纺织学报 ›› 2019, Vol. 40 ›› Issue (07): 169-173.doi: 10.13475/j.fzxb.20180602805

• 管理与信息化 • 上一篇    下一篇

基于最小二乘支持向量机的棉针织物活性染料湿蒸染色预测模型

陶开鑫, 俞成丙(), 侯颀骜, 吴聪杰, 刘引烽   

  1. 上海大学 材料科学与工程学院, 上海 200444
  • 收稿日期:2018-06-06 修回日期:2019-03-25 出版日期:2019-07-15 发布日期:2019-07-25
  • 通讯作者: 俞成丙
  • 作者简介:陶开鑫(1995-),男,硕士生。主要研究方向为先进纺织材料的制备与性能。
  • 基金资助:
    国家十三五重大科技专项(2017YFB0309700)

Wet-steaming dyeing prediction model of cotton knitted fabric with reactive dye based on least squares support vector machine

TAO Kaixin, YU Chengbing(), HOU Qi'ao, WU Congjie, LIU Yinfeng   

  1. College of Materials Science and Engineering, Shanghai University, Shanghai 200444, China
  • Received:2018-06-06 Revised:2019-03-25 Online:2019-07-15 Published:2019-07-25
  • Contact: YU Chengbing

RichHTML

1

PDF (PC)

69

摘要：

针对棉针织物在用活性染料连续湿蒸染色过程中出现的染色条件对织物色光难以控制和预测,易导致染色织物不符合预期产品要求的问题,选用雷马素金黄RGB对棉针织物进行湿蒸染色,研究了元明粉和纯碱浓度、汽蒸时间对织物表观染色深度(K/S值)的影响,同时基于最小二乘支持向量机(LS-SVM),将这些影响因素作为预测模型的输入变量,织物K/S值作为输出变量,建立了多因素模型并进行预测。结果表明,织物K/S实验值和模型预测值的相关系数高达0.999 6,平均相对误差小于1%,说明该模型具有较高的精度,该建模方法可用于预测织物K/S值,为棉针织物活性染料湿蒸染色工艺的优化提供参考。

关键词: 湿蒸染色, 活性染料, 最小二乘支持向量机, 多因素模型, 棉针织物

Abstract: Aim

ing at the problem of hard control and prediction of dyeing conditions on the color of dyed fabrics in the continuous wet-steaming dyeing of cotton knitted fabrics with reactive dye, the influences of sodium sulfate concentration, soda concentration, and steaming time on the color depth (K/S value) of the dyed fabrics were studied in the wet-steaming dyeing process of cotton knitted fabrics with Remazol golden yellow RGB. At the same time, based on least squares support vector machine (LS-SVM), using these factors as the input variables of the prediction model and the K/S value of fabric color depth as the output variable, a multi-factor model of K/S value was established to predict K/S value. The experiment results show that the correlation coefficient between the experimental value and the predicted value of the model is 0.999 6, and the mean relative error is lower than 1%, which indicates that the model has high accuracy. The modeling method can be applied to predict the K/S value of fabric, providing a basis reference for the optimization of the wet-steaming reactive dyeing process conditions for cotton knitted fabric.

Key words: wet-steaming dyeing, reactive dye, least squares support vector machine, multi-factor model, cotton knitted fabric

中图分类号: 

  • TP181

表1

40组染色样本K/S的实验值和回归值"

实验
号		 实验方案 K/S值 相对
误差/%		 支持
向量
α
X1 X2 X3 实验值 回归值
1 21.43 7.52 90 7.04 7.20 2.27 -219.14
2 42.86 7.52 90 9.05 8.72 3.65 448.78
3 64.29 7.52 90 10.43 10.39 0.38 49.94
4 85.71 7.52 90 11.61 12.16 4.74 -758.76
5 100.00 7.52 90 13.67 13.37 2.19 410.48
6 107.14 7.52 120 14.64 14.73 0.61 -128.82
7 125.00 7.52 120 16.93 16.57 2.13 491.39
8 150.00 7.52 120 18.57 18.91 1.83 -461.32
9 175.00 7.52 120 21.02 20.85 0.81 234.97
10 125.00 3.76 150 13.78 13.89 0.80 -157.38
11 125.00 9.40 150 17.96 17.47 2.73 677.28
12 125.00 15.04 150 16.92 16.82 0.59 142.89
13 125.00 20.68 150 17.29 17.28 0.06 17.35
14 125.00 26.32 150 18.56 18.56 0.00 -5.47
15 75.00 15.04 90 12.97 13.02 0.39 -61.72
16 75.00 15.04 120 12.40 12.31 0.73 125.05
17 75.00 15.04 150 14.19 14.24 0.35 -65.37
18 75.00 15.04 180 13.95 13.79 1.15 225.42
19 75.00 15.04 210 14.31 14.70 2.73 -535.14
20 75.00 15.04 240 15.62 15.61 0.06 18.85
21 150.00 3.76 180 19.62 19.57 0.25 66.16
22 150.00 9.40 180 19.24 19.17 0.36 90.16
23 150.00 15.04 180 19.58 19.46 0.61 160.72
24 150.00 20.68 180 19.73 19.86 0.66 -176.02
25 150.00 26.32 180 20.03 19.99 0.20 60.81
26 125.00 7.52 210 15.58 15.50 0.51 111.94
27 125.00 15.04 210 20.16 19.45 3.52 970.54
28 175.00 7.52 210 15.21 15.28 0.46 -102.52
29 175.00 15.04 210 18.37 18.70 1.80 -453.11
30 100.00 11.28 90 14.70 14.61 0.61 129.45
31 100.00 11.28 120 13.29 13.46 1.28 -239.28
32 100.00 11.28 150 15.45 15.43 0.13 20.94
33 100.00 11.28 180 13.57 13.86 2.14 -397.39
34 100.00 11.28 210 15.19 15.21 0.13 -21.57
35 100.00 11.28 240 14.50 14.51 0.07 -13.20
36 50.00 11.28 150 10.39 10.21 1.73 242.15
37 75.00 11.28 150 12.64 12.97 2.61 -450.50
38 125.00 11.28 150 16.80 17.42 3.69 -846.23
39 150.00 11.28 150 19.63 18.76 4.43 1187.46
40 175.00 11.28 150 18.80 19.38 3.09 -789.78

表2

模型拟合回归性能对比"

(γ,σ2) 均方
误差		 均方根
误差		 R值 P值 平均相对
误差/%
A 0.069 4 0.263 4 0.996 8 <0.000 1 1.17
B 0.091 7 0.302 8 0.995 8 <0.000 1 1.41
C 0.001 1 0.033 2 0.999 9 <0.000 1 0.20
D 0.002 1 0.045 8 0.999 9 <0.000 1 0.28
E 0.006 8 0.082 5 0.999 9 <0.000 1 0.49

表3

模型预测性能对比"

实验
号		 实验方案 K/S值 相对
误差/
%		 (γ,σ2)
X1 X2 X3 实验值 预测值
1 35.71 6.77 108 7.91 8.033 1.55 A
2 78.57 9.02 140 12.83 12.655 1.36
3 92.86 15.79 170 14.94 14.810 0.87
4 128.57 13.54 205 17.10 17.212 0.65
5 157.14 22.56 82 19.41 19.695 1.47
1 35.71 6.77 108 7.91 8.014 1.31 B
2 78.57 9.02 140 12.83 12.674 1.22
3 92.86 15.79 170 14.94 14.900 0.27
4 128.57 13.54 205 17.10 17.178 0.46
5 157.14 22.56 82 19.41 19.597 0.96
1 35.71 6.77 108 7.91 15.183 91.95 C
2 78.57 9.02 140 12.83 15.183 18.34
3 92.86 15.79 170 14.94 15.183 1.63
4 128.57 13.54 205 17.10 15.197 11.13
5 157.14 22.56 82 19.41 15.183 21.78
1 35.71 6.77 108 7.91 15.068 90.49 D
2 78.57 9.02 140 12.83 15.068 17.44
3 92.86 15.79 170 14.94 15.068 0.86
4 128.57 13.54 205 17.10 15.175 11.26
5 157.14 22.56 82 19.41 15.068 22.37
1 35.71 6.77 108 7.91 15.215 92.35 E
2 78.57 9.02 140 12.83 15.215 18.59
3 92.86 15.79 170 14.94 15.215 1.84
4 128.57 13.54 205 17.10 15.265 10.73
5 157.14 22.56 82 19.41 15.215 21.61

表4

K/S实验值和K/S预测值的对比"

实验
号		 实验方案 K/S值 相对
误差/%
X1 X2 X3 实验值 预测值
1 60.71 5.26 160 11.49 11.366 1.08
2 96.43 24.44 110 14.77 15.008 1.61
3 117.86 12.03 78 14.68 14.801 0.82
4 142.86 17.30 130 18.43 18.411 0.10
5 160.71 10.15 220 15.92 15.708 1.33
[1] 李连颖, 臧少玉, 毛志平 , 等. 平绒织物湿蒸短流程轧染工艺条件的优化[J]. 印染助剂, 2010,27(1):45-48.
LI Lianying, ZANG Shaoyu, MAO Zhiping , et al. The optimization of short wet-steam process in pad-dyeing panne fabric[J]. Textile Auxiliaries, 2010,27(1):45-48.
[2] 李连颖, 王天靖, 陈志华 , 等. ECO活性染料湿蒸短流程和轧烘轧蒸染色工艺[J]. 印染助剂, 2010,27(2):39-42.
LI Lianying, WANG Tianjing, CHEN Zhihua , et al. Short wet-steam process and pad-dry-pad-steam dyeing process of ECO reactive dye[J]. Textile Auxiliaries, 2010,27(2):39-42.
[3] 汪岚, 金福江 . 活性染料上染率的多元预测模型分析[J]. 纺织学报, 2008,29(8):78-80.
WANG Lan, JIN Fujiang . Analysis of reactive dye uptake-rate of multivariate regression[J]. Journal of Textile Research, 2008,29(8):78-80.
[4] 姜会钰, 杨锋, 王振东 , 等. BP神经网络预测活性染色织物K/S值[J]. 印染, 2007(9):23-24.
JIANG Huiyu, YANG Feng, WANG Zhendong , et al. K/S value prediction of the reactive dyeing with BP nerve network[J]. China Dyeing & Finishing, 2007(9):23-24.
[5] GESTEL T V, SUYKENS J A K, BAESENS B, et al. Benchmarking least squares support vector machine classifiers[J]. Machine Learning, 2004,54(1):5-32.
[6] WU Yonghong, SHEN Hui . Grey-related least squares support vector machine optimization model and its application in predicting natural gas consumption demand[J]. Journal of Computational and Applied Mathematics, 2018,338:211-220.
[7] MAO Xuefei, WANG Yijun, LIU Xiangdong , et al. A hybrid feedforward-feedback hysteresis compensator in piezoelectric actuators based on least squares support vector machine[J]. IEEE Transactions on Industrial Electronics, 2018,65(7):5704-5711.
[8] FU Li, LUO Jun, CHEN Weimin , et al. LS-SVM-based surface roughness prediction model for a reflective fiber optic sensor[J]. Chinese Optics Letters, 2017,15(9):61-65.
[9] 王建国, 张文兴 . 支持向量机建模及其智能优化[M]. 北京: 清华大学出版社, 2015: 32-33.
WANG Jianguo, ZHANG Wenxing. Support Vector Machine Modeling and Intelligent Optimization[M]. Beijing: Tsinghua University Press, 2015: 32-33.
[10] 王克奇, 杨少春, 戴天虹 , 等. 采用遗传算法优化最小二乘支持向量机参数的方法[J]. 计算机应用与软件, 2009,26(7):109-111.
WANG Keqi, YANG Shaochun, DAI Tianhong , et al. Method of optimizing parameter of least squares support vector machines by genetic algorithm[J]. Computer Applications and Software, 2009,26(7):109-111.
[11] 齐亮 . 基于蚁群算法的支持向量机参数选择方法研究[J]. 系统仿真技术, 2008,4(1):14-18.
QI Liang . Parameters selection of support vector machine based on ant colony algorithm. system simulation technology[J]. System Simulation Technology, 2008,4(1):14-18.
[12] 曾勍炜, 徐知海, 吴键 . 基于粒子群优化和支持向量机的电力负荷预测[J]. 微电子学与计算机, 2011,28(1):147-149, 153.
ZENG Qingwei, XU Zhihai, WU Jian . Forecasting of electricity load based on particle swarm optimization and support vector machine[J]. Microelectronics & Computer, 2011,28(1):147-149, 153.
[1] 李庆, 管斌斌, 王雅, 刘天卉, 张洛红, 樊增禄. 光敏剂敏化Cu-有机骨架对活性深蓝K-R 的高效光催化降解[J]. 纺织学报, 2020, 41(10): 87-93.
[2] 丁永生, 代亚敏, 钟毅, 徐红, 毛志平, 张琳萍, 陈支泽. 棉纱线在活性染料皮克林乳液体系中的染色动力学[J]. 纺织学报, 2020, 41(07): 101-108.
[3] 张炜, 毛庆楷, 朱鹏, 柴雄, 李惠军. 乙醇/ 水体系中改性蚕丝织物的活性染料染色动力学和热力学[J]. 纺织学报, 2020, 41(06): 86-92.
[4] 吴伟, 陈小文, 钟毅, 徐红, 毛志平. 硫酸钠在低带液轧-焙-蒸活性染料染色中的作用[J]. 纺织学报, 2020, 41(05): 85-93.
[5] 尉腾祥, 李敏, 彭虹云, 付少海. 纬平针棉针织物平幅丝光条件与其线圈结构的关系[J]. 纺织学报, 2020, 41(04): 98-105.
[6] 王秋平, 毛志平, 钟毅, 徐红, 张琳萍. 平幅轧染中针织物形变对染色的影响[J]. 纺织学报, 2019, 40(11): 94-99.
[7] 尉腾祥, 李敏, 彭虹云, 付少海. 纬平棉针织物双向拉伸线圈形态分析[J]. 纺织学报, 2019, 40(11): 64-68.
[8] 何青青, 徐红, 毛志平, 张琳萍, 钟毅, 吕景春. 高导电性聚吡咯涂层织物的制备[J]. 纺织学报, 2019, 40(10): 113-119.
[9] 张帆 张儒 周文常 周辉 汪南方. 金属铜配合物催化双氧水用于棉针织物的低温漂白[J]. 纺织学报, 2019, 40(08): 101-108.
[10] 杨海贞, 房宽峻, 刘秀明, 蔡玉青, 安芳芳, 韩双. 棉织物组织结构对墨滴铺展及颜色性能的影响[J]. 纺织学报, 2019, 40(07): 78-84.
[11] 王阿明 夏良君 王运利. 活性红195 在中性电解质溶液中的聚集行为[J]. 纺织学报, 2019, 40(04): 77-82.
[12] 吴臣仁, 吕汪洋, 陈文兴. 铜配合物在棉针织物低温中性漂白中的应用[J]. 纺织学报, 2019, 40(01): 91-96.
[13] 李佳平 沈国康 欧耀明 孟想 辛斌杰. 应用连续投影算法及最小二乘支持向量机的单组分纺织品识别[J]. 纺织学报, 2018, 39(08): 46-51.
[14] 舒大武 房宽峻 刘秀明 刘曰兴 蔡玉青 门雅静 李付杰. 活性染料无盐连续轧-蒸与冷轧堆染色效果的比较[J]. 纺织学报, 2018, 39(04): 77-81.
[15] 安亚洁 李敏 杜长森 田安丽 张奕 付少海. 微量墨滴在蚕丝机织物上的扩散行为[J]. 纺织学报, 2018, 39(04): 87-92.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
京ICP备14006648号　 京公网安备11010502044800号
版权所有 © 2021 《纺织学报》编辑部
地址： 北京市朝阳区延静里中街3号主楼6层《纺织学报》杂志社　邮政编码：100025　
电话：010-65017711,65917740　传真：010-65016539　Email:fangzhixuebao@vip.126.com
本系统由北京玛格泰克科技发展有限公司设计开发