Predicting properties of single jersey fabrics using regression and artificial neural network models

In our previous works, we had predicted cotton ring yarn properties from the fiber properties successfully by regression and ANN models. In this study both regression and artificial neural network has been applied for the prediction of the bursting strength and air permeability of single jersey knitted fabrics. Fiber properties measured by HVI instrument and yarn properties were selected as independent variables together with wales’ and courses’ number per square centimeter. Firstly conventional ring yarns were produced from six different types of cotton in four different yarn counts (Ne 20, Ne 25, Ne 30, and Ne 35) and three different twist multipliers (α _e 3.8, α _e 4.2, and α _e 4.6). All the yarns were knitted by laboratory circular knitting machine. Regression and ANN models were developed to predict the fabric properties. It was found that all models can be used to predict the single jersey fabric properties successfully. However, ANN models exhibit higher predictive power than the regression models.     

Prediction of cotton yarn properties using support vector machine

This paper presents a support vector machine (SVM) regression approach to forecast the properties of cotton yarns produced on ring and rotor spinning technologies from the fibre properties measured by HVI and AFIS. Prediction performance of SVM models have been compared against those of the artificial neural network (ANN) models. A k-fold cross validation technique is applied to assess the expected generalization accuracies of both SVM and ANN models. The investigation indicates that the yarn properties can be predicted with a very high degree of accuracy using SVM models and the prediction performance of SVM models are better than that of ANN models.     

Modelling of ring yarn unevenness by soft computing approach

This paper demonstrates the application of two soft computing approaches namely artificial neural network (ANN) and neural-fuzzy system to forecast the unevenness of ring spun yarns. The cotton fiber properties measured by advanced fiber information system (AFIS) and yarn count have been used as inputs. The prediction accuracy of the ANN and neural-fuzzy models was compared with that of linear regression model. It was found that the prediction performance was very good for all the three models although ANN and neural-fuzzy models seem to have some edge over the linear regression model. The linguistic rules developed by the neural-fuzzy system unearth the role of input variables on the yarn unevenness.     

Using artificial neural network to predict colour properties of laser-treated 100% cotton fabric

In this paper, artificial neural network (ANN) model was used for predicting colour properties of 100 % cotton fabrics, including colour yield (in terms of K/S value) and CIE L, a, and b values, under the influence of laser engraving process with various combination of laser processing parameters. Variables examined in the ANN model included fibre composition, fabric density (warp and weft direction), mass of fabric, fabric thickness and linear density of yarn (warp and weft direction). The ANN model was compared with a linear regression model where the ANN model produced superior results in prediction of colour properties of laser engraved 100 % cotton fabrics. The relative importance of the examined factors influencing colour properties was also investigated. The analysis revealed that laser processing parameters played an important role in affecting the colour properties of the treated 100 % cotton fabrics.     

Assessment of the surface roughness of cotton fabrics through different yarn and fabric structural properties

The effects of some yarn properties (i.e. type, count, twist level, ply number, unevenness and crimp) and fabric constructional properties (i.e. cover, thickness and balance) on surface roughness values of cotton woven fabrics were investigated. A general overview of the results showed that surface roughness values of fabrics were affected from yarn and fabric properties and the effects were related to fabric balance, fabric cover (not cover factor), fabric thickness and crimp values of yarns in fabric structures. Surface roughness values of fabrics decreased as yarn fineness and yarn twist levels increased but as yarn ply number decreased. Also, surface roughness values gradually decreased from open-end yarn constituting fabrics to combed yarn constituting fabrics. Results showed that different properties of yarns caused changes in yarn crimps in fabric structure and also governed the changes in fabric balance, as well as changes in roughness of fabric surfaces. The changing properties of yarns and impact of these properties on fabric construction affected the formation of cotton fabric surfaces from smooth to coarse.     

An adsorption study of alum-morin dyeing onto silk yarn

Silk yarn was dyed with morin (2′,3,4′,5,7-pentahydroxyflavone) by using alum as mordant. In order to optimize the process, three methods of dyeing involving: pre-mordanting, simultaneous mordanting, and post-mordanting were assessed and compared with a mordant-free process. The adsorption of alum-morin dye onto silk fibers indicated that the adsorption capacities were significantly affected by pH, the initial dye concentration, and temperature. The initial dye adsorption rates of alum-morin dye on silk before equilibrium was reached increased with higher dyeing temperatures. The pseudo second-order kinetic model was indicated for alum-morin dyeing (simultaneous mordanting) of silk at pH 4.0 with an activation energy (E _a ) of 45.26 kJ/mol. The value of the enthalpy of activation (ΔH ^#) for alum-morin dyeing on silk at pH 4.0 was −31.29 kJ/mol. Also, the free energy (ΔG ^o) and entropy changes (ΔS ^o) for alum-morin dyeing on silk were −17.73 kJ/mol and −45.7 J/molK, respectively, consistent with a spontaneous and exothermic adsorption process.     

Investigation of inter fiber cohesion in yarns. I. Influence of certain spinning parameters on the cohesion in cotton yarns

This paper investigates the influence of raw material and process parameters in spinning that affect the inter fiber cohesion in yarns. An instrument has been developed for measuring the minimum twist of cohesion. With regard to the raw material parameters, the influence of different cotton fiber mixings for a given count of yarn is investigated. Also the effect of spinning to varying counts for a given cotton variety is studied. With regard to the process parameters, studies have been carried out to investigate the influence of noil extraction in comber, number of draw frame passages, draft pressure in ring frame and direction of twist. Cohesion improved with increase in the noil extraction percentage in the comber. Increase in the number of draw frame passages also improved the cohesion. Draft pressure in ring frame improved the fiber cohesion in yarn up to a pressure of 2.1 kg/cm². Direction of twist had no effect on the cohesion.     

Cotton yarn engineering via fuzzy least squares regression

Modeling of yarn and fiber properties has been a popular topic in the field of textile engineering in recent decades. The common method for fitting models has been to use classical regression analysis, based on the assumptions of data crispness and deterministic relations among variables. However, in modeling practical systems such as cotton spinning, the above assumptions may not hold true. Prediction is influential and we should therefore attempt to analyze the behavior and structure of such systems more realistically. In the present research, we investigate a procedure to provide a soft regression method for modeling the relationships between fiber properties, roving properties, and yarn count as independent variables and yarn properties as dependent (response) variable. We first selected the effective variables by multivariate test (mtest) and then considered fuzzy least squares regression for evaluating relationship between cotton yarn properties such as tensile, hairiness, unevenness and fiber properties that were measured by HVI system. We also used mean of capability index (MCI) to evaluate the goodness of fit of the fuzzy regression models. The results showed that the equations were significant at very good MCI levels.     

Comparison of the new methodologies for predicting the CSP strength of rotor yarn

This paper provides preliminary results on the relative performance of the adaptive neuro-fuzzy system inference (ANFIS) model versus linear multiple regression method, when applied to the use of cotton fiber properties to predict spun yarn strength obtained from open-end rotor spinning. Fiber properties and yarn count are used as inputs to train the two models and the output (dependent variable) would be the count-strength-product (CSP) of the yarn. The predictive performances of the two models are estimated and compared. We found that the ANFIS has a better average prediction successful in comparison with linear multiple regression model.     

Cotton yarn engineering using robust regression and criteria of Mallow’s Cp

The main purpose of the present study was to predict yarn’s important properties i.e., tensile, unevenness, hairiness, and imperfections of cotton yarn with minimum random errors and maximum accuracy. In this work, cotton fiber properties were measured from rovings carefully untwisted. HVI system and evenness tester of Premier were used to measure the various properties. All yarns (108 samples) were spun at yarn counts of 16, 20, 24, 28, and 32 Ne with optimum twist factor. The robust regression and criteria of Mallow’s Cp were used to evaluate the data. Optimal equations with appropriate variables and relative importance of various variables were also investigated. After the goodness of fit, desirable Cp and very large adjusted R² values were observed. Furthermore, the analysis of variance tables showed that the obtained equations were significant at usual significance levels.     

A study on coarse Hanji yarn manufacturing and properties of the Hanji fabric

Hanji (Korean traditional paper) yarn displays excellent humidity control, air permeability, and absorbency as well as pleasantness to the touch due to its structural characteristics, and thus, it has been developed as a new eco-friendly fibrous materials. In this study, Hanji, having a basis weight of 8 and 10 g/m², was prepared using mulberry fibers. The prepared Hanji was cut into Hanji tape of 5–10 mm in width using a rotary slitter and then the tape was twisted to manufacture Hanji yarn. To ensure a uniform twist of Hanji yarn and a smooth twisting process, a water supply system was designed to provide water directly at the twisting zone. At a fixed spindle speed, the feeding speed of the delivery roller was varied to provide different twist numbers for the Hanji yarn. The Hanji yarn manufactured with water treatment has higher tensile properties and a softer touch than the Hanji yarn prepared without water treatment. The Hanji yarns have count numbers of 7–11 Ne and tensile strengths of 1.0–1.2 gf/d. Moreover, the fabric from Hanji yarn shows an excellent color fastness of 4.0 grade, staining of 4–5 to washing, and 4–5 grade to dry cleaning.     

Study on Spinning triangles in the common ring spinning and Super draft ring spinning systems

In the paper, one kind of super draft ring spinning frame with four drafting rollers and corresponding three drafting zones were introduced. The yarn qualities spun by the super draft ring spinning frame were analyzed by studying the shape of spinning triangles. Using the high speed camera system OLYMPUS i-speed3 and one kind of transparent front top roller, the spinning triangles were captured, and the geometry size of spinning triangle were measured. Then, according to the theoretical model of fiber tension in the spinning triangle, fiber tension distributions in the spinning triangles were presented by using Matlab software. Using the combed roving of 350 tex as raw material, three kinds of cotton yarns, 27.8 tex (21^S), 18.2 tex (32^S) and 14.6 tex (40^S), were spun in the common ring spinning frame with three different suitable spindle speeds, travelers and twist factors. Using the combed roving of 350 tex and 500 tex as raw material, 14.6 tex cotton yarns were spun in the super draft ring spinning frame with three different drafting ratios at back zone. It is shown that with the increasing of spindle speed, a more asymmetric shape of spinning triangle would be produced, and lead to worsen yarn evenness. With the decreasing of traveler weight, the height and horizontal deviation of the spinning triangle is decreased, and may lead to better yarn evenness and less long hairiness. By taking suitable large yarn twist factors, the comprehensive qualities can be improved. Comparing with the common ring spinning, the spinning triangle is larger in the super draft ring spinning. That is, in the super draft ring spinning, the fibers in the strand in the front roller nip are more dispersed, and not benefit for yarn qualities. Therefore, the compact device was introduced into the super draft ring spinning, and the cotton pure yarns and blend yarns were spun, and the yarn qualities were measured and analyzed.     

Effect of repeated winding on carded ring cotton yarn properties

In this study, ten carded ring spun cotton yarns were subjected to windings. Yarn hairiness, fineness, unevenness and tensile properties were then examined. Results showed that the majority of the increased yarn hairiness occurred at the beginning cycles of windings. Weight loss occurred for most yarns after repeated windings. Tensile properties deteriorated for nearly all the yarn samples after repeated windings. On the contrary, yarn unevenness was improved for most yarns after corresponding windings. To explain the better evenness of yarn after repeated windings, unevenness of yarn was divided into two parts, namely stem unevenness and surface hairiness unevenness; yarn imperfections were subdivided into two categories: the imperfections of yarn stem and the imperfections caused by yarn hairs. Specifically, a balanced opinion was given to discuss the gains and losses in quality and cost due to repeated windings.     

Evaluation of bamboo charcoal/stainless steel/TPU composite woven fabrics

Composite woven fabric satisfies what people require. Bamboo charcoal (BC) has been identified as a multifunctional material that has far-infrared ray, anions, deodorization and etc. BC fibers and yarns were made of bamboo charcoal powders and have further become a pervasive materials used in textile industry. In this study, cotton yarns, stainless steel/cotton (SS/C) complex yarn, bamboo charcoal/cotton (BC/C) complex yarns were woven into the plain, twill and Dobby composite woven fabrics. The warp yarn was composed of cotton yarns, and the weft yarn was made up of BC/C and SS/C complex yarns with a picking ratio of 1:1 and 3:1. Thermoplastic polyurethanes (TPU) film was then attached to the composite woven fabrics, forming the BC/SS/TPU composite woven fabrics. Tests of electromagnetic shielding effectiveness (EMSE), far-infrared emissivity, anions, water resistance, and water vapor permeability measured the single-layer, two-layer and four-layer composite woven fabrics, obtaining a far-infrared emissivity of 0.95 by 39.8 counts per minute, an anion count of 149 amount/cc, an EMSE of −11.87 dB under frequency of 900 MHz, a surface resistivity of 8×10⁻⁶ Ω/square, a water resistance of −8219 mmH₂O, and water vapor permeability of 989 g/m²·h and 319 g/m²·24 h in accordance with JIS L 1099 A1 and ASTM E96 BW.     

Dyeing properties and colour fastness of cotton and silk fabrics dyed with<Emphasis Type="Italic">Cassia tora L.</Emphasis> extract

A natural colorant was extracted fromCassia tora L. using buffer solutions (pH: 2–11) as extractants. The dyeing solution (Cassia tora L. extract) extracted using pH 9 buffer solution was found to give the highest K/S values of dyed fabrics. Cotton and silk fabrics were dyed withCassia tora L. extract at 60°C for 60 min with pre-treatment of various metal salts as mordants. It was found thatCassia tora L. extract was polygenetic dyestuffs and its major components were anthraquinones. Studies have been made on the effects of the kind of mordant on dyeing properties and colour fastnesses of cotton and silk fabrics. The K/S of cotton fabrics increased in the order of the dyeing using FeSO₄>CuSO₄>ZnSO₄>MnSO₄≅Al₂(SO₄)₃>NiSO₄>none, however, the K/S of silk fabrics increased in the order of the dyeing using FeSO₄>CuSO₄>ZnSO₄≅Al₂(SO₄)₃>MnSO₄≅NiSO₄>none. It was found that the K/S values of dyed fabrics were largely affected by the colour difference (ΔE) between mordanted fabric and control fabric. However, they were not depended on the content of mordanted metal ion of the fabrics. Mordants FeSO₄ and CuSO₄ for cotton fabric, FeSO₄, CuSO₄, and Al₂(SO₄)₃ for silk fabric were found to give good light fastness (rating 4).     

Studies on reduction of yarn hairiness by nozzles in ring spinning and winding by airflow simulation

Reduction of yarn hairiness by nozzles in ring spinning and winding is a new approach. Simulation of the airflow pattern inside the nozzles provides useful information about actual mechanism of hairiness reduction. The swirling air current inside the nozzles is capable of wrapping the protruding hairs around the yarn body, thereby reducing yarn hairiness. Since production rate of winding is very high and the process itself increases yarn hairiness any method to reduce the hairiness of yarns at this stage is a novel approach. A CFD (computational fluid dynamics) model has been developed to simulate the airflow pattern inside the nozzles using Fluent 6.1 software. In this study, both S- and Z-type nozzles having an axial angle of 50° and diameter of 2.2 mm were used for simulation studies. To create a swirling effect, four air holes of 0.4 mm diameter are made tangential to the inner walls of the nozzles. S- and Z-twisted yarns of 30 tex were spun with and without nozzles and were tested for hairiness, tensile and evenness properties. The total number of hairs equal to or exceeding 3 mm (i.e. the S3 values) for yarn spun with nozzle is nearly 49–51 % less than that of ring yarns in case of nozzle-ring spinning, and 15 % less in case of nozzle-winding, while both the yarn types show little difference in evenness and tensile properties. Upward airflow gives best results in terms of hairiness reduction for nozzle-ring and nozzle wound yarns compared to ring yarns. Yarn passing through the centre of the nozzle shows maximum reduction in S3 values.     

Comparative study on sizing properties of amphoteric starch and phosphorylated starch for warp sizing

By varying the ratios of N-(3-chloro-2-hydroxypropl) trimethylammonium chloride and orthophosphate to starch, a series of amphoteric starch with different degree of substitution (DS) were prepared for evaluating sizing effect of amphoteric starch for cotton warps. The amphoteric starch contained quaternary ammonium and phosphate groups simultaneously, and was set to electric neutrality by varying relative quantity of anionic and cationic groups in order to prevent adverse effects of negative and positive charges. The influence of amphoteric modification of starch on the adhesion to cotton fibers was assessed by measuring tensile strength and work-to-break of slightly sized cotton roving and comparing the adhesion of amphoteric starch with those of phosphorylated one. Comparison on mechanical performances of amphoteric starch film over phosphorylated one was evaluated in terms of tensile strength, breaking extension and wear loss of starch film. The properties such as increase in tensile strength, loss in elasticity, abrasion resistance, and hairiness of cotton yarns sized with amphoteric starch were evaluated through control tests by the comparison with those of phosphorylated one. When zeta potential of amphoteric starch was set close to zero, the adhesion increased and the properties of sized yarns enhanced as the modification level increased. The amphoteric starch was evidently superior to phosphorylated one in improving the quality of sized cotton yarns. The amphoteric starch with neutral zeta potential and DS levels of 0.02–0.03 for quaternary ammonium groups and phosphate ones, respectively, could be applied to size cotton warp yarns for the improvement of yarn quality.     

Comparative study of cellulase treatment on low stress mechanical properties of cotton denim fabric made by torque-free ring spun yarn

Cellulase is useful for bio-polishing cotton fabrics which enhances their aesthetic performance instead of stonewashing process. Torque-free ring spun process is a widely used technique to produce newly low-twist and balanced torque yarns with soft hand. In this paper, denim fabrics woven with torque-free ring spun yarn and conventional ring spun yarn respectively were treated with cellulase under the same condition and their fabric handle, expressed as low stress mechanical properties, such as tensile strength, bending, shearing, compression and surface performance were investigated by Kawabata Evaluation System for Fabric (KES-F). After cellulase treatment, both denim fabrics revealed better flexibility, elasticity recovery, raised shearing stiffness, fluffier and improved smoothness. While torque-free ring spun yarn made denim fabric showed a better fabric handle than conventional ring spun yarn made denim fabric.     

Synthesis, characterization and application of quinazolinone based reactive dyes for various fibers

Seven hot brand heterocyclic mono azo reactive dyes (7a–g) have been synthesized by coupling diazotized 2-phenyl-3{4′-[(4″-aminophenyl)sulphonyl]phenyl}-quinazoline-4(3H)-one-6-sulphonic acid (4) with various 2-chloro-4-nitro anilino cyanurated coupling components (6a–g) and their dyeing performance on silk, wool, and cotton has been assessed. The purity of dyes was checked by thin layer chromatography. These dyes were identified by recording IR and ¹H-NMR spectra. The λ _max, R _f value, %exhaustion, %fixation, light fastness, wash fastness, rubbing fastness, reflectance (%R) value, and K/S value have also been studied.