Application of Artificial Neuron Networks for Recipe Formulation in Textile Printing

Abstract

The Kubelka-Munk theory, which is the basis of dye formulation, has found no application in textile printing. Recipe formulation with dyestuffs in viscose printing pastes is carried out manually by matching the recipe of the printed sample to the standard. In order to find the desired shade this procedure is time-consuming. The consequence is that in the time of rapid fashion changes intensive efforts are made to find out the methods for automatic recipe formulation. One of these methods is the application of neuron networks. The paper describes, as an example of generating different input values, the creation and application of a neuron network for various concentrations and combinations of yellow and blue dye.