基于区间数聚类分析的多属性瓶颈区域识别方法

制造业生产环境复杂,瓶颈现象的出现会制约其发展.针对利用单一数据识别单个瓶颈机器的方法难以具体描述系统瓶颈的问题,提出了一种基于区间数聚类分析的多属性瓶颈区域识别方法.首先采用k-means++聚类分析方法,根据决策矩阵比较各指标的相似程度,找出不同距离下的机器区域.然后利用决策矩阵求出的可能度矩阵排序向量找出各区域的...

Multi-attribute bottleneck region identification method based on interval number cluster analysis

The production environment of manufacturing industry is complex,and the emergence of bottleneck phenomenon will restrict its development.In order to solve the problem that it is difficult to describe the system bottleneck by using single data to identify a single bottleneck machine,a multi-attribute bottleneck region identification method based on interval number cluster analysis was proposed.Firstly,the k-means++clustering method was used to compare the similarity degree of each index according to the decision matrix,and the machine regions under different distances were found out.Then,the ordering vector of the probability matrix obtained by the decision matrix was used to find out the leading machines in each region,and the bottleneck region was determined after comparison.Finally,an example was given to verify the effectiveness and accuracy of the proposed method.