Prediction of the coating thickness of wire coating extrusion processes using artificial neural network (ANN)

Recep Kozan and Bekir Cirak

Modern Applied Science, 2009, vol. 3, issue 7, 52

Abstract: This paper presents a new method of modeling the nonlinear parameters of a coating systems base on neural Networks with artificial neural network neurons. Artificial neural networks (ANNs) are a new type of information processing system based on modeling the neural system of human brain. The wire coating thickness and quality depend on the wire speed, polymer viscosity, polymer melt temperature and the gap between the wire and exit end of the die. In this paper, results of experimental investigation are presented by comparing the coating quality on galvanized mild steel wire using EP 58 PVC molten is used as the coating material in a wire coating extrus?on unit at different extruder temperatures and extruder speeds. The coating thickness and quality are also discussed for different wire speeds of up to 15 m/s. A three layer back propogation artificial neutral network (ANN) model was used for the description of wire coating thickness.On comparing the experimental data, the predictions the ANN model predictions, it is found that the ANN model is capable of predicting the coating thickness. The neural network model shows how the significant parameters influencing thickness can be found. Inthis studies, a back propagation neural network model is developed to map the complex non-linear wire coating thickness between process conditions . Â

Date: 2009
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://ccsenet.org/journal/index.php/mas/article/download/1520/2812 (application/pdf)
https://ccsenet.org/journal/index.php/mas/article/view/1520 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ibn:masjnl:v:3:y:2009:i:7:p:52

Access Statistics for this article

More articles in Modern Applied Science from Canadian Center of Science and Education Contact information at EDIRC.
Bibliographic data for series maintained by Canadian Center of Science and Education ().