Predicting the colour properties of viscose knitted fabrics using soft computing approaches. Issue 10 (3rd October 2017)

• Record Type: Journal Article
• Authors: Hossain, Ismail; Choudhury, Imtiaz Ahmed; Mamat, Azuddin Bin; Hossain, Altab
• Is Part Of: Journal of the Textile Institute. Volume 108:Issue 10(2017)
• Page Start: 1689
• Page End: 1699
• Publication Date: 2017-10-03
• Subjects: Colour strength -- prediction -- viscose knitted fabric -- fuzzy logic -- artificial neural network; Textile industry -- Periodicals; Textile fabrics -- Periodicals; Periodicals; 677.005
• DOI: 10.1080/00405000.2017.1279004
• Languages: English
• ISSNs: 0040-5000

Abstract

Abstract: The aim of this paper was to predict the colour strength of viscose knitted fabrics by using fuzzy logic (FL) model based on dye concentration, salt concentration and alkali concentration as input variables. Moreover, the performance of fuzzy logic (FL) model is compared with that of artificial neural network (ANN) model. In addition, same parameters and data have been used in ANN model. From the experimental study, it was found that dye concentration has the main and greatest effects on the colour strength of viscose knitted fabrics. The coefficient of determination ( R 2 ), root mean square (RMS) and mean absolute errors (MAE) between the experimental colour strength and that predicted by FL model are found to be 0.977, 1.025 and 4.61%, respectively. Further, the coefficient of determination ( R 2 ), root mean square (RMS) and mean absolute errors (MAE) between the experimental colour strength and that predicted by ANN model are found to be 0.992, 0.726 and 3.28%, respectively. It was found that both ANN and FL models have ability and accuracy to predict the fabric colour strength effectively in non-linear domain. However, ANN prediction model shows higher prediction accuracy than that of Fuzzy model.