Application of ANN and ANFIS in prediction of color strength of plasma-treated wool yarns dyed with a natural colorant

Abstract

Purpose Despite the increasing popularity of natural dyeing of textiles, the low substantivity between the fibers and the natural dyes is a problem. Several methods have been used to overcome this problem. In this study, wool fibers were pretreated with oxygen plasma under different conditions and dyed with the extract of grape leaves. The purpose of this study is to investigate the effects of plasma treatment parameters on the color strength of the dyed samples using artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) and evaluate the ability of these methods for predicting the color strength. Design/methodology/approach Woolen yarns were modified under different conditions of oxygen plasma treatment. Oxygen flow rate, power and time were considered as the treatment variable factors. Plasma-treated samples were dyed under constant conditions with the extract of grape leaves as a natural dye. ANN and ANFIS were applied to model and analyze the effect of plasma treatment parameters on the color strength of the dyed samples. Findings The results showed that increasing all the plasma treatment process variables, including oxygen flow rate, power and time increased the color strength of the dyed samples. The results showed that the developed ANN and ANFIS could accurately predict the experimental data with correlation coefficients of 0.986 and 0.997, respectively. According to the obtained correlation coefficients, ANFIS had a higher accuracy in prediction of the results of this study compared with the ANN and RSM models (correlation coefficient = 0.902, from our previous study). Originality/value This study uses ANN and ANFIS for predicting color strength of naturally dyed textiles for the first time. The use of computational intelligence for the optimization and prediction of the effects plasma treatment for the improvement of natural dyeing of wool is another novelty of this study.

Comparing the accuracy of ANN and ANFIS models for predicting the thermal data

“…Hajiand and Payvandy applied ANN and ANFIS to assess the ability of these methods for predicting the color strength of plasma-treated wool yarns dyed with a natural colorant. As a result, ANFIS had higher accuracy based on the obtained correlation coefficients [5].…”

Comparison of ANFIS and ANN modeling for predicting the water absorption behavior of polyurethane treated polyester fabric

“…Commonly, the ANN and ANFIS model shows better performance with a larger amount of data that is labor-intensive to obtain and may not always be possible in an industrial situation [ 44 , 45 ]. But it is not uncommon to use a limited amount of data to successfully design models and predict different properties with satisfactory accuracy [ 24 , 39 , 46 ]. Hence it is clear that laboratory-scale experimental data can also be used to train the ANN and ANFIS models to predict data with distinctive accuracy.…”

Environmentally Benign Dyeing of Polyester Fabric with Madder: Modelling by Artificial Neural Network and Fuzzy Logic Optimized by Genetic Algorithm

“…Usually, plant-derived natural dyes contain more than one coloring compound and their dyeing behavior needs to be investigated on every textile fiber. The optimization of the dyeing process variables toward obtaining the highest extraction, exhaustion, and color strength is necessary and several studies have been reported on optimization of natural dyeing of wool, cotton, and other fibers using response surface methodology (RSM) and artificial neural networks (ANN) [36][37][38][39][40]. Despite the significant advantages of RSM over the traditional methods of optimization such as economy in number of trials, flexibility in experimental approach, and efficiency in controlling undesirable variations, these statistical methods are sometimes weak in prediction of the behavior of systems with complex and highly nonlinear data [41].…”