ARL computation and parameters optimization for MEWMA control chart based on the Markov chain
-
摘要: 平均运行链长(ARL)是控制图性能评价的一个重要指标,深入研究ARL是控制图参数优化、性能评价和实际应用的重要工作.在采样数据标准化处理的基础上,应用马尔可夫链进一步研究了多元指数移动平均(MEWMA)控制图中ARL计算的数学模型,采用Matlab实现了算法,就算法的收敛性及计算结果进行分析.以ARL为优化指标,给出了MEWMA控制图参数优化的具体步骤、计算实例和参数优化结果.Abstract: Average run length(ARL) is one of the important indices in performance evaluation on quality control charts, the research on which will set up the foundation of quality control chart parameters optimization, performance evaluation and application. An ARL computation model based on the Markov chain was studied for the multivariate exponentially weighted moving average(MEWMA) control chart, the Matlab program was designed and implemented. The convergence of the algorithm and the performance of the MEWMA control chart in different conditions through the analysis of the computation results were analyzed. A procedure for parameters optimization of MEWMA control chart was proposed. An computation example and some optimization results was presented.
-
[1] Brook D, Evans D A. An approach to the probability distribution of CUSUM length [J]. Biometrika, 1972, 59:539-549 [2] Runger G C, Prabhu S S. A Markov chain model for the multivariate exponentially weighted moving averages control chart [J]. Journal of the American Statistical Association, 1996, 91(436):1701-1706 [3] Lowry C A, Woodall W H. A multivariate exponentially weighted moving average control chart[J]. Technometrics, 1992, 34(1):46-53 [4] Rigdon S E. A double-integral equation for the average run length of a multivariate exponentially weighted moving average control chart [J]. Statistics & Probability Letters, 1995,24:365-373 [5] Prabhu S S, Runger G C. Designing a multivariate EWMA control chart[J]. Journal of Quality Technology, 1997, 29(1):8-15 [6] Sonesson C. Evaluations of some exponentially weighted moving average methods [J]. Journal of Applied Statistics, 2003, 30(10):1115-1133 -
点击查看大图
计量
- 文章访问数: 3537
- HTML全文浏览量: 192
- PDF下载量: 1455
- 被引次数: 0
下载:
