An Artificial Neural Network Model for Prediction of Colour Properties of Knitted Fabrics Induced by Laser Engraving

Abstract

In this paper, we propose an artificial neural network (ANN) model for prediction of color properties, including color yield (in terms of K/S value) and CIE L, a and b values of 1005 cotton knitted fabrics under the effect of laser engraving process with different process parameters. Fabric factors to be examined in the ANN model included fiber composition, fabric density, mass of fabric, fabric thickness, linear density of yarn, yarn twist, direction of yarn twist and crimp. After obtaining the ANN model, its performance was compared with linear regression model. It is noted that the ANN model produced superior results in prediction of color properties of laser engraved 100 % cotton knitted fabrics. The relative importance of the examined factors influencing color properties was also investigated.