PROGNOSTICATING THE SHADE CHANGE AFTER SOFTENER APPLICATION USING ARTIFICIAL NEURAL NETWORKS

Softener application on fabric surface facilitates the process and wear abilities of the fabric. However, the application of softeners and other functional finishes influence the color of dyed fabrics, which results in shade change in the final finished fabrics. This article presents the method of intelligent prediction of the shade change of dyed knitted fabrics after finishing application by using artificial neural networks (ANNs). Individual neural networks are trained for the prediction of delta values (Delta L, Delta a, Delta b, Delta c, and Delta h) of finished samples with the help of reflectance values of the knitted dyed samples along with color, shade percentage, and finishing concentrations, which were selected as input parameters. The trained ANNs were validated through holdout and cross-validation techniques. The trained ANNs were combined to develop the model for shade prediction. The developed system can predict the shade change with >90% accuracy and help to decrease the rework and reprocessing in the wet processing industries.

Automated summary

This article presents a method of using artificial neural networks for intelligent prediction of shade change in dyed knitted fabrics after finishing application, with individual neural networks trained for delta values and combined to develop a predictive model with over 90% accuracy, aiming to reduce rework and reprocessing in the wet processing industries.