Machine Learning Approach to Predict Dielectric Permittivity of PE/TiO₂ Nanocomposites

Abstract:

Controlling process parameters has significant influence in designing and developing nanocomposites materials with tailored dielectric properties. In the present study, polyethylene/TiO₂ nanocomposites were fabricated using ball milling technique. The effects of TiO₂ nanoparticles on the final dielectric properties of the nanocomposites in frequency domain were investigated. The dielectric spectroscopy measurements revealed that relative dielectric permittivity of the nanocompsoites was increased with TiO₂ content. Besides, machine learning approach based on artificial neural networks (ANNs) algorithm was used to predict the dielectric permittivity of the nanocomposites materials. Modeling results showed clearly that the predicted data of the proposed artificial model are in good agreement with the experimental values. Moreover, the present study proved that ANNs can be used as successful tool to predict the dielectric properties of nanocomposites materials.

• Periodical: Materials Science Forum (Volume 998)
• Pages: 239-245
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.998.239
• Online since: June 2020
• Authors: Bouchaib Zazoum*
• Keywords: Artificial Neural Networks (ANNs), Ball Milling, Dielectric Properties, Nanocomposites, Polymer, TiO₂

References

[1] Matos M, Pinho S, Tagarielli V. Predictions of the electrical conductivity of composites of polymers and carbon nanotubes by an artificial neural network. Scripta Materialia. 2019; 166: 117-21.

DOI: 10.1016/j.scriptamat.2019.03.003

[2] Shi L, Lin S, Lu Y, Ye L, Zhang Y. Artificial neural network based mechanical and electrical property prediction of engineered cementitious composites. Construction and Building Materials. 2018;174:667-74.

DOI: 10.1016/j.conbuildmat.2018.04.127

[3] Hoyos M, Garcia N, Navarro R, Dardano A, Ratto A, Guastavino F, et al. Electrical strength in ramp voltage AC tests of LDPE and its nanocomposites with silica and fibrous and laminar silicates. Journal of Polymer Science Part B: Polymer Physics. 2008;46:1301-11.

DOI: 10.1002/polb.21464

[4] Ubale SB, Deshmukh SD, Ghosh S. Artificial Neural Network based Modelling of Wire Electrical Discharge Machining on Tungsten-Copper Composite. Materials Today: Proceedings. 2018;5:5655-63.

DOI: 10.1016/j.matpr.2017.12.159

[5] Osman M.A, Rupp JEP, Suter U.W. Tensile properties of polyethylene-layered silicate nanocomposites. Polymer. 2005;46:1653-60.

DOI: 10.1016/j.polymer.2004.11.112

[6] Zazoum B, David E, Ngô A. LDPE/HDPE/Clay Nanocomposites: Effects of Compatibilizer on the Structure and Dielectric Response. Journal of Nanotechnology. 2013;(2013).

DOI: 10.1155/2013/138457

[7] Guo Y, Jiang S, Grena BJ, Kimbrough IF, Thompson EG, Fink Y, et al. Polymer composite with carbon nanofibers aligned during thermal drawing as a microelectrode for chronic neural interfaces. ACS nano. 2017;11:6574-85.

DOI: 10.1021/acsnano.6b07550

[8] Utracki L, Kamal M. Clay-containing polymeric nanocomposites. Arabian Journal Science & Engineering--special issue. 2002;27:43-67.

[9] Sharif MA, Lei H, Al-Rubaiai MK, Tan X. Ionic polymer-metal composite torsional sensor: physics-based modeling and experimental validation. Smart Materials and Structures. 2018; 27: 075039.

DOI: 10.1088/1361-665x/aac364

[10] Kornmann X, Lindberg H, Berglund LA. Synthesis of epoxy–clay nanocomposites: influence of the nature of the clay on structure. Polymer. 2001;42:1303-10.

DOI: 10.1016/s0032-3861(00)00346-3

[11] David E, Fréchette M, Zazoum B, Daran-Daneau C, Ngô AD, Couderc H. Dielectric properties of PE/clay nanocomposites. Journal of Nanomaterials. 2013;(2013).

DOI: 10.1155/2013/703940

[12] Morais M, Oliva-Avilés A, Matos M, Tagarielli V, Pinho S, Hübner C, et al. On the effect of electric field application during the curing process on the electrical conductivity of single-walled carbon nanotubes–epoxy composites. Carbon. 2019;150:153-67.

DOI: 10.1016/j.carbon.2019.04.087

[13] Montazer E, Salami E, Yarmand H, Chowdhury ZZ, Dahari M, Kazi SN, et al. Development of a new density correlation for carbon-based nanofluids using response surface methodology. Journal of Thermal Analysis and Calorimetry. 2018;132:1399-407.

DOI: 10.1007/s10973-018-6978-4

[14] Khan W.S, Hamadneh N.N, Khan W.A. Prediction of thermal conductivity of polyvinylpyrrolidone (PVP) electrospun nanocomposite fibers using artificial neural network and prey-predator algorithm. PloS one. 2017;12:e0183920.

DOI: 10.1371/journal.pone.0183920

[15] Şahin Y, Sahin S, İnal M. Modelling of the Tensile Properties of Calcium Carbonate Filled Polypropylene Composite Materials with Taguchi and Artificial Neural Networks. IFAC-PapersOnLine. 2018;51:282-6.

DOI: 10.1016/j.ifacol.2018.11.302

[16] Esfahani NN, Toghraie D, Afrand M. A new correlation for predicting the thermal conductivity of ZnO–Ag (50%–50%)/water hybrid nanofluid: an experimental study. Powder Technology. 2018;323:367-73.

DOI: 10.1016/j.powtec.2017.10.025

[17] Vallejo-Giraldo C, Pugliese E, Larrañaga A, Fernandez-Yague MA, Britton JJ, Trotier A, et al. Polyhydroxyalkanoate/carbon nanotube nanocomposites: flexible electrically conducting elastomers for neural applications. Nanomedicine. 2016;11:2547-63.

DOI: 10.2217/nnm-2016-0075

[18] Yousefi F, Karimi H, Mohammadiyan S. Viscosity of carbon nanotube suspension using artificial neural networks with principal component analysis. Heat and Mass Transfer. 2016;52:2345-55.

DOI: 10.1007/s00231-015-1745-6

[19] Zhang Z, Friedrich K. Artificial neural networks applied to polymer composites: a review. Composites science and technology. 2003; 63:2029-44.

DOI: 10.1016/s0266-3538(03)00106-4

[20] Wallace GG, Teasdale PR, Spinks GM, Kane-Maguire LA. Conductive electroactive polymers: intelligent polymer systems: CRC press; (2008).

DOI: 10.1201/9781420067156

[21] Bezerra E, Ancelotti A, Pardini L, Rocco J, Iha K, Ribeiro C. Artificial neural networks applied to epoxy composites reinforced with carbon and E-glass fibers: Analysis of the shear mechanical properties. Materials Science and Engineering: A. 2007; 464:177-85.

DOI: 10.1016/j.msea.2007.01.131

[22] Lefik M, Boso D, Schrefler B. Artificial neural networks in numerical modelling of composites. Computer Methods in Applied Mechanics and Engineering. 2009;198:1785-804.

DOI: 10.1016/j.cma.2008.12.036

[23] Marquardt DW. An algorithm for least-squares estimation of nonlinear parameters. Journal of the society for Industrial and Applied Mathematics. 1963; 11:431-41.

DOI: 10.1137/0111030

[24] Vogl TP, Mangis J, Rigler A, Zink W, Alkon D. Accelerating the convergence of the back-propagation method. Biological cybernetics. 1988;59:257-63.

DOI: 10.1007/bf00332914

[25] Rojas R. Neural Networks-A Systematic Introduction Springer-Verlag. New York. (1996).

[26] Pater L. Application of artificial neural networks and genetic algorithms for crude fractional distillation process modeling. arXiv preprint arXiv:160500097. (2016).

[27] Laredo E, Grimau M, Sanchez F, Bello A. Water absorption effect on the dynamic properties of nylon-6 by dielectric spectroscopy. Macromolecules. 2003; 36: 9840-50.

DOI: 10.1021/ma034954w