Artificial Neural Network Modelling of PP/PET Blends

Year 2018, Volume: 2 Issue: 2, 77 - 82, 30.06.2018

Murat Beken , Fatma Çavuş Kosovalı Yeşim Özcanlı

Abstract

In this study, comparison between the dynamic mechanical properties of polymer blends and the results of artificial neural networks (ANN) modeling has been conducted. The glass transition temperature and storage modulus values of PP(polypropylene)/PET(polypropylene terephthalate) polymer blends was used for ANN modelling. The observations on ANN results and the experimental results has shown sufficient accuracy mutually. At the same time, these results were supported by scanning analyzes. The artificial intelligence modeling studies for this article proves the applicability of dynamic mechanical properties of PP/PET blends. These results shows that artificial neural networks can be a helpful tool for experimental work of dynamic mechanical properties of polymer materials.

Keywords

PP/PET blends, dynamical mechanical properties, artificial neural network

References

• Sargolzaei, B. Ahangari, Thermal behavior prediction of mdpe nanocomposite/cloisite Na + using artificial neural network and neuro-fuzzy tools, Journal of Nanotechnology in Engineering and Medicine Vol. 1, No. 4, October 2010.
• X. Si, L. Guo, et. al, preparation and study of polypropylene/polyethylene terephthalate composite fibres, Composites Science and Technology, Vol. 68, pp. 2943-2947, November 2008.
• Y. X. Pang, D. M. Jia, et. al, Effects of a compatibilizing agent on the morphology, interface and mechanical behaviour of polypropylene /poly(ethylene terephthalate) blends, Polymer, Vol. 41, pp. 357-365, January 2000.
• Ç. Çam, Production of surface coating materials from postconsumer pet bottles M., Istanbul University, M.Sc, thesis, Turkey, 2015.
• C. Gartner, M. Suarez,et. al, Grafting of maleic anhydride on polypropylene and its effect on blending with poly(ethylene terephthalate), Polymer Engineering & Science, Vol. 48, pp.1910-1916, August 2008.
• K. Jayanarayanan, S. Thomas, et. al, Morphology, static and dynamic mechanical properties of in situ microfibrillar composites based on polypropylene /poly (ethylene terephthalate) blends, Composites:Part A, Vol. 39, No. 2, pp.164-175, February 2008.
• N. Baş, Artificial neural networks approach and an application, Mimar Sinan University, M. Sc, thesis, Turkey 2006.
• T. M., Ballı, Demand forecasting with artificial neural networks and implementation in the food industry, Yildiz Technical University, M.Sc, thesis, Turkey, 2014.
• F. İnala, G. Tayfur, et. al, Experimental and artificial neural network modeling study on soot formation in premixed hydrocarbon flames,Fuel, Vol. 82, No.12, pp. 1477-1490, August 2003.
• A. T. Seyhan, G. Tayfur, et. al, Artificial neural network (ANN) prediction of compressive strength of VARTM processed polymer composites, Computational Materials Science, Vol. 34, No. 1, pp. 99-105, August 2005.