羊毛纤维平均直径检测结果差异性分析  被引量:1

Difference analysis on the test results of average diameter of wool fibers

在线阅读下载全文

作  者:徐静[1] 董绍伟 XU Jing;DONG Shaowei(Basic Science Department,Yangzhou Polytechnic Institute,Yangzhou,Jiangsu 225127,China;Nanjing Customs District Industrial Products Inspection Center,Nanjing,Jiangsu 210019,China)

机构地区:[1]扬州工业职业技术学院基础科学部,江苏扬州225127 [2]南京海关工业产品检测中心,江苏南京210019

出  处:《毛纺科技》2023年第11期96-101,共6页Wool Textile Journal

摘  要:为了提高羊毛纤维平均直径检测的精准度,研究光学纤维直径分析仪法、气流仪法和激光扫描法测量结果的差异性,分别运用3种仪器对2017—2022年12期国际羊毛实验室的96个毛条比对样品进行细度测量。通过Mann-Whitney U法检验3组数据总体两两之间的差异,运用聚类算法将数据分组,进一步研究不同聚类区间数据的差异性。结果表明:3种方法测量总体结果在95%的置信区间下是无显著性差异的,但在数据值较小和较大区间内存在显著差异;当存在显著差异时,3种测量方法之间可建立回归关系;羊毛纤维平均直径测试结果差异性减少,可以有效应用于羊毛贸易,促进羊毛产业健康良好发展。In order to improve the accuracy of wool fiber average diameter detection,the difference of measurement results of optical fiber diameter analyzer,airflow meter and laser scanning method was studied,and the fineness of 96 wool comparison samples from 12 international wool laboratories from 2017 to 2022 was measured by three kinds of instruments respectively.The difference between the overall pairwise of the three groups of data was tested by Mann-Whitney U method,and the data were grouped by clustering algorithm to further study the difference of data in different cluster intervals.The results show that there is no significant difference between the three methods in the 95%confidence interval,but there are significant differences between the smaller and larger data intervals.When there is a significant difference,the regression relationship between the three measurement methods can be established,and the difference of the average diameter test results of wool fiber is reduced,which can be effectively applied to wool trade and promote the healthy development of wool industry.

关 键 词:羊毛平均直径 假设检验 K-MEANS聚类 回归分析 

分 类 号:TS137[轻工技术与工程—纺织材料与纺织品设计]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象