text{new}}) \)

The new weight associated with xi signal

\( w_{i} ({\text{old}}) \)

The old weight associated with xi signal

\( \Delta w_{i} \)

The weight correction associated with xi signal

\( w_{ji} (n) \)

The synaptic weight connecting the output of neuron i to the input of neuron j at iteration n

F(s)

A nonlinear function

\( W_{jk}^{i} \)

The different weights connecting different elements

\( \Delta w_{ji} (n) \)

The correction applied to \( w_{ji} (n) \) at iteration n

f(x)output

The result of the neural network

f(x)actual

The actual value

\( \delta_{j} \)

The error associated with the jth element

δ

Associated error

\( w_{nj} \)

The weight associated with the line from element n to element j

α

Momentum constant

I

Input vector to unit n

η

The learning ratio parameter

α

The momentum constant

N

Denotes the total number of samples in training set

C

The set including all the neurons in the output layer of the network

\( e_{k} (n) \)

The error signal at the output of neuron k for iteration n

\( d_{k} (n) \)

The desired response for neuron k

\( y_{k} (n) \)

The function signal appearing at the output neuron k at iteration n

\( \varepsilon (n) \)

The instantaneous sum of error squares at iteration n

\( \varepsilon_{\text{av}} (n) \)

The average squared error

References

  1. 1.
    El-Daly AA, Abdelhameed M, Hashish M, Daoush WM (2013) Fabrication of silicon carbide reinforced aluminum matrix nanocomposites and characterization of its mechanical properties using non-destructive technique. Mater Sci Eng, A 559:384–393CrossRefGoogle Scholar
  2. 2.
    Karbalaei M, Akbari M, Mirzaee O, Baharvandi HR (2013) Fabrication and study on mechanical properties and fracture behaviour of nanometric Al2O3 particle-reinforced A356 composites focusing on the parameters of vortex method. Mater Des 46:199–205CrossRefGoogle Scholar
  3. 3.
    Sweet GA, Brochu MR Jr, Hexemer L, Donaldson IW, Bishop DP (2015) Consolidation of aluminum-based metal matrix composites via spark plasma sintering. Mater Sci Eng, A 648:123–133CrossRefGoogle Scholar
  4. 4.
    Bin X, Xiaogang W (2015) Thermo-physical properties and reaction process of SiCp/Al–7Si–5 Mg aluminum matrix composites fabricated by pressureless infiltration. Rare Met Mater Eng 44(5):1057–1061CrossRefGoogle Scholar
  5. 5.
    Bobic I, Ruzic J, Bobic B, Babic M, Vencl A (2014) Microstructural characterization and artificial aging of compo-casted hybrid A356/SiCp/Grp composites with graphite macroparticles. Mater Sci Eng, A 612:7–15CrossRefGoogle Scholar
  6. 6.
    Robert MH, Jorge AH, Achiev J (2012) Processing and properties of AA7075/porous SiO2–MgOAl2O3 composite. Mater Manuf Eng 3:1–5Google Scholar
  7. 7.
    Ramesha CS, Keshavamurthy R (2012) Influence of forging on mechanical properties of Ni–P coated Si3N4 reinforced Al6061 composites. Mater Sci Eng, A 551:59–66CrossRefGoogle Scholar
  8. 8.
    ThüNemann M, Beffort O, Herzog A, Vog U (2004) Porous SiC preforms by intergranular binding with preceramic polymers. Adv Eng Mater 6(3):167–172CrossRefGoogle Scholar
  9. 9.
    Long S, Beffort O, Moret G, Thevoz PH (2000) Processing of Al-based MMCs by indirect squeeze infiltration of ceramic preforms on a shot control high pressure die casting machine. Aluminium 76(1/2):82–89Google Scholar
  10. 10.
    ThüNemann M, Beffort O, Kleiner S, Vogt U (2007) Aluminum matrix composites based on preceramic-polymer-bonded SiC preforms. Compos Sci Technol 67:2377–2383CrossRefGoogle Scholar
  11. 11.
    Gil R, Jinnapat A, Kennedy AR (2012) Pressure-assisted infiltration of molten aluminium into open cell ceramic foams: experimental observations and infiltration modeling. Compos Part A 243:880–884CrossRefGoogle Scholar
  12. 12.
    Yang B, Wang F, Zhang JS (2003) Microstructural characterization of in situ TiC/Al and TiC/Al–20Si–5Fe–3Cu–1 Mg composites prepared by spray deposition. Acta Mater 51:4977–4989CrossRefGoogle Scholar
  13. 13.
    Raju K, Ojha SN, Harsha AP (2008) Spray forming of aluminum alloys and its composites. Spray forming of aluminum alloys and its composites. J Mater Sci 43:2509–2521CrossRefGoogle Scholar
  14. 14.
    Huang LJ, Geng L, Peng HX (2015) Microstructurally inhomogeneous composites: is a homogeneous reinforcement distribution optimal. Prog Mater Sci 71:93–168CrossRefGoogle Scholar
  15. 15.
    Li JG (1994) Wetting of ceramic materials by liquid silicon, aluminium and metallic melts containing titanium and other reactive elements: a review. Ceram Int 20:391–412CrossRefGoogle Scholar
  16. 16.
    Lemster K, Delporte M, Graule T, Kuebler J (2007) Activation of alumina foams for fabricating MMCs by pressureless infiltration. Ceram Int 33:1179–1185CrossRefGoogle Scholar
  17. 17.
    Lemster K, Graule T, Kuebler J (2005) Processing and microstructure of metal matrix composites prepared by pressureless Ti-activated infiltration using Fe-base and Ni-base alloys. Mater Sci Eng, A 393:229–238CrossRefGoogle Scholar
  18. 18.
    Kevorkijan V, Kosmac T, Kristoffer K (2002) Spontaneous reactive infiltration of porous ceramic preforms with Al–Mg and Mg in the presence of both magnesium and nitrogen—new experimental evidence. Mater Manuf Process 17:307CrossRefGoogle Scholar
  19. 19.
    Mortensen A (2000) Melt infiltration of metal matrix composites. Compr Compos Mater 3:521–554CrossRefGoogle Scholar
  20. 20.
    Srivatsan T, Al-Hajri M (2002) The fatigue and final fracture behavior of SiC particle reinforced 7034 aluminum matrix composites. Compos Part B Eng 33(5):391–404CrossRefGoogle Scholar
  21. 21.
    Srivatsan T, Al-Hajri M, Petraroli M, Hotton B, Lam P (2002) Influence of silicon carbide particulate reinforcement on quasi static and cyclic fatigue fracture behavior of 6061 aluminum alloy composites. Mater Sci Eng, A 325(1):202–214CrossRefGoogle Scholar
  22. 22.
    Unlu BS (2008) Investigation of tribological and mechanical properties Al2O3eSiC reinforced Al composites manufactured by casting or P/M method. Investig Mater Des 29:2002–2008Google Scholar
  23. 23.
    Shaha SK, Czerwinski F, Kasprzak W, Friedman J, Chen DL (2015) Improving high temperature tensile and low-cycle fatigue behavior of Al–Si–Cu–Mg alloys through micro-additions of Ti, V and Zr. Metall Mater Trans A 46A:3063–3078CrossRefGoogle Scholar
  24. 24.
    Davidson CJ, Griffiths JR, Machin AS (2002) The effect of solution heat-treatment time on the fatigue properties of an Al–Si–Mg casting alloy. Fatigue Fract Eng Mater 25:223–230CrossRefGoogle Scholar
  25. 25.
    Sharmaa NK, Misra RK, Sharma S (2016) Modeling of thermal expansion behavior of densely packed Al/SiC composites. Int J Solids Struct 102–103:777–788Google Scholar
  26. 26.
    Shaga A, Shen P, Guo RF, Jiang QC (2016) Effects of oxide addition on the microstructure and mechanical properties of lamellar SiC scaffolds and Al–Si–Mg/SiC composites prepared by freeze casting and pressureless infiltration. Ceram Int 42:9653–9659CrossRefGoogle Scholar
  27. 27.
    Sharifi H, Ostovan K, Tayebi M, Rajaee A (2017) Dry sliding wear behavior of open-cell Al–Mg/Al2O3 and Al–Mg/SiC–Al2O3 composite preforms produced by a pressureless infiltration technique. Tribol Int 116:244–255CrossRefGoogle Scholar
  28. 28.
    Kumar S, Chakraborty M, Sarma VS, Murty BS (2005) Tensile and wear behavior of in situ Al–7Si/TiB2 particulate composites. Wear 265:134–142CrossRefGoogle Scholar
  29. 29.
    Gundrum BC, Cahill DG, Averback RS (2005) Thermal conductance of metal–metal interfaces. Phys Rev B Condens Matter Mater 72(24):245426/1–245426/5CrossRefGoogle Scholar
  30. 30.
    Haykin S (1994) Neural networks. Macmillan College Publishing Company, New York, p 138zbMATHGoogle Scholar
  31. 31.
    Atrian A, Majzoobi GM, Nourbakhsh SH, Galehdari SA, Nejad RM (2016) Evaluation of tensile strength of Al7075–SiC nanocomposite compacted by gas gun using spherical indentation test and neural networks. Adv Powder Technol 27:1821–1827CrossRefGoogle Scholar
  32. 32.
    Rashed FS, Mahmoud TS (2009) Prediction of wear behaviour of A356/SiCp MMCs using neural networks. Tribol Int 42(5):642–648CrossRefGoogle Scholar
  33. 33.
    Hayajneh M, Hassan AM, Alrashdan A, Mayyas AT (2009) Prediction of tribological behavior of aluminum–copper based composite using artificial neural network. J Alloy Compd 470:584–588CrossRefGoogle Scholar
  34. 34.
    Jalham IS (2003) Modeling capability of the artificial neural network (ANN) to predict the effect of the hot deformation parameters on the strength of Al-base metal matrix composites. Compos Sci Technol 63:63–67CrossRefGoogle Scholar
  35. 35.
    Dashtbayazi MR (2012) Artificial neural network based multi-objective optimization of mechanical alloying process for synthesizing of metal matrix nanocomposite powder. Artif Mater Manuf Process 27(1):333–342Google Scholar
  36. 36.
    Tofigh AA, Rahimipour MR, Shabani MO, Davami P (2015) Application of the combined neuro-computing, fuzzy logic and swarm intelligence for optimization of compocast nanocomposites. J Compos Mater 49(13):1653–1663CrossRefGoogle Scholar
  37. 37.
    Shabani MO, Mohammad Reza Rahimipour MR, Tofigh AA, Davami P (2015) Refined microstructure of compo cast nanocomposites: the performance of combined neuro-computing, fuzzy logic and particle swarm techniques. Neural Comput Appl 26:899–909CrossRefGoogle Scholar
  38. 38.
    Tofigh AA, Shabani MO (2013) Efficient optimum solution for high strength Al alloys matrix composites. Ceram Int 39:7483–7490CrossRefGoogle Scholar
  39. 39.
    Shamsipour M, Pahlevani Z, Shabani MO, Mazahery A (2016) Optimization of the EMS process parameters in compocasting of high-wear-resistant Al-nano-TiC composites. Appl Phys A 122:456–457CrossRefGoogle Scholar
  40. 40.
    Rahimipour MR, Tofigh AA, Mazahery A, Shabani MO (2014) Strategic developments to improve the optimization performance with efficient optimum solution and produce high wear resistance aluminum–copper alloy matrix composites. Neural Comput Appl 24:1531–1538CrossRefGoogle Scholar
  41. 41.
    Mazahery A, Shabani MO, Elrefaei A (2014) Searching for the superior solution to the population-based optimization problem: processing of the wear resistant commercial AA6061 AMCs. Int J Damage Mech 23(7):899–916CrossRefGoogle Scholar
  42. 42.
    Shamsipour M, Pahlevani Z, Shabani MO, Mazahery A (2017) Squeeze casting of electromagnetically stirred aluminum matrix nanocomposites in semi-solid condition using hybrid algorithm optimized parameters. Kovove Mater 55:33–43Google Scholar
  43. 43.
    Shabani MO, Shamsipour M, Mazahery A, Pahlevani Z (2018) Performance of ANFIS coupled with PSO in manufacturing superior wear resistant aluminum matrix nano composites. Trans Indian Inst Met 71(9):2095–2103CrossRefGoogle Scholar
  44. 44.
    Scudino S, Liu G, Prashanth KG, Bartusch K et al (2009) Mechanical properties of Al based metal matrix composites reinforced with Zr based glassy particles produced by powder metallurgy. Acta Mater 57:2029–2039CrossRefGoogle Scholar
  45. 45.
    Abdizadeh H (2002) Investigation on mechanical properties and fracture behavior of A356 Al alloy based ZrO2 particle reinforced metal matrix composites. Ceram Int 39:2045–2050CrossRefGoogle Scholar
  46. 46.
    Das B, Roy S, Raic RN, Saha SC (2015) Studies on effect of cutting parameters on surface roughness of AlCu–TiC MMCs an artificial neural network approach. Procedia Comput Sci 45:745–752CrossRefGoogle Scholar
  47. 47.
    Aleksendric D, Duboka C (2006) Prediction of automotive friction material characteristics using artificial neural networks-cold performance. Wear 261(3–4):269–282CrossRefGoogle Scholar
  48. 48.
    Xu L, Ji J, Davim P, Cardoso R (2007) Prediction on tribological behaviour of composite PEEK-CF30 using artificial neural networks. J Mater Process Technol 189(1–3):374–378Google Scholar
  49. 49.
    Abdelhay AM (2002) Application of artificial neural networks to predict the carbon content and the grain size for carbon steels. Egypt J Solids 25(2):229–243Google Scholar
  50. 50.
    Ciarapica FE, Giacchetta G (2006) Managing the condition-based maintenance of a combined-cycle power plant: an approach using soft computing techniques. J Loss Prev Process Ind 19:316–325CrossRefGoogle Scholar
  51. 51.
    Hassan AM, Alrashdan A, Hayajneh M, Mayyas AT (2009) Prediction of density, porosity and hardness in aluminum–copper-based composite materials using artificial neural network. J Mater Process Technol 209:894–899CrossRefGoogle Scholar
  52. 52.
    Gürgen S, Ünver B, Altin İ (2008) Prediction of cyclic variability in a diesel engine fueled with n-butanol and diesel fuel blends using artificial neural network. Renew Energy 117:538–544CrossRefGoogle Scholar
  53. 53.
    Akdag U, Komur MA, Ozguc AF (2009) Estimation of heat transfer in oscillating annular flow using artificial neural networks. Adv Eng Softw 40:864–870CrossRefGoogle Scholar
  54. 54.
    Kentel E (2009) Estimation of river flow by artificial neural networks and identification of input vectors susceptible to producing unreliable flow estimates. J Hydrol 375:481–488CrossRefGoogle Scholar
  55. 55.
    Bishop CM (1994) Neural networks and their applications. Rev Sci Instrum 65(6):1803–1830CrossRefGoogle Scholar
  56. 56.
    Chamjangali MA, Beglari M, Bagherian G (2007) Prediction of cytotoxicity data (CC50) of anti-HIV 5-pheny-l-phenylamino-1H-imidazole derivatives by artificial neural network trained with Levenberg–Marquardt algorithm. J Mol Graph Model 26:360–367CrossRefGoogle Scholar

Copyright information

© The Brazilian Society of Mechanical Sciences and Engineering 2018

Authors and Affiliations

  1. 1.Department of Machine and Metal Technologies, Hendek Vocational SchoolSakarya Applied Sciences UniversityHendekTurkey

Personalised recommendations