Spectrophotometric colour matching algorithm for top‐dyed mélange yarn, based on an artificial neural network

Abstract

Colour, the first element of quality control of textile products, is a complex subject relating to physical optics, psychology, and the human visual system. Colour matching remains one of the major problems in the textile industry. M elange yarn is a class of textile product with a specific colour appearance, which colour is mainly affected by colour matching of the dyed fibres and their ratio for spinning rather than by the dyeing process. The existing colour matching models for m elange yarn derived from specific types of fibre or specific spinning processes are restricted by the adopted conditions and parameters of the model, resulting in low universal applicability and low accuracy. In this paper, a spectrophotometric colour matching algorithm based on the back-propagation (BP) neural network and its processes were proposed. The weighted average spectrum was predicted by a BP neural network, followed by recipe prediction from the weighted average with constrained least squares. The results showed that the average colour difference of practical samples, based on the prediction of nine blind testing targets, was 0.79 CMC (2:1) units if more than two a priori training samples were used. This result indicated the capability and practicality of accurate prediction of colour matching for top-dyed m elange yarn by this novel method.

Effect of production speed on polyester/nylon intermingled yarn and melange fabric properties

“…Melange yarn is a class of textile product with a two-tone colour appearance, whose colour is mainly affected by colour matching of the ratio of the dyed and undyed fibres rather than by the dyeing process. The existing colour matching models for melange yarn derived from specific types of fibre or specific spinning processes are restricted by the adopted conditions and parameters of the model, resulting in low universal applicability and low accuracy (Shen and Zhou, 2017). Researchers have focused on textile image processing for the fancy yarn fabrics using Microsoft Visual Studio 2010 (Zhang et al , 2018), MATLAB-based algorithm (Halepoto et al , 2019) and CIELAB system (Ozkan et al , 2018).…”

Research on colored yarns for a full color phase mixing model and the Stearns–Noechel color prediction approach

“…. ; 31Þ (19) Equation ( 16) provides a method to acquire the reflectance function of grid points according to the reflectance conversion coefficient corresponding to the mixing ratio of grid points, but it cannot be directly used to perform the solution of the reflectance function of non-grid points. For this purpose, using the reflectance conversion coefficients of the adjacent grid points as a foundation, an interpolation method is applied to obtain the average of the reflectance conversion coefficients Mði; k f Þ.…”

“…Whether using the neural networks alone or combining traditional models of neural networks, they can improve the prediction accuracy of the mixed color spectrum, but they require a large number of training samples, otherwise the generalization ability is relatively inferior; there also exists a black box issue, which is not conducive to theoretical analysis. [17][18][19][20] According to the intelligent algorithm and computer control techniques, the three-channel CNC ring spinning frame can achieve the regulation of the mixing ratios of the three primary colored fibers of the forming yarn by regulating the coupled drafting of the three drafting channels to the three rovings, and the control of the colors of the forming yarn by controlling the mixing ratios of the three primary colored fibers, which provides an equipment platform for the realization of the spinning of the yarn of the full color phase. 21,22 In order to enhance the function of color matching and color prediction of CNC spinning, it is essential to construct a digital mixing model for six primary colored fibers, to design a full color phase mixing model for six primary colored fibers according to binary coupled mixing, and to establish a mechanism for regulating the mixed colors within the range of full color phases in accordance with the mixing ratios of six primary colored fibers; for enhancing the accuracy of predicting colors of yarns by the mixing ratios of colored fibers, the solution method for the reflectance conversion coefficients of grid points and arbitrary points in the Stearns-Noechel formula needs to be improved for the prediction of the color of yarn; to implement the capability of predicting the mixing ratios of colored fibers according to colors of yarns and to improve the color matching accuracy, an improved reflectance conversion coefficient approach together with the least squares method is used for forecasting the mixing ratios.…”

Seepage Time Soft Sensor Model of Nonwoven Fabric Based on the Extreme Learning Machine Integrating Monte Carlo

“…Laura et al proposed a system that can generate color formula when combined with the BP algorithm, which could control small changes in color and reduce the subjectivity of visual evaluation of the color of textile products [11]. Similarly, for the key issue of color matching in the dyeing industry, Shen et al also combined the spectrophotometric color matching algorithm with the BP method to predict the color matching for top-dyed mélange yarn [12]. In addition to the BP, the RBF neural network has also been widely applied to prediction models.…”