基于模糊聚类的设备分组技术

Machines grouping base on fuzzy clustering

在动态联盟形成过程中 ,需要对候选企业的设备空间进行搜索 ,当设备数量较大时 ,设备搜索时间较长 ,求解时间增加 ,计算复杂度加大 .因此 ,采用设备分组方法 ,设备分组是减少设备搜索空间和时间的一个有效途径 .介绍了一种具有新的聚类有效性测度的扩展模糊C -均值聚类算法 (EFCM) ,根据设备所具有的工艺元素进行分组 ,形成功能加工单元 .EFCM算法具有新的聚类有效性测度 ,使同组设备具有最大紧密度 ,异组设备具有最大排斥度 ,分组更加合理 ,增强了模糊聚类算法的实用性 .具体实例验证了EFCM算法的实用性和有效性 .

It is necessary in the course of building the virtual organization to search the machine space. If there are lots of machines, the searching time is very long, and the complexity is very high. Then, machine groaping is used to resolve the problem. Machine grouping is an effective method to reduce searching space and time. An extended fuzzy c means (EFCM) clustering algorithm with a new cluster validity measure is proposed to group the machines according to their process elements. The machine grouping algorithm make the maximum compactness of the machines within the one group and maximum repellency of the machines between different groups, and it is better than FCM algorithm. The practical applicability of the fuzzy-c means clustering algorithm is improved. The example shows that EFCM algorithm is practical and effective.