ANN Modellingfor Predicting the Water Absorption of Composites with Waste Plastic Pyrolysis Char Fillers

Year 2018, Volume: 1 Issue: 1, 45 - 51, 26.12.2018

Esra Yel , Sait Ali Uymaz , Gülay Tezel

Abstract

Waste material was fragmented into gas, liquid and solid fractions by pyrolysis. Recently the solid fraction (char) has been used as filler in epoxy composites. Type and properties of filler affect water absorption of epoxy composites. A recent water absorption database (of 1512 data) has been obtained experimentally. Accordingly, type of pyrolysed plastic, waste pre–washing, pyrolysis temperature, additive dosage and water exposure time were input parameters in the estimation model developed with multilayer perceptron artificial neural network (MLP ANN) to predict the absorbed water quantity as output. Four datasets were derived with data preprocessing. Among all the configurations worked up, 0.991 training and 0.986 testing R² were attained as the highest R² values under conditions including 2e4 iterations, lr 0.04, mc 0.9, first hidden layer of 22 nodes, and second hidden layer of 15 nodes. The R² value attained in the optimum configuration and the average R² attained via 5-fold cross-validation are close to each other for both training and test. The established model will help users to predict the quantity of water that absorbed upon exposure. This will give idea about the availability of that composite for using it for particular purposes.

Keywords

ANN, waste plastics, composite, epoxy resin, water.

References

• [1] U. Huner, "Effect of water absorption on the mechanical properties of flax fiber reinforced epoxy composites," Advances in Science and Technology Research J., cilt 9(26), ss. 1–6, 2015.
• [2] D. F. Hasson ve M. K. Hamm, "Effects of Freeze/Thaw Cycles on Hydrostatically Conditioned E–Glass/J–2 Composite," Report Number EW–17–92, United States Naval Academy Division of Engineering and Weapons Mechanical Engineering Department, 1992.
• [3] S. Pujari, A. Ramakrishna ve K. Padal, "Comparison of ANN and Regression Analysis for Predicting the Water Absorption Behaviour of Jute and Banana Fiber Reinforced Epoxy composites," Materials Today: Proceedings, cilt 4, ss. 1626–1633, 2017a.
• [4] S. Pujari, A. Ramakrishna ve K. Padal, "Prediction of Swelling Behaviour of Jute and Banana Fiber Composites by using ANN and Regression Analysis," Materials Today: Proceedings, cilt 4, ss. 8548–8557, 2017b.
• [5] S. Sheshmani, A. Ashori ve Y. Hamzeh, "Physical properties of polyethylene/wood fiber/organoclaynanocomposites," Appl Polym Sci, cilt 118(6), ss. 3255–3259, 2010.
• [6] L. Yan, N. Chouw ve K. Jayaraman, "Flax fibre and its composites –a review," Composites, Part B, cilt 56, ss. 296–317, 2014.
• [7] H. El Kadi, "Modeling the mechanical behavior of fiber-reinforced polymeric composite materials using artificial neural networks—A review," Composite Structures, cilt 73(1), ss. 1-23, 2006.
• [8] C. S. Kumar, V. Arumugam, R. Sengottuvelusamy, S. Srinivasan ve H. N. Dhakal, "Failure strength prediction of glass/epoxy composite laminates from acoustic emission parameters using artificial neural network," Applied Acoustics, cilt 115, ss. 32-41, 2017.
• [9] M. Thiruchitrambalam, A. Athijayamani, A. Sathiyamurthy ve S. A. Thaheer, "A Review on the Natural Fiber-Reinforced Polymer Composites for the Development of Roselle Fiber-Reinforced Polyester Composite," J. of Natural Fibers, cilt 7, ss. 307–323, 2010.
• [10] A. Nazari ve T. Azimzadegan, "Prediction the Effects of ZnO2 Nanoparticles on Splitting Tensile Strength and Water Absorption of High Strength Concrete," Materials Research, cilt 15(3), ss. 440-454, 2012.
• [11] K. Chen, T. Zhang ve S. Bao, "Water Absorption Rate Prediction of PMMA and Its Composites Using BP Neural Network," MATEC Web of Conf. 06017, 2016.
• [12] E. Yel (Project Director), "The wastes/products of washing and pyrolysis of thermoplastic domestic solid wastes (PET, PE, PS, PP) and new reclamation approach for char, treatment approcah for washing wastewater," TÜBİTAK–ÇAYDAG 1001 Project Grant No:114Y116, 2015–2017.
• [13] L. Fausett, Fundamentals of Neural Networks Architectures, Algorithms and Applications, Prentice Hall, Upper Saddle River, New Jersey, 1994.
• [14] S. Haykin, Neural Networks: A Comprehensive Foundation, New York: Macmillan, 1994.
• [15] R. Kohavi ve F. Provost, "Glossary of terms: Editorial for the special Issue on applications of machine learning and the knowledge discovery process30 (2/3)," 1998.
• [16] D. Anderson ve G. McNeil, Artificial neural Networks Technology Data&Analysis Center for Software, 1992.
• [17] D. P. Morgan, C. L. Scofield ve J. E. Adcock, "Multiple Neural Network Topologies Applied to Keyword Spotting," International Conference on Acoustics Speech and Signal Processing ICASSP-91, ss. 313-316, 1991.
• [18] R. K. Sinan, "Estimation of Primary Treatment and Biological Treatment Effluent Parameters by Artificial Neural Networks in Domestic Wastewater treatment Plants(Evsel Atıksu Arıtma Tesislerinde Ön Arıtım ve Biyolojik Arıtım Çıkış Parametrelerinin YSA ile Tahmini)," Msc Thesis, Selcuk University, Konya, 2010 (In Turkish).