A Novel Approach to Determine the Amount of Natural Fiber and Polymer of Composite Materials via Artificial Neural Networks


DÖNMEZ ÇAVDAR A., ÖZTÜRK E., ÇAVDAR T.

International Conference on Artificial Intelligence and Data Processing (IDAP), Malatya, Turkey, 28 - 30 September 2018 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • City: Malatya
  • Country: Turkey

Abstract

In this study, it is aimed to use Tea Mill Waste Fiber (TMWF) as a mixture raw material to produce a high quality and durable composite product via Artificial Neural Network (ANN) which is a new and developing method. It is aimed to be able to produce better quality products by mixing polypropylene (PP), high density polyethylene (HDPE) and TMWF as raw materials in the correct proportions. An ANN was generated in the Matlab environment and it was trained using data, which was obtained as a result of empirical studies to find the ideal mixture ratio to obtain a quality product. It has been shown that the ratio of the mixture in the simulation result is correct and the created ANN is successful as these results are compared to the results obtained from the experimental studies.