Improvement of process conditions in acrylic fiber dyeing using gray-based Taguchi-neural network approach

被引：0
作者：
Mithat Zeydan
Deniz Yazıcı
机构：
[1] Erciyes University,Department of Industrial Engineering
[2] Atlantic Carpet Factory,undefined
来源：
Neural Computing and Applications | 2014年 / 25卷
关键词：
Acrylic dyeing; Gray relational analysis; Taguchi design of experiment; Artificial neural network;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The main aim of this study was to enhance the product quality by improving dyeing process conditions of acrylic fiber used as raw material in a factory-produced carpet. There are three quality characteristics consisting of desired (nominal) color strength, maximized acrylic fiber strength and minimized dyestuff in dye bath. Dyeing temperature, fixation duration, softener, antistatic, amount of material (fiber), pH, retarder and dispergator, which have an influence on dyeing, were chosen as control factors. Dyeing temperature and antistatic were seemed to be significant factors on dyeing for 95 % confidence interval statistically. Optimal dyeing process conditions were determined by hybrid gray-based Taguchi–artificial neural network (ANN) method. Gray relational grade as a performance evaluation index obtained from gray relational analysis reduces the number of quality characteristics. Gray relational grade was found as 0.6630 for existing conditions and improved as 0.7749 by gray-based Taguchi ANN method. The suggested methodology improves quality of dyed acrylic fiber, reduces defective products and provides dyeing operations much more efficient. All of these translate into significant cost savings.
引用
收藏
页码：155 / 170
页数：15
相关论文
共 39 条
[1]  
Kuo CC(2010)Applying regression analysis to improve dyeing process quality: a case study Int J Adv Manuf Technol 49 357-368
[2]  
Pietras S(2006)Optimization of process variables by the application of response surface methodology to optimize the process variables for reactive red and acid brown dye removal using a novel adsorbent Dyes Pigm 72 66-74
[3]  
Ravikumar K(2008)Optimization of the dyeing process and prediction of quality characteristics on elastic fiber blending fabrics Polym Plast Technol Eng 47 678-687
[4]  
Krishnan S(2006)Optimization of the processing conditions and prediction of the quality for dyeing nylon and lycra blended fabrics Fibers Polym 4 344-351
[5]  
Ramalingam S(2004)Fuzzy control of dye bath pH in exhaust dyeing Color Technol 120 51-55
[6]  
Balu K(2011)Optimization of pigment dyeing process of high performance fibers using feed-forward bottleneck neural networks mapping technique Anal Chim Acta 705 148-154
[7]  
Kuo CFJ(2012)Investigation of tensile properties and dyeing behavior of various polypropylene/polyamide 6 blends using a mixture experimental design Dyes Pigm 92 642-653
[8]  
Chang CD(2012)Optimization of dyeing wool fibers procedure with Isatis tinctoria by response surface methodology J Nat Fibers 9 73-86
[9]  
Su TL(2011)Prediction of the spectrophotometric response of a carded fiber composed by different kinds of coloured row materials:an artificial neural network-based approach Color Res Appl 36 179-191
[10]  
Fu CT(2010)Prediction of the color and of the color solidity of a jigger-dyed cellulose-based fabric: a cascade neural network approach Text Res J 80 1682-1696
1234