Investigation and feed-forward neural network-based estimation of dyeing properties of air plasma treated wool fabric dyed with natural dye obtained from hibiscus sabdariffa

Abstract

In the colouring processes of textile products, more environmentally friendly chemicals and finishing methods should be used instead of conventional ones that harm the environment every day, so that alternative realistic ways to protect nature, both academically and industrially, could be possible. Due to some inconveniences caused by synthetic dyes that are widely used today, in this study, ultrasonic dyeing of wool fabric with Hibiscus sabdariffa was carried out after environmental-friendly air vacuum plasma application which increased the absorption of the dyes into the textile material. According to the performance results, colour strengths of the wool fabrics were increased significantly. Surface morphology analysis was carried out and etching effects of air vacuum plasma treatment were clearly seen on the micrographs of the treated wool fabrics. An environmental-friendly green process was achieved through this study and it was concluded that vacuum air plasma treatment could be an alternative green-process as a pretreatment to increase the dye up-take of natural dyeing treatment. Moreover, in this study, a feed-forward neural network (FFNN) model was presented and used for predicting the dyeing properties (L, a, b and K/S) of samples. The experimental results showed that the presented model achieves the regression values greater than 0.9 for all dyeing properties. Consequently, it was considered that the proposed FFNN was successfully modelled and could be efficiently utilised for dyeing characteristics of wool fabrics dyed with natural dye extracted from Hibiscus sabdariffa.