基于要素匹配的连衣裙成本快速核算方法  

Cost rapid accounting technology of dress based on element matching

作　　者：夏明[1,2] 李沛儒 丁蓉 XIA Ming;LI Peiru;DING Rong(College of Fashion and Design, Donghua University, Shanghai 200051, China;Key Laboratory of Clothing Design and Technology, Ministry of Education, Donghua University, Shanghai 200051, China)

机构地区：[1]东华大学服装与艺术设计学院,上海200051 [2]东华大学现代服装设计与技术教育部重点实验室,上海200051

出　　处：《纺织学报》2022年第3期146-152,共7页Journal of Textile Research

基　　金：中央高校基本科研业务费专项资金资助项目(2232020G-08)。

摘　　要：为提高企业对服装成本的快速核算能力,就服装成本计算和相似度匹配的方法进行了研究。首先以连衣裙要素提取和量化为基础,计算同一要素之间的相似度;然后基于加权欧式距离计算样本相似度,取相似度最大的样本成本值做为待估样本成本的参考值,实现成本的快速核算。同时设置了欧氏距离计算和BP神经网络2组对照实验。结果表明:使用加权欧氏距离计算的匹配效果最佳,其次是欧式距离,最后为人工神经网络;使用加权欧式距离计算的面布成本、里布成本和服装加工成本误差平均值分别为7.44%、8.90%、6.11%,满足企业服装成本核算精度要求。In order to improve the ability of enterprises to quickly calculate clothing cost,the methods of cost calculation and similarity matching of clothing was studied.Firstly,calculate the similarity between the same elements based on the dress elements extraction and quantification;Secondly,calculate the sample similarity by using weighted Euclidean distance and take the largest similarity sample cost as dress sample cost.At the same time,Euclidean distance calculation and BP neural network calculation were set up for comparison.The results show that the matching effect of weighted Euclidean distance calculation is the best.The average error of face cloth cost,lining cost and clothing processing cost calculated by weighted Euclidean distance is 7.44%,8.90%,6.11%,which meet the accuracy requirement for enterprise cost accounting.

关 键 词：连衣裙 成本核算 模糊量化 加权欧式距离 神经网络 

分 类 号：TS941.17[轻工技术与工程—服装设计与工程]