We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Comparison of Mechanical Properties and Artificial Neural Networks Modeling of PP/PET Blends.
- Authors
ÖZCANLI, Y.; ÇAVUŞ, F. KOSOVALI; BEKEN, M.
- Abstract
The aim of this study is to show the applicability of artificial neural networks, which are getting more applications with the advancement of technology, to determine the mechanical properties of polymeric materials. Mechanical properties of pure polypropylene, polyethylene terephthalate and their blends are determined in this study and the effect of temperature (room temperature, 40 °C and 60 °C) on mechanical properties is investigated. The method of artificial neural networks is used to make a prediction for mechanical properties. Mechanical properties of samples are measured using Lloyd 250N capacity tension and compression apparatus at crosshead speed of 10 mm/min, 25 mm/min, and 50 mm/min. For artificial neural networks modelling, the tensile experiment results, temperature, percent ratio, and crosshead speed are used as the input and output parameters. Three-layered multilayer perception, feed-forward neural network architecture is used and trained with the error back propagation. The results obtained from the output of the network are compared with the experiment results. The suitability of the method is found to be satisfactory.
- Subjects
ARTIFICIAL neural networks; POLYMERS; POLYPROPYLENE; POLYETHYLENE terephthalate; TENSILE strength
- Publication
Acta Physica Polonica: A, 2016, Vol 130, Issue 1, p444
- ISSN
0587-4246
- Publication type
Article
- DOI
10.12693/APhysPolA.130.444