|本期目录/Table of Contents|

[1]周俊文,宋晓霞.基于GRNN神经网络的面料热阻预测模型研究[J].丝绸,2018,55(8):081108.[doi:10.3969/j.issn.1001-7003.2018.08.008]
 ZHOU Junwen,SONG Xiaoxia.thermal resistance prediction model of fabrics based on general regression neural network[J].Journal of Silk,2018,55(8):081108.[doi:10.3969/j.issn.1001-7003.2018.08.008]
点击复制

基于GRNN神经网络的面料热阻预测模型研究(PDF)
分享到:

《丝绸》[ISSN:1001-7003/CN:33-1122/TS]

卷:
55
期数:
2018年8期
页码:
081108
栏目:
研究与技术
出版日期:
2018-08-20

文章信息/Info

Title:
thermal resistance prediction model of fabrics based on general regression neural network
文章编号:
1001-7003(2018)08-0041-06
作者:
周俊文宋晓霞
上海工程技术大学 服装学院,上海 201620
Author(s):
ZHOU Junwen SONG Xiaoxia
 School of Fashion Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
关键词:
热阻预测神经网络GRNNBP
Keywords:
thermal resistance prediction neural network GRNN BP
分类号:
TS941.15
doi:
10.3969/j.issn.1001-7003.2018.08.008
文献标志码:
A
摘要:
热阻是衡量面料热舒适性的一项重要指标,为获得不同环境下面料的热阻值,多采用测试获得。文章通过YG(B)606G 型纺织品热阻和湿阻测试仪,对不同面料在不同环境下的热阻进行测试。运用Matlab,基于GRNN(General Regression Neural Network)广义回归神经网络,使用少量输入参数,对不同环境下的热阻值进行预测。与传统的测试相比,GRNN神经网络实验量小,方便快捷、省时省力且预测结果准确性好;与BP(Back Propagation)神经网络相比,GRNN神经网络人为设定量更少,更为客观,预测结果更加准确。经Wilcoxon符号秩检验配对样本检验发现,GRNN神经网络预测值与实际值更加接近,可信度更强。
Abstract:
Thermal resistance is an important measurement index of the thermal comfort of fabrics. The heat resistance value of fabrics in different environments is mostly gained by testing. Thermal resistance values of different fabrics were tested under different environments through YG (B) 606G textile thermal resistance and moisture resistance equipment. Thermal resistance values of fabrics under different environments were predicted with a few input parameters by Matlab and GRNN (General Regression Neural Network). Compared with traditional test, smaller experiment indexes are needed by using GRNN. At the same time, the method is simpler, more convenient and more accurate. Compared with BP(Back Propagation) neural network, fewer subjective indexes are needed in GRNN, so the prediction result of the model is more objective and more accurate. Wilcoxon signed rank test paired sample test result indicates that, the predictions of GRNN are more accurate and more reliable.

参考文献/References:

[1]于瑶, 钱晓明. 针织服装热湿舒适性预测模型[J]. 纺织学报, 2011, 32(12): 108-118.
YU Yao, QIAN Xiaoming. Prediction model of thermal-wet comfort of knitted garments [J]. Journal of Textile Research, 2011, 32(12): 108-118.
[2]李云凤. 不同混纺比下仿棉聚醋针织物热湿舒适性研究[D]. 上海: 东华大学, 2014: 9-12.
LI Yunfeng. Study on Heat-Moisture Comfort of Cotton-Like Polyester Knitted Fabrics with Various Blend Ratios [D]. Shanghai: Donghua University, 2014: 9-12.
[3]柯莹, 李俊. 服装通风对主观热湿舒适感的影响[J].纺织导报, 2016(12): 72-74.
KE Yin, LI Jun. Effects of clothing ventilation on subjective thermal-wet comfort sensations [J].China Textile Leader, 2016(12): 72-74.
[4]王林玉. 基于人工神经网络的针织内衣面料热湿舒适性评价及预测[D]. 青岛: 青岛大学, 2006: 3-18.
WANG Linyu. Evaluation and Prediction for Knit Inner Wear Comfort Proper Based on Artificial Neural Network [D]. Qingdao: Qingdao University, 2006: 3-18.
[5]蒋培清, 唐世君, 谌玉红. 夏季服用织物动态热湿舒适性的影响因素研究[J]. 中国纺织大学学报, 1999, 25(2): 9-13.
JIANG Peiqing,TANG Shijun,SHEN Yuhong. Study on the factors to influence dynamic heat-moisture comfort of summer clothing fabrics [J]. Journal of China Textile University , 1999, 25(2): 9-13.
[6]丁殷佳. 风速与汗湿对运动服面料热湿舒适性的影响及综合评价[D]. 杭州: 浙江理工大学, 2015: 36-47.
DING Yinjia.The Influence and Comprehensive Evaluation of Air Velocity and Sweat on Thermal-Wet Comfort of Sportswear Fabrics [D]. Hangzhou: Zhejiang Sci-Tech University, 2015: 36-47.
[7]王小川, 史峰, 郁磊. MATLAB神经网络43个案例分析[M]. 北京: 北京航空航天大学出版社, 2013(8): 67-73.
WANG Xiaochuan, SHI Feng, YU Lei. The 43 Cases Analysis of MATLAB Neural Network [M]. Beijing: National Defense Industry Press, 2013(8): 67-73.
[8]闻新, 李新, 张兴旺, 等. 应用MATLAB实现神经网络[M]. 北京: 国防工业出版社, 2015(6): 205-223.
WEN Xin, LI Xin, ZHANG Xingwang,et al. The Application of MATLAB Neural Network [M]. Beijing: National Defense Industry Press, 2015(6): 205-223.
[9]楚艳艳, 汪青, 崔世忠, 等. 基于组合神经网络模型对纺织品热阻与湿阻的估计研究[J]. 丝绸, 2008(4): 40-42.

备注/Memo

备注/Memo:
收稿日期:2017-06-17
修回日期:2018-00-00
作者简介:周俊文(1993—),女,硕士研究生,研究方向为服装舒适性
通信作者:宋晓霞,教授,songxiaoxiavivian@126.com
更新日期/Last Update: 2018-06-29