面向小批量生产过程的多变量贝叶斯控制图  

Economically designed multivariate Bayesian control chart for short-run production

作　　者：张鹏伟[1,2,3] 苏秦[1,2,3] 李乘龙[1,2,3] 

机构地区：[1]西安交通大学管理学院,陕西西安710049 [2]机械制造系统工程国家重点实验室,陕西西安710049 [3]过程控制与效率工程教育部重点实验室,陕西西安710049

出　　处：《系统工程学报》2013年第3期387-393,共7页Journal of Systems Engineering

基　　金：国家自然科学基金资助项目(70872091);高等学校博士点专项基金资助项目(20090201110031)

摘　　要：针对多维数据的贝叶斯更新难题,首先利用变量转换将多变量的贝叶斯更新公式转变为单变量更新公式.在对过程状态进行重新划分的基础上,利用马尔科夫链分别构造了不同情形下的贝叶斯过程状态转移矩阵,区分了扰动发生的不同时刻对于成本函数的影响.利用迭代的思想构造了过程的成本函数,在此基础上最终构造了面向小批量生产过程的多变量控制图优化模型.仿真结果表明,相比于已有的多变量控制图,本文设计的控制图可以有效地降低过程成本,因此具有更大的实用价值.Dealing with the Bayesian updation of multivariate data, we convert the multivariate Bayesian updation into a univariate one using variable conversion. Based on new partition of process state, process transition matrices under different scenarios were constructed employing Markov chain method. Thus, the influence of the disturbance occurrence time on process cost was taken into consideration. A process cost function was constructed iteratively, and finally a multivariate control chart optimization model for short-run production was formulated. Simulation results show that, compared with the existing multivariate control chart, the control chart proposed in this paper can reduce the process cost effectively, therefore has greater application value.

关 键 词：小批量生产 多变量控制图 贝叶斯更新 

分 类 号：F253.3[经济管理—国民经济]