Artificial Neural Network Based Modeling For Compressional Properties Of Woven Fabrics

glibdoadingΤεχνίτη Νοημοσύνη και Ρομποτική

20 Οκτ 2013 (πριν από 3 χρόνια και 10 μήνες)

85 εμφανίσεις

Artificial Neural Network Based Modeling For Compressional Properties Of
Woven Fabrics


Gurumurthy.B.R. and B.K.Behera

Department of Textile Technology, Indian Institute of Technology


Abstract

Data analysis of compression properties of a fabric can be do
ne only when the
limits of compression are known. The best formula is van wyks’s although the
meaning of the physical parameter is stil not clear. On the basis of Van wyks
equation, a study of the compressibility of woven fabrics can be initiated coupled
w
ith Pierce, Kemp and Hamilton’s approach for circular yarns and flattened yarns
of a fabric under pressure. Neural network models promises to solve the draw
backs of De.Jong and other models. Fit of pressure
-
thickness relationship may
be improved using exp
onential interpolations and Iterative method like
marquardt algorithm for evaluation of compression properties. Back
-
propogation
promises to give better results, since KES
-
FB3 compression measuring
instrument compliments by minimizing error levels.