带参数估计的加权自适应多元累计和控制图及其应用  

Weighted Adaptive MCUSUM Control Charts With Parameter Estimation and Its Application

作　　者：敖银辉[1] 吴先沛 Ao Yinhui;Wu Xianpei(School of Electromechanical Engineering,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东工业大学机电工程学院,广州510006

出　　处：《统计与决策》2020年第10期28-32,共5页Statistics & Decision

摘　　要：针对多元累计和控制图(MCUSUM)在具体实施中缺乏整体协方差矩阵,以及无法确定过程的均值偏移的情况。文章提出了通过使用压缩估计法得到协方差矩阵,然后与自适应加权方法相结合来对统计量进行计算,利用蒙特卡洛模拟仿真法对控制图的平均运行链长进行计算,以此来描述控制图的性能。和传统方法计算统计量的控制图进行比较,结果表明文章提出的控制图在样本少、均值偏移不定的情况下性能较优。将控制图技术应用到锂电池行业,并在OCV工序中取得了较好的效果。In view of the lack of global covariance matrix in the concrete implementation of Multivariate Cumulative Sum(MCUSUM)control charts,and the mean shift process that cannot be determined,this paper proposes using compression estimation method to obtain the covariance matrix,and then combining with the adaptive weighting method to calculate the statistics.The paper also uses Monte Carlo simulation method to calculate the average running chain length of the control chart to describe the performance of the control chart.Compared with the control chart of the traditional method,the results show that the proposed control chart has better performance in the case of fewer samples and variable mean deviation.Finally,the proposed control chart technology is applied to lithium battery industry and good results are obtained in OCV process.

关 键 词：多元累计和控制图 协方差矩阵估计 均值偏移 蒙特卡洛 

分 类 号：O213.1[理学—概率论与数理统计]