监测Lévy稳定过程均值变点的平均运行时间估计

平均运行长度(时间)(ARL)是判断一控制图监测变点效果好坏的一个重要工具.本文主要研究Lévy稳定过程的均值变点监测问题.我们给出了三个控制图,即EWMA,GEWMA和GLR的ARL估计,并通过数值模拟比较了4个控制图监测均值变点的效果和差异.     

监测L\'{e}vy稳定过程均值变点的平均运行时间估计

平均运行长度(时间) (ARL)是判断一控制图监测变点效果好坏的一个重要工具\bd 本文主要研究L\'{e}vy 稳定过程的均值变点监测问题\bd 我们给出了三个控制图, 即EWMA, GEWMA和GLR的ARL 估计, 并通过数值模拟比较了4个控制图监测均值变点的效果和差异.     

铝、铜、镍三元合金系中τ相的晶体结构变迁

A thorough investigation by means of X-rays has been carried out with the purpose to determine the nature of the ternary phase τ in Al-Cu-Ni alloys. In contrast with the conventional concept of alloy phase which is characterized by a definite type of crystal structure, systematic structure changes are found in the single phase field of τ which occupies quite an extensive area in the isothermal section of the phase diagram at room temperature. There are eight types of structures altogether, all derived from a basic rhombohedron with corners occupied by Al atoms and centres either occupied by the heavy atoms or remaining vacant. The basic rhombohedron is the building stone in the crystal architecture. By transforming the basic rhombohedron into a hexagonal prism in the usual way, all structures may be considered to be built up by stacking together a number of these hexagonal prisms along the triad. The transformation of one structure into another is quite systematic in the way that the number of the stacking stories in the unit cell increases according to the order 10, 11, 12, 13, 14, 15, 16, 17. The atomic arrangements in the different structures are closely related too, in the respect that they are all superstructures due to the presence of ordered vacancies in the rhombohedral centres.The principal factor controlling the formation of these structures has been fully considered. In view of the fact that the change of structure types follows closely with the content of Ni or Cu for alloys of constant Al content, the atomic size factor appears to be unimportant in the formation of these alloys. It has been shown that for alloy phases of the defect lattice type as the r-phase, the most fundamental factor is the average number of valency electrons per structural unit which is the basic rhombohedron in the present case. By assuming Hume-Rothery's valencies, the average number of valency electrons remains remarkably constant throughout the entire phase field, while the electron concentration varies with compositions. It has also been pointed out that for alloy phases where there is no unit cell change, the average number of electrons per structural unit is equivalent to the number of electrons per unit cell, and for alloy phase where there is no defect, this is in effect equivalent to the electron concentration.     

CUSUM，GLR，GEWMA以及RFCuscore控制图监测稳定过程均值漂移的效果比较

本文给出了累积和控制图(CUSUM)监测稳定过程均值漂移的平均运行长度(ARL)的区间估计,并采用数字模拟的方法对CUSUM,GLR,GEWMA以及RFCuscore四种控制图监测稳定过程均值漂移的效果进行比较,结果显示CUSUM效果最好.     

监测均值变动的多重控制图方法

本文证明了当受控平均运行长度充分大时, 多重控制图有两个优点: 一是相比较GLR (广义似然比) 和GEWMA (广义指数权重移动平均)控制图它可以大大降低运算的复杂性; 二是能够较快地监测均值变化的大小. 数值模拟也表明: 多重控制图不仅优于其构成的单个控制图, 而且在监测未知的均值变动方面也优于单个的CUSUM, EWMA, 多重EWMA和GLR控制图.     

CUSUM,GLR,GEWMA以及RFCuscore控制图监测稳定过程均值漂移的效果比较(英)

本文给出了累积和控制图(CUSUM)监测稳定过程均值漂移的平均运行长度(ARL)的区间估计,并采用数字模拟的方法对CUSUM,GLR,GEWMA以及RFCuscore四种控制图监测稳定过程均值漂移的效果进行比较,结果显示CUSUM效果最好.     

Comparison of the cuscore, GLRT and cusum control charts for detecting a dynamic mean change

Although statistical process control (SPC) techniques have been focused mostly on detecting constant mean shifts, dynamic and time-varying process changes frequently occur in the monitoring of feedback-controlled and autocorrelated processes. In this research, the performances of cumulative score (Cuscore), generalized likelihood ratio test (GLRT), and cumulative sum (CUSUM) charts in detecting a dynamic mean change that finally approaches a steady-state value are compared. Theoretical results in average run length (ARL) comparison are provided. From the theretical study we find that, when the steady-state value is greater or less than a critical value,Rδ/2+δ/2, the Cuscore and CUSUM charts have a different performance in detecting the mean change. We prove also that the GLRT has the best performance among the three charts in detecting any mean change for which the steady-state value is not equal to δ or δR, when the in-control ARL is large.     

关于6Sigma管理中的1.5Sigma系统偏移

1 5sigma系统偏移是6Sigma管理中一个很重要的概念和度量值,这个值的解释和确定始终存在着很多的疑问和争议。本文从过程能力和控制图等概念入手,介绍了1.5Sigma系统偏移的由来和相关的理论基础,以及在网上的争议,并阐述了一些看法和对它进行研究的意义。