In this work, the effect of four factors including the nanoclay (NC) content, polyamide 6 (PA-6) content, compatibilizer type, and amount, as material variables on barrier properties of different high-density polyethylene (HDPE)/PA-6/clay nanocomposites, was described. Response surface method was used as a tool for experimental design. Different PA-6/clay nanocomposites were prepared by melt mixing of PA-6 at different clay loadings using a corotating twin-screw extruder. Subsequently, different PA-6/NC compounds containing different amounts of clay were melt mixed with HDPE to produce blow-molded containers under fixed processing conditions. In order to model the permeability, a neural network modelling approach in combination with a modified version of differential evolution was employed. The differential evolution modifications included, among others, a local search procedure based on backpropagation. The best models determined had a mean squared error in the testing phase of less than 0.1 and an average relative error lower than 12.2%, the difference between experimental results and predictions being within an acceptable range. This indicates that the methodology used was able to efficiently model the considered process.
MoghriMGarmabiHMolajavadiV. Correlation of morphology, rheology, and performance improvement in gasoline tubes based on PA-6 nanocomposites. J Vinyl Additive Technol2010; 16: 195–203.
2.
ChoudalakisGGotsisAD. Permeability of polymer/clay nanocomposites: a review. Eur Polym J2009; 45: 967–984.
3.
RhimJW. Effect of clay contents on mechanical and water vapor barrier properties of agar-based nanocomposite films. Carbohydr Polym2011; 86: 691–699.
4.
MoghriMGarmabiH. Investigation of the effects of formulation and processing parameters on properties of PA 6 nanocomposites using Taguchi method of experimental design. Int Polym Proc2008; 23: 430–438.
5.
KelnarIKapralkovaLKratochvilJ. Effect of nanofiller on the behavior of a melt−drawn HDPE/PA6 microfibrillar composite. J Appl Polym Sci2015; 132: 41868.
6.
FornesTDPaulDR. Modeling properties of nylon 6/clay nanocomposites using composite theories. Polymer2003; 44: 4993–5013.
7.
FornesTDYoonPJHunterDL. Effect of organoclay structure on nylon 6 nanocomposite morphology and properties. Polymer2002; 43: 5915–5933.
8.
BhattacharyaSNKamalMR,GuptaRK. Polymeric nanocomposites: theory and practice. Munich: Carl Hanser Publishers, 2008.
9.
RaySSOkamotoM. Polymer/layered silicate nanocomposites: a review from preparation to processing. Prog Polym Sci2003; 28: 1539–1641.
10.
ShahabadiSISGarmabiH. Response surface analysis of structural, mechanical, and permeability properties of polyethylene/Na+-montmorillonite composites, prepared by slurry-fed melt intercalation. Express Polym Lett2012; 6: 657–671.
11.
ErdmannEDiasMLPitaVJ. Characterization of HDPE/polyamide 6/nanocomposites using scanning-and transmission electron microscopy. Hoboken: Wiley-Blackwell, 2007, pp. 82–89.
12.
ChavarriaFShahRKHunterDL. Effect of melt processing conditions on the morphology and properties of nylon 6 nanocomposites. Polym Eng Sci2007; 47: 1847–1864.
13.
ZhangMLinB,SundararajU. Effects of processing sequence on clay dispersion, phase morphology, and thermal and rheological behaviors of PA6−clay nanocomposites. J Appl Polym Sci2012; 125: E714–E724.
14.
FasihiMAbolghasemiMR. Oxygen barrier and mechanical properties of masterbatch based PA6/nanoclay composite films. J Appl Polym Sci2012; 125: E2–E8.
15.
FangZXuY,TongL. Effect of clay on the morphology of binary blends of polyamide 6 with high density polyethylene and HDPE−graft−acrylic acid. Polym Eng Sci2007; 47: 551–559.
16.
BhattacharyyaAChatterjeeSDuttaS. Removal and recovery of lead (II) from simulated solution using alginate immobilized papain (AIP). Environl Eng Manag J2014; 13: 835–846.
17.
de CassiaFSda SilvaRRufinoRD. Enhancement of biosurfactant production from Pseudomonas cepacia CCT6659 through optimisation of nutritional parameters using response surface methodology. Tenside Surfact Det2013; 50: 137–142.
18.
HafiziAAhmadpourAKoolivand-SalookiM. Comparison of RSM and ANN for the investigation of linear alkylbenzene synthesis over H 14 NaP 5 W 30 O 110]/SiO 2 catalyst. J Ind Eng Chem2013; 19: 1981–1989.
19.
SubudhiBJenaD. A differential evolution based neural network approach to nonlinear system identification. Appl Soft Comput2011; 11: 861–871.
20.
HimmelblauD. Applications of artificial neural networks in chemical engineering. Korean J Chem Eng2000; 17: 373–392.
21.
LahiriSKGhantaKC. Artificial neural network model with the parameter tuning assisted by a differential evolution technique: the study of the hold up of the slurry flow in a pipeline. Cheml Ind Chem Eng Quarterly2009; 15: 103–117.
22.
LobatoJCanizaresPRodrigoMA. The neural networks based modeling of a polybenzimidazole-based polymer electrolyte membrane fuel cell: effect of temperature. J Power Sources2009; 192: 190–194.
23.
ContantSMesaPVR,LonaLMF. Modeling of styrene living radical polymerization mediated by 2,2,6,6-tetramethyl-1-piper-idinoxyl (Tempo) using neural networks. In: 2nd Mercosur Congress on Chemical Engineering. 4th Mercosur Congress on Process System Engineering. Available athttp://www.enpromer2005.eq.ufrj.br/nukleo/pdfs/0204_lona_enpromer.pdf, 2005.
24.
CurteanuSLeonF. Hybrid neural network models applied to a free radical polymerization process. Polym Plastics Technol Eng2006; 45: 1013–1023.
25.
FarmakiEGThomaidisNS,EfstathiouCE. Artificial neural networks in water analysis: theory and applications. Int J Environ Analytical Chem2010; 90: 85–105.
26.
CurteanuSSudituGBuburuzanAM. Neural networks and differential evolution algorithm applied for modelling the depollution process of some gaseous streams. Environ Sci Pollut Res2014; 21(22): 12856–18567.
27.
DragoiENCurteanuSLeonF. Modeling of oxygen mass transfer in the presence of oxygen-vectors using neural networks developed by differential evolution algorithm. Eng Appl Artif Intell2011; 24: 1214–1226.
28.
DragoiENCurteanuSGalactionAI. Optimization methodology based on neural networks and self-adaptive differential evolution algorithm applied to an aerobic fermentation process. Appl Soft Comput2013; 13: 222–238.
29.
PirdashtiMMovagharnejadKCurteanuS. Prediction of partition coefficients of guanidine hydrochloride in PEG-phosphate systems using neural networks developed with differential evolution algorithm. J Ind Eng Chem2015; 27: 268–275.
30.
TalebniaFMighaniMRahimnejadM. Ethanol production from steam exploded rapeseed straw and the process simulation using artificial neural networks. Biotechnol Bioproc Engg2015; 20: 139–147.
31.
FernandesFAN. Selection of a mixture of initiators for batch polymerization using neural networks. J Appl Polym Sci2005; 98: 2088–2093.
32.
MarcollaRFMachadoRAFCancelierA. Modeling techniques and processes control application based on neural networks with on-line adjustment using genetic algorithms. Brazilian J Chem Eng2009; 26: 113–126.
33.
NoorRAMAhmadZDonMM. Modelling and control of different types of polymerization processes using neural networks technique: a review. Can J Chem Eng2010; 88: 1065–1084.
34.
CullarMPLapresta-FernandezAHerreraJM. Thermochromic sensor design based on Fe(II) spin crossover/polymers hybrid materials and artificial neural networks as a tool in modelling. Sensor Actuat B: Chem2015; 208: 180–187.
35.
MoritzerEMullerEMartinY. Artificial neural networks to model formulation-property correlations in the process of inline-compounding on an injection moulding machine. Cleveland: AIP Publishing, 2015 p. 110001.
36.
RodriguesAMFranceschiSPerezE. Formulation optimization for thermoplastic sizing polyetherimide dispersion by quantitative structure-property relationship: experiments and artificial neural networks. J Mater Sci2015; 50: 420–426.
37.
DennisHRHunterDLChangD. Effect of melt processing conditions on the extent of exfoliation in organoclay-based nanocomposites. Polymer2001; 42: 9513–9522.
FloreanoDDurrP,MattiussiC. Neuroevolution: from architectures to learning. Evol Intell2008; 1: 47–62.
40.
AbbassHA. A memetic pareto evolutionary approach to artificial neural networks. In: StumptnerMCorbettDBrooksM (eds) AI 2001: advances in artificial intelligence. 2256 ed. Berlin/Heidelberg: Springer, 2001, pp. 113–152.
41.
MontanaDVanWykEBrinnM. Evolution of internal dynamics for neural network nodes. Evol Intell2009; 1: 233–251.
42.
DragoiENCurteanuS,FissoreD. Freeze-drying modeling and monitoring using a new neuro-evolutive technique. Chem Eng Sci2012; 72: 195–204.
43.
RahnamayanSTizhooshH. Differential evolution via exploiting opposite populations. In: TizhooshHVentrescaM (eds) Oppositional concepts in computational intelligence. 155 ed. Berlin/Heidelberg: Springer, 2008, pp. 143–160.
44.
NomanNIbaH. Cellular differential evolution algorithm. In: LiJ (ed) AI 2010: Advances in artificial intelligence. 6464 ed. Berlin/Heidelberg: Springer, 2011, pp. 293–302.
45.
MininnoENeriF. Estimation distribution differential evolution. In: Di ChioCCagnoniSCottaC. (eds) Applications of evolutionary computation. 6024 ed. Berlin/Heidelberg: Springer, 2010, pp. 522–531.
46.
PriceKStornR,LampinenJ. Differential evolution. A practical approach to global optimization. Berlin: Springer, 2005.
