Professional Documents
Culture Documents
2020 Mohammad A Alam JMRT Sintered Composite RSM ANN
2020 Mohammad A Alam JMRT Sintered Composite RSM ANN
2 0 2 0;9(6):14036–14050
https://www.journals.elsevier.com/journal-of-materials-research-and-technology
Original Article
Mohammad Azad Alam a,∗ , Hamdan H. Ya a , Mohammad Azeem a , Patthi Bin Hussain a ,
Mohd Sapuan bin Salit b , Rehan Khan a , Sajjad Arif c , Akhter Husain Ansari c
a Mechanical Engineering Department, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak, Malaysia
b Laboratory of Biocomposite Technology, Institute of Tropical Forestry and Forest Products, Universiti Putra Malaysia, 43400 UPM
Serdang, Selangor, Malaysia
c Department of Mechanical Engineering, Aligarh Muslim University, Aligarh 202002, India
a r t i c l e i n f o a b s t r a c t
Article history: In present work, Aluminium matrix composites reinforced with x wt.% SiC (x = 5, 7.5 and
Received 13 July 2020 10) microparticles were synthesised by powder metallurgy route. The microhardness (VHN)
Accepted 24 September 2020 of the Al/SiC composites were investigated using Response Surface Methodology (RSM)
Available online 9 October 2020 and artificial neural network (ANN) approach. Scanning electron microscopy (SEM), Energy-
dispersive X-ray spectroscopy (EDS), Elemental mapping and Optical microscopy were done
Keywords: for the microstructural investigations. The X-ray diffraction (XRD) analysis was done for
Al–SiC composites received powders and composites samples for phase recognition and existence of rein-
Powder metallurgy forcement particles (SiC) in the synthesised sintered composites. The design of experiments
Vickers Microhardness based on RSM was utilised following the central composite design method. Empirical models
Response surface methodology have been developed by considering variance analysis (ANOVA), to establish relationships
Artificial neural networks among the control factors and the response variables. A feed-forward back-propagation neu-
ral network (FF-BPNN) was used to determine the qualitative characteristics of the process,
and the accuracy of the BPNN system was attributed with mathematical models based on
RSM model. The ANN model predicted surface hardness values are near the experimental
findings. It is established that the developed models can be used to predict the hardness of
the surface within the investigation range. The composite with reinforcement 7.5% revealed
higher sintered density and Vickers microhardness due to the uniform distribution of filler
particles in the Al matrix featuring no pores. The results indicate overall higher accuracy in
the ANN method than RSM model.
© 2020 The Author(s). Published by Elsevier B.V. This is an open access article under the
CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Abbreviations: ANN, artificial neural network; RSM, response surface methodology; R2, determination coefficient; ANOVA, Analysis of
Variance; FFBPN, Feed-Forward Backpropagation Network; RMSE, Root Mean Square Error; MAPE, Mean Absolute Percentage Error; XRD,
X-ray diffraction; AMCs, Aluminium matrix composites.
∗
Corresponding author.
E-mail: azadalam.mech3@gmail.com (M.A. Alam).
https://doi.org/10.1016/j.jmrt.2020.09.087
2238-7854/© 2020 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://
creativecommons.org/licenses/by-nc-nd/4.0/).
j m a t e r r e s t e c h n o l . 2 0 2 0;9(6):14036–14050 14037
2.2. Blending of powders observing the patterns of received Al, reinforcement SiC and
synthesised composites. Utilising EDS elemental mapping, the
The various weight percentages (5, 7.5 and 10.0 wt.%) of SiC degree of uniformity of composites and the dispersion of filler
reinforced Al composite powders were prepared using a cen- material was observed.
trifugal ball mill made by FRITSCH, Germany. The speed of
rotation and the ball to powder ratio (BPR) were 150 rpm and 2.4.2. Optical microscopy
10:1, respectively. The microstructure of all the sintered composite samples was
observed through an optical microscope (Model: Leica DM LM,
2.3. Compaction and controlled environment sintering Wetzlar, Germany) following the preparation of the metallog-
raphy. It was used to investigate the impact of reinforcement
The blended powders were compacted into 8 mm diameter, particles on the microstructural evolution of the composites
and 12 mm long cylindrical pellets utilising uniaxial com- system. The polished and etched sections of the sintered
paction dies in a hydraulic pallet press (Kimaya Engineers, composites were exposed for the optical micrographic obser-
India), at a compaction pressure of 450 Mpa. Zinc-stearate was vations, homogenisation of the grain size is observed after
applied over the die wall before each compaction for reducing addition of SiC particles.
the frictional effects at the die wall. Under a controlled envi-
ronment, the green pellets had been sintered in an electric 2.5. Density measurement
tubular furnace with flow regulator at temperatures of 500, 550
and 600 ◦ C for 2 h. Sintering was accomplished under a steady For all the specimens of Al and composites, the experimental
supply of argon gas at a flow rate = 1 litre/min. To avoid oxida- sintered densities have been measured using the principle of
tion of the synthesised composites [25]. The sintered pellets Archimedes’ by standard test method (ASTM B0311-93R02E01).
were cooled down to ambient temperature within the furnace. For measurement of the density of the composites, HR-250
AZ analytical balance developed by A&D Company, Limited,
2.4. Characterisation Tokyo, Japan was used. The figure of the analytical balance
used is given in the supplementary data file (Fig. 4). Four sam-
2.4.1. X-ray diffraction ples were measured for each formulation, and the mean value
XRD of received powders and synthesised composites was of the sintered density has been reported.
done utilising X-ray Diffractometer (D8 ADVANCE, Bruker AXS
Inc., USA) to confirm the existence of reinforcement parti- 2.6. Microhardness measurement
cles (SiC). The diffractometer had been monitored employing
CuKa radiation (k = 1.5406 Å) with 40 kV operational voltage The microhardness of all the sintered composites samples was
and 40 mA current. XRD data was gathered at a sluggish scan- measured according to the standard test method (ASTM E92-
ning rate of 0.02 steps/second for meticulous estimation of 82) by Vickers hardness tester at a load of 300 gf keeping dwell
existing phases. The scan range was 20◦ –80◦ in 0.01◦ steps. time 25s. In the hardness test, the possible experimental error
The comparative analysis of XRD spectra was too executed by was below 5%. The test was conducted at room temperature
Fig. 1 – SEM micrograph of received powder (a) Aluminium particles, (b) SiC particles.
Fig. 2 – EDS spectrum of powder samples (a) Al, and (b) SiC.
(25 ◦ C), hardness measurement was noted four times for each model can be developed efficiently. To enable the estimate
test sample at different locations, and the mean values were of control parameters of a second-order model, CCD designs
taken into consideration for microhardness. are strengthened by the extra centre and axial points. The
input parameters/factors were SiC concentrations and sinter-
2.7. Experimental design ing temperature, Table 1 shows the process parameters with
lower and higher levels.
The central composite design (CCD) approach was used for the The output parameters/response variables were density
model development in RSM to examine both the individual and microhardness, as shown in Table 2. The descriptions
and interaction effect on hardness of the synthesised com- of the design matrix of the factors in the particular units
posites under multivariable (SiC concentrations and sintering used in the surface response system, together with the hard-
temperatures) conditions. The objective of applying CCD to ness and density responses were observed and depicted in
the variables used in the present work is that the 2nd order Table 2.
14040 j m a t e r r e s t e c h n o l . 2 0 2 0;9(6):14036–14050
Fig. 3 – XRD patterns of (a) Al powder, (b) SiC powder, depicting various phase peaks.
Fig. 6 – Optical microscopy observations of (a) Aluminium, (b) Al + 5% SiC, (c) Al+ 7.5% SiC and (d) Al + 10%SiC.
14042 j m a t e r r e s t e c h n o l . 2 0 2 0;9(6):14036–14050
The RSM models for sintered density and hardness were devel-
oped by utilising experimental results using design expert
software version 12. A complete quadratic model comprising
of the terms linear, square and interaction were developed.
The equation of the developed model for comparing the
responses (Hardness and sintered density) to input variables
A and B using design expert software can be expressed as
follows:
Let A = Reinforcement (SiC) concentrations (wt.%),
B = Sintering temperature (◦ C) as mentioned in Table 1.
Fig. 10 – 3D contour plot of SiC concentration and sintering temperature on hardness response.
14044 j m a t e r r e s t e c h n o l . 2 0 2 0;9(6):14036–14050
Bold values indicates the most feasible model suggested by RSM tool i.e Qudratic out of four models mentioned in the table 4.
The bold values indicates the best possible solution with highest value of hardness and desirability among the two solutions.
14046 j m a t e r r e s t e c h n o l . 2 0 2 0;9(6):14036–14050
Fig. 16 – Predictive regression graphs for training, validation, and testing of the developed network.
RSM ANN
2
R 0.8957 0.9868
RMSE 1.729 1.035
MAPE 0.490 0.060
Fig. 17 – Performance curve of the developed model (Mean RSM and ANN are prediction tools capable of solving multi-
squared error (MSE) Vs. number of epochs. variate linear and nonlinear correlation problems. From the
prior studies, RSM and ANN have been a powerful tool for
the estimation of process variables for the manufacturing of
ment is shown in Fig. 17. The best validation performance composite materials[24,39]. These models have been used to
was achieved at 379 epochs, and developed network attains identify the impact of input parameters on output variables
accuracy even at a lower value of epochs. and also to describe the relations between variables. Differ-
14048 j m a t e r r e s t e c h n o l . 2 0 2 0;9(6):14036–14050
The present research work investigates the synthesis, Declaration of Competing Interest
microstructural characterisations, hardness behaviour of the
Al-x wt.% SiC (x = 5, 7.5 and 10 wt.%) sintered composites syn- The authors report no declarations of interest.
thesised by powder metallurgy technique. RSM technique was
used for the design of experiments, modelling and optimi-
sation of process variables. Further, ANN prediction of the Acknowledgements
hardness and density for Al/SiC composites were done and
resembled the results achieved by the RSM techniques. From The authors admiringly acknowledge the support of Mechan-
this investigation, the following major conclusions are drawn. ical Engineering Department, Universiti Teknologi Petronas,
Malaysia for granting PhD Scholarship under GA scheme,
(1) The SiC micron particles were encapsulated and evenly and authors also would like to thank Mechanical Engineer-
distributed in the Al matrix, which was verified by ele- ing Department (ZHCET, Aligarh Muslim University, Aligarh,
mental mapping and optical microscopy. The effect of India) for providing necessary facilities for experiments and
SiC addition on the Vickers microhardness of the synthe- Advanced Engineering Materials and Composites Research
sised composites results in the increment with increasing Centre (AEMC), Department of Mechanical and Manufacturing
SiC particles. The hardness of the composites was higher Engineering, Universiti Putra, Malaysia for informative sup-
than the base Al in all compositions. XRD and optical port throughout the work.
microscopy analyses verified the presence of SiC particles
in Al composites microstructures. references
(2) The composites with 7.5 wt.% reinforcement (SiC) content
and 550 ◦ C sintering temperature reveal the highest Vick-
ers hardness 59.68 VHN. Further incorporation of SiC leads [1] Verma N, Vettivel SC. Characterisation and experimental
to a reduction in composites hardness due to the agglom- analysis of boron carbide and rice husk ash reinforced
j m a t e r r e s t e c h n o l . 2 0 2 0;9(6):14036–14050 14049
AA7075 aluminium alloy hybrid composite. J Alloys Compd [21] Kannaiyan M, Karthikeyan G, Thankachi Raghuvaran JG.
2018;741:981–98. Prediction of specific wear rate for LM25/ZrO2 composites
[2] Fernández H, Ordoñez S, Pesenti H, González RE, Leoni M. using Levenberg-Marquardt back-propagation algorithm. J
Microstructure homogeneity of milled aluminum Mater Res Technol 2020;9:530–8.
A356-Si3N4 metal matrix composite powders. J Mater Res [22] Kurt HI, Oduncuoglu M, Yilmaz NF, Ergul E. A Comparative
Technol 2019;8:2969–77. Study on the Effect of Welding Parameters of Austenitic
[3] Surya MS, Prasanthi G. Manufacturing, microstructural and Stainless Steels Using Artificial Neural Network and Taguchi
mechanical characterisation of powder metallurgy processed Approaches with ANOVA Analysis 1845.
Al7075/SiC metal matrix composite. Mater Today Proc 2020. [23] Dinaharan I, Palanivel R, Murugan N, Laubscher RF.
[4] Halil K, Ismail OI, Sibel D, Ramazan Çi. Wear and mechanical Application of artificial neural network in predicting the
properties of Al6061/SiC/B4C hybrid composites produced wear rate of copper surface composites produced using
with powder metallurgy. J Mater Res Technol 2019;8:5348–61. friction stir processing. Aust J Mech Eng 2020:1–12.
[5] Şenel MC, Gürbüz M, Koç E. Fabrication and characterisation [24] Kumar R, Chauhan S. Study on surface roughness
of synergistic Al-SiC-GNPs hybrid composites. Compos Part B measurement for turning of Al 7075/10/SiCp and Al 7075
Eng 2018;154:1–9. hybrid composites by using response surface methodology
[6] Şenel MC, Gürbüz M, Koç E. New generation composites with (RSM) and artificial neural networking (ANN). Meas J Int
graphene reinforced aluminium matrix. Eng Mach Meas Confed 2015;65:166–80.
2015;56:36–47. [25] Arif S, Alam T, Ansari AH, Bilal M, Shaikh N. Morphological
[7] Hafizpour HR, Sanjari M, Simchi A. Analysis of the effect of characterisation, statistical modelling and tribological
reinforcement particles on the compressibility of Al-SiC behaviour of aluminum hybrid nanocomposites reinforced
composite powders using a neural network model. Mater with micro- nano-silicon carbide. J Asian Ceram Soc
Des 2009;30:1518–23. 2019;00:1–15.
[8] Mohit H, Arul Mozhi Selvan V. Optimization of the tensile [26] Ravindran P, Manisekar K, Rathika P, Narayanasamy P.
strength of sintered Al6061/SiC nanocomposites using Tribological properties of powder metallurgy–processed
response surface methodology. Mater Today Proc 2020. aluminium self lubricating hybrid composites with SiC
[9] Almotairy SM, Boostani AF, Hassani M, Wei D, Jiang ZY. Effect additions. Mater Des 2013;45:561–70.
of hot isostatic pressing on the mechanical properties of [27] Reddy MP, Shakoor RA, Parande G, Manakari V, Ubaid F,
aluminium metal matrix nanocomposites produced by dual Mohamed AMA, et al. Progress in natural science: materials
speed ball milling. J Mater Res Technol 2020;9:1151–61. international enhanced performance of nano-sized SiC
[10] Nassar AE, Nassar EE. Properties of aluminium matrix Nano reinforced Al metal matrix nanocomposites synthesised
composites prepared by powder metallurgy processing. J through microwave sintering and hot extrusion techniques.
King Saud Univ – Eng Sci 2017;29:295–9. Prog Nat Sci Mater Int 2017;27:606–14.
[11] Xie MX, Li YX, Shang XT, Wang XW, Pei JY. Microstructure and [28] Aziz EIA. Characterisation of the microstructure and
mechanical properties of a fiber welded socket-joint made of mechanical properties of Al/SiC composite produced by FSP
powder metallurgy molybdenum alloy. Metals 2019;9:640. technique, vol. 9; 2019. p. 28–33.
[12] Khuri AI, Mukhopadhyay S. Response surface methodology. [29] Bisht A, Srivastava M, Kumar RM, Lahiri I, Lahiri D.
Wiley Interdiscip Rev Comput Stat 2010;2:128–49. Strengthening mechanism in graphene nanoplatelets
[13] Sharma VK, Kumar V, Joshi RS. Parametric study of reinforced aluminum composite fabricated through spark
aluminium-rare earth based composites with improved plasma sintering. Mater Sci Eng A 2017;695:20–8.
hydrophobicity using response surface method. J Mater Res [30] El-kady O, Fathy A. Effect of SiC particle size on the physical
Technol 2020;9:4919–32. and mechanical properties of extruded Al matrix
[14] Kumar SS, Erdemir F, Varol T, Kumaran ST, Uthayakumar M, nanocomposites. Mater Des 2014;54:348–53.
Canakci A. Investigation of WEDM process parameters of [31] Khdair AI, Fathy A. Enhanced strength and ductility of Al-SiC
Al–SiC–B4C composites using response surface methodology. nanocomposites synthesised by accumulative roll. Integr
Int J Light Mater Manuf 2019. Med Res 2019;9:478–89.
[15] Khajelakzay M, Bakhshi SR. Optimization of spark plasma [32] Rahimi MH, Shayganmanesh M, Noorossana R, Pazhuheian
sintering parameters of Si3N4-SiC composite using response F. Modelling and optimisation of laser engraving qualitative
surface methodology (RSM). Ceram Int 2017;43:6815–21. characteristics of Al-SiC composite using response surface
[16] Sardar S, Pradhan SK, Karmakar SK, Das D. Modeling of methodology and artificial neural networks. Opt Laser
abraded surface roughness and wear resistance of Technol 2019;112:65–76.
aluminum matrix composites. J Tribol 2019;141:25–9. [33] Gopalakannan S, Senthilvelan T. Application of response
[17] Daniel G. Principles of artificial neural networks, vol. 7. surface method on machining of Al–SiC nano-composites.
World Scientific; 2013. Measurement 2013;46:2705–15.
[18] Hafeez A, Ammar Taqvi SA, Fazal T, Javed F, Khan Z, Amjad [34] Varol T, Canakci A, Ozsahin S. Artificial neural network
US, et al. Optimisation on cleaner intensification of ozone modeling to effect of reinforcement properties on the
production using Artificial Neural Network and Response physical and mechanical properties of Al2024-B4C
Surface Methodology: parametric and comparative study. J composites produced by powder metallurgy. Compos Part B
Clean Prod 2020;252:119833. Eng 2013;54:224–33.
[19] Roohi R, Jafari M, Jahantab E, Aman MS, Moameri M, Zare S. [35] Arif S, Alam MT, Ansari AH, Shaikh MBN, Siddiqui MA.
Application of artificial neural network model for the Analysis of tribological behaviour of zirconia reinforced
identification the effect of municipal waste compost and Al-SiC hybrid composites using statistical and artificial
biochar on phytoremediation of contaminated soils. J neural network technique. Mater Res Express 2018;5:56506.
Geochem Explor 2020;208:106399. [36] Mahanta S, Chandrasekaran M, Samanta S, Arunachalam R.
[20] Negassi M, Suarez-Ibarrola R, Hein S, Miernik A, Reiterer A. Multi-response ANN modelling and analysis on sliding wear
Application of artificial neural networks for automated behavior of Al7075/B4C/fly ash hybrid nanocomposites.
analysis of cystoscopic images: a review of the current status Mater Res Express 2019;6:0850h4.
and future prospects. World J Urol 2020:1–10.
14050 j m a t e r r e s t e c h n o l . 2 0 2 0;9(6):14036–14050
[37] Muthukrishnan N, Davim JP. Optimisation of machining analysis on solid particle erosion behavior of polymer matrix
parameters of Al/SiC-MMC with ANOVA and ANN analysis. J composites. Materials (Basel) 2020;13.
Mater Process Technol 2009;209:225–32. [40] Nwobi-Okoye CC, Ochieze BQ. Age hardening process
[38] Shaikh MBN, Raja S, Ahmed M, Zubair M, Khan A, Ali M. Rice modeling and optimisation of aluminum alloy A356/Cow
husk ash reinforced aluminium matrix composites: horn particulate composite for brake drum application using
fabrication, characterisation, statistical analysis and artificial RSM, ANN and simulated annealing. Def Technol
neural network modelling. Mater Res Express 2019;6:056518. 2018;14:336–45.
[39] Antil SK, Antil P, Singh S, Kumar A, Pruncu CI. Artificial
neural network and response surface methodology based