摘要
提出了一种基于改进型模糊聚类的缝纫平整度客观评价系统。首先,用FAST仪器测量得到服装面料的各项力学性能指标,并根据主因子分析法提取6个贡献最大的综合指标;其次,通过基于输出空间的SFCM算法对获取的综合指标进行模糊聚类,得到相应的各聚类中心;最后,根据聚类结果确定径向基神经网络的节点中心和宽度。经过大量实验,系统可以根据中厚毛型面料的不同结构及物理性能快速准确地给出该织物成衣后的缝纫性能评价指标。
In this paper,an objective evaluation system based on improving fuzzy clustering is proposed for seam pucker evaluation.In the first step we use FAST apparatuses to obtain the mechanical properties of fabric and extract 6 most important integrated indexes.Afterwards we apply supervised FCM based on output space to classify and get corresponding prototypes. According to the clustering results,we determine the prototypes and width of hidden nodes of RBF neural network finally. Experimental results demonstrate that the proposed approach could efficiently be used as an objective seam pucker evaluation system with high convergence and accuracy,which is robust for various structures and mechanical properties of thick woolen fabric.
出处
《计算机工程与应用》
CSCD
北大核心
2008年第9期212-216,共5页
Computer Engineering and Applications
关键词
缝纫平整度
径向基网络
监督模糊聚类
主因子分析
seam pucker grade
RBF neural network
supervised fuzzy clustering
principal factor analysis