共查询到20条相似文献，搜索用时 31 毫秒
1.
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. 相似文献
2.
In this study artificial neural network (ANN) models have been designed to predict the ring cotton yarn properties from the
fiber properties measured on HVI (high volume instrument) system and the performance of ANN models have been compared with
our previous statistical models based on regression analysis. Yarn count, twist and roving properties were selected as input
variables as they give significant influence on yarn properties. In experimental part, a total of 180 cotton ring spun yarns
were produced using 15 different blends. The four yarn counts and three twist multipliers were chosen within the range of
Ne 20–35 and α
e 3.8–4.6 respectively. After measuring yarn tenacity and breaking elongation, evaluations of data were performed by using
ANN. Afterwards, sensitivity analysis results and coefficient of multiple determination (R2) values of ANN and regression models were compared. Our results show that ANN is more powerful tool than the regression models. 相似文献
3.
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. 相似文献
4.
This study was focus on the influence of filament and roving location on yarn properties during embeddable and locatable spinning (ELS). ELS composite yarns were produced with various filament and roving locations on an experimental ring spinning frame. Besides yarn formation zone configurations, ELS yarn properties were compared including yarn hairiness, unevenness and tensile properties. Results showed that spinning triangles became larger; however, the reinforced composite spinning strand length kept constant. With a constant filament-roving spacing on each side of ELS, Filament spacing variations caused no significant changes of spun yarn hairiness, tenacities, imperfections and unevenness CV. For roving location variations with constant filament spacing, the reinforced strand length became longer as the roving spacing increased. Hairs exceeding 3 mm were lower for ELS yarn spun with 4 mm and 10 mm roving spacings than that spun with 6 mm, 8 mm and 12 mm roving spacings. Roving spacing variations had a trivial influence on ELS yarn unevenness; whereas, yarn tensile index variation coefficients fluctuated dramatically due to hairiness variations for different roving spacings. 相似文献
5.
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. 相似文献
6.
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. 相似文献
7.
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. 相似文献
8.
In this study, spinning with a contact surface was introduced as a simple and energy-saving method to reduce spun yarn hairiness. Theoretical analysis indicated that yarn hairiness could be reduced via a sufficient long contact surface applied in other part of yarn formation zone in addition to spinning triangle. Then, a simple contact apparatus was installed on ring frame to validate the theoretical analysis. Results proved that yarn hairiness was reduced via a contact surface in the yarn formation zone. However, unevenness was deteriorated for most yarns spun with contact apparatus during the spinning, which might be due to fiber mass concentration. Most of yarns spun with contact apparatus had a lower strength than the conventional yarns. This might be because evenness deterioration to decrease yarn strength overpowered hairiness reduction to increase yarn strength for most yarns spun with a contact surface. 相似文献
9.
Opening of the fibres in all industrial rotor spinning units is being done by an opening roller, which intakes the fibres
from one feed point. Increasing number of feed rollers from one to two may improve fibre opening on the opening roller by
gradual loading of the opening roller, which may improve fibre orientation in the final yarn and yarn properties. In this
research a modified SE-8 rotor spinning unit of Suessen was used in which two separate fibre feed systems were employed. Raw
material used was 38 mm, 1.7 den viscose fibre, to spin a 40 tex yarn. Yarn properties produced with this unit, were compared
with that of the original yarn. Yarn properties tested were tenacity, extension, work of rupture, mass irregularity and imperfections,
abrasion resistance and hairiness, which were measured on Shirley (SDL) and keisokki yarn testing machines. Test results were
analyzed by ANOVA for any difference between the means, and Tukey and Duncan for classification and ranking of the yarn properties.
Test results showed that, tenacity, extension and work of rupture of the modified yarn increased in comparison to the original
yarn. Its mass irregularity, number of thin places and neps, and hairiness decreased. Number of thick places and yarn abrasion
didn’t change. According to the test results, it was concluded that increasing the number of feed rollers on the opening roller
from one to two has improved yarn properties. 相似文献
10.
Farooq Ahmed Arain Anwaruddin Tanwari Tanveer Hussain Zulfiqar Ali Malik 《Fibers and Polymers》2012,13(1):118-122
In this study, a multiple response optimization model based on response surface methodology was developed to determine the best rotor speed and yarn twist level for optimum rotor yarn strength and unevenness, and minimum yarn hairiness and imperfections. Cotton yarn of 30 tex, was produced on rotor spinning machine with different twist levels (i.e. 500, 550, 600 and 700 tpm) at different rotor speeds (i.e. 70000, 80000, 90000 and 100000 rpm). Yarn quality characteristics were determined for all the experiments. Based on the results, multiple response optimization model was developed using response surface regression on MINITAB® 16 statistical tool. Optimization results indicate that with the quality of raw material selected for this study, top 50 % quality level, according to USTER® yarn quality benchmarks, can be achieved with 100 % desirability satisfaction for all the selected yarn quality parameters at rotor speed of 77,800 rpm and yarn twist of 700 twists per meter. 相似文献
11.
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. 相似文献
12.
Yarn tension is a key factor that affects the efficiency of a ring spinning system. In this paper, a specially constructed
rig, which can rotate a yarn at a high speed without inserting any real twist into the yarn, was used to simulate a ring spinning
process. Yarn tension was measured at the guide-eye during the simulated spinning of different yarns at various balloon heights
and with varying yarn length in the balloon. The effect of balloon shape, yarn hairiness and thickness, and yarn rotating
speed, on the measured yarn tension, was examined. The results indicate that the collapse of balloon shape from single loop
to double loop, or from double loop to triple etc, lead to sudden reduction in yarn tension. Under otherwise identical conditions,
a longer length of yarn in the balloon gives a lower yarn tension at the guide-eye. In addition, thicker yarns and/or more
hairy yarns generate a higher tension in the yarn, due to the increased air drag acting on the thicker or more hairy yarns. 相似文献
13.
Although gradient based Backpropagation (BP) training algorithms have been widely used in Artificial Neural Networks (ANN) models for the prediction of yarn quality properties, they still suffer from some drawbacks which include tendency to converge to local minima. One strategy of improving ANN models trained using gradient based BP algorithms is the use of hybrid training algorithms made of global based algorithms and local based BP algorithms. The aim of this paper was to improve the performance of Levenberg-Marquardt Backpropagation (LMBP) training algorithm, which is a local based BP algorithm by using a hybrid algorithm. The hybrid algorithms combined Differential Evolution (DE) and LMBP algorithms. The yarn quality prediction models trained using the hybrid algorithms performed better and exhibited better generalization when compared to the models trained using the LM algorithms. 相似文献
14.
In this study, an artificial neural network (ANN) and a statistical model are developed to predict the unevenness of polyester/viscose
blended open-end rotor spun yarns. Seven different blend ratios of polyester/viscose slivers are produced and these slivers
are manufactured with four different rotor speed and four different yarn counts in rotor spinning machine. A back propagation
multi layer perceptron (MLP) network and a mixture process crossed regression model (simplex lattice design) with two mixture
components (polyester and viscose blend ratios) and two process variables (yarn count and rotor speed) are developed to predict
the unevenness of polyester/viscose blended open-end rotor spun yarns. Both ANN and simplex lattice design have given satisfactory
predictions, however, the predictions of statistical models gave more reliable results than ANN. 相似文献
15.
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. 相似文献
16.
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. 相似文献
17.
Chung-Feng Jeffrey Kuo Hsin-Jung Wei Chang-Chiun Huang Te-Li Su 《Fibers and Polymers》2010,11(6):891-898
In the field of yarn spinning engineering, the importance of the processing parameters taken depends directly on the quality
characteristics of the yarn. This study aimed to find the optimal processing parameters for an open-end rotor spinning frame
at work to identify its multiple quality characteristics for yarn. In this study, Bamboo charcoal and cotton 70 %/polyester
30 % (CVC) blended fibers were adopted as the materials, and the open-end rotor spinning frame was used to spin the yarn.
In order to identify optimal conditions of an open-end rotor spinning frame, the Taguchi experimental method was applied to
design open-end rotor spinning experiments, and the L9 orthogonal array was chosen in accordance with nine sets of experiments and contained four control factors and three levels.
Furthermore, a response surface methodology (RSM) was used to obtain the models of significant processing parameters for the
strength, unevenness, I.P.I, and hairiness. Based on experiments designed to obtain an open-end rotor spun yarn Ne 30, the
strength, unevenness, imperfection indicator/km (I.P.I) and hairiness were then chosen as the quality characteristics. In
addition, grey relational analysis integrated the optimal processing parameter of multiple quality characteristics, and a
confirmation experiment was performed. In conclusion, the optimal processing parameters under steady spinning conditions were
a rotor speed of 88000 rpm, a feed speed of 0.392 m/min, and a winding speed of 39.466 m/min. 相似文献
18.
This paper examines the use of pressurized steam for wrapping and setting the yarn hairs concurrently via a new steam-jet
process during winding. Yarn torque can also be stabilized as an added advantage. The results obtained with two batches of
pure wool yarns suggest that there is potential to achieve yarn hairiness reduction of up to 60 % with minimum deterioration
in hairiness even after subsequent rewinding. 相似文献
19.
Fiber length distribution has an impact not only on the theoretical unevenness of yarn caused by random fiber alignment, but
also upon the additional unevenness caused during processing, especially in drafting. For a given fiber length distribution,
there is a discrepancy between the theoretical unevenness of yarn which is calculated with Martindale’s equation and the actual
unevenness tested by instrument. In order to reflect the effect of fiber length distribution on the theoretical unevenness
of yarn, in this research, a kernel function was used to estimate the probability density function of fiber length, therefore,
calculation of Suh’s model for theoretical unevenness was realized. On this basis, the theoretical and additional unevenness
of yarn were calculated. The statistical influence of fiber length parameters on yarn unevenness was discussed. It can be
concluded that decreasing the values of effective length, length irregularity and 16 mm SFC by weight would improve the uniformity
of yarn. 相似文献
20.
In this study, an analysis on the breaking elongation mechanism of the polyester/viscose blended open-end rotor spun yarns
has been carried out. In addition, a back propagation multi layer perceptron (MLP) network and a mixture process crossed regression
model with two mixture components (polyester and viscose blend ratios) and two process variables (yarn count and rotor speed)
are developed to predict the breaking elongation of polyester/viscose blended open-end rotor spun yarns. Seven different blend
ratios of polyester/viscose slivers are produced and these slivers are manufactured with four different rotor speed and four
different yarn counts in rotor spinning machine. In conclusion, ANN and statistical model both have given satisfactory predictions;
however, the predictions of ANN gave relatively more reliable results than those of statistical models. Since the prediction
capacity of statistical models is also obtained as satisfactory, it can also be used for breaking elongation (%) prediction
of yarns because of its simplicity and non-complex structure. In addition, it is also found in this study that yarn count,
rotor speed and breaking elongation of polyester-viscose fibers and the blend ratios of these fibers in the yarn have major
effects on yarn breaking elongation. 相似文献