一种云模型相似性度量方法  

A New Similarity Measurement Method for Cloud Models

作　　者：黄琼桃 刘瑞敏[1] HUANG Qiong-tao;LIU Rui-min(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《控制工程》2022年第9期1600-1604,共5页Control Engineering of China

基　　金：国家自然科学基金资助项目(61163051)。

摘　　要：针对现有方法存在的区分度不高、运行时间代价过高等问题,提出一种云模型相似性度量方法。首先采用云模型的扩展模型三角云模型作为研究对象,将三角云模型看作对称三角模糊数,根据EW-型距离公式引入指数贴近度概念,并用其表征云模型的距离相似度;然后通过云模型云滴的方差,计算出云模型的形状相似度;最后将云模型的距离与形状相似度综合起来,共同衡量两云模型的相似度。从仿真实验可以看出,该方法有较高的区分度;对Synthetic control chart data数据集进行的分类实验表明,该方法具有较好的分类精度及较小的运行时间代价。Aiming at the problems of low discrimination and high run-time cost in the existing methods, a similarity measurement method for cloud models is proposed. First, the triangle cloud model, an extended model of the cloud model, is used as the research object. The triangle cloud model is regarded as a symmetric triangular fuzzy number. According to the EW-type distance formula, the concept of exponential closeness is introduced and used to represent the distance similarity of the cloud model. Then, the shape similarity of the cloud model is calculated by the variance of the cloud drop. Finally, the distance similarity and the shape similarity are integrated to jointly measure the similarity of the two cloud models. It can be seen from the simulation experiment that the method has high discrimination. The classification experiment on the synthetic control chart data shows that the method has good classification accuracy and low run-time cost.

关 键 词：三角云模型 对称三角模糊数 指数贴近度 相似性度量 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]