Please use this identifier to cite or link to this item: http://nopr.niscair.res.in/handle/123456789/9757
Title: Modeling of cotton yarn hairiness using adaptive neuro-fuzzy inference system
Authors: Majumdar, Abhijit
Keywords: Artificial neural network
Cotton
Fuzzy logic
Hairiness
Membership function
Neuro-fuzzy system
Yarn
Issue Date: Jun-2010
Publisher: CSIR
Abstract: This paper reports the modeling of cotton yarn hairiness using adaptive neuro-fuzzy inference system, combining the advantages of both artificial neural network and fuzzy logic. Three cotton fibre properties, namely mean length, short fibre content and maturity, measured by the advanced fibre information system and the yarn linear density (English count, Ne) have been used as the inputs to the model. Two levels of membership function have been considered for each of the four inputs and sixteen fuzzy rules are trained. The developed model predicts the cotton yarn hairiness with average error of around 2% even in the unseen test samples. Trained fuzzy rules give good understanding about the role of various input parameters on the cotton yarn hairiness. Yarn count and cotton fibre mean length are having major role in determining the yarn hairiness. Higher cotton fibre maturity reduces the yarn hairiness.
Description: 121-127
URI: http://hdl.handle.net/123456789/9757
ISSN: 0975-1025 (Online); 0971-0426 (Print)
Appears in Collections:IJFTR Vol.35(2) [June 2010]

Files in This Item:
File Description SizeFormat 
IJFTR 35(2) 121-127.pdf909.06 kBAdobe PDFView/Open


Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.