基于单个观测值用于检测多元协方差矩阵的EWMA控制图

基于单个样本观测值提供了一个指数加权移动平均(EWMA)控制图用于监测p维多元正态过程协方差矩阵的飘移。模拟研究表明,此图对各种形式的飘移都有很好的表现,且不受均值变化的影响。实例表明,新设计的控制图在实际应用中具有很好的表现。     

两阶段抽样中位值-极差联合控制图

在统计质量控制中,通常利用中位值图和极差图来控制生产过程的均值和方差.建立了两阶段中位值和极差联合控制图,在第一阶段抽取一个样本进行检测,如果过程处于控制,就停止抽样,否则进行第二阶段抽样检测.文中将其与其他类型的中位值-极差联合控制图做了比较.结果表明,两阶段抽样控制图能更有效地检测生产过程的波动变化.     

基于定数截尾样本监控Weibull分布形状参数的控制图设计

基于定数截尾样本提出了单侧和双侧ARL无偏控制图监控Weibull分布形状参数的变化.提出的控制图仅依赖于样本容量n,失效数r和指定的受控平均链长ARL0.利用模拟方法研究了常见(r,n)组合下提出的控制图在失控状态下的平均链长性质.模拟结果显示,对于形状参数小和中等的向下飘移,文中提出的控制图要优于现有文献的结果.特别是对形状参数中等程度的向下飘移,当失效数r较大时,提出的控制图的平均链长比现有结果小了近一半.由于单侧控制图比双侧控制图能更快地发出报警信号,故建议应尽可能地使用单侧控制图监控形状参数变化.最后用一个例子说明了所提控制图的应用.     

可变抽样区间同时监控均值标准差的EWMA控制图

传统的EWMA控制图分别针对监控过程均值变化和监控过程标准差变化进行研究,在实际生产中,很多情形需要同时监控过程均值变化和过程标准差变化。为了提高控制图的监控效率,本文研究了同时监控均值和标准差变化时,EWMA控制图的可变抽样区间设计。其次运用马科夫链法计算可变抽样区间EWMA控制图的平均报警时间;然后与传统的EWMA控制图进行比较得出:同时监控均值和标准差时,可变抽样区间的EWMA控制图能够更快地发现过程中的异常波动,具有较短的平均报警时间,其监控效率明显优于传统的EWMA控制图。     

一种带链规则的变样本容量X图

将一种链规则和变化样本容量的思想一起并入休哈特均值图以加快其发现过程均值小漂移的速度.利用马氏链方法计算了控制图稳态表现下的平均链长.与几种图的比较显示,该图能显著加速发现过程均值小的漂移.     

基于小波的预分析稳健控制图

本文提出了一种基于小波的预分析控制图, 用于监测第一阶段过程控制中的均值飘移. 该方法的基本思想是利用多个不同尺度下的一些相对较大的小波系数来探查过程中的异常变化. 这个控制图具有很好的稳健性, 所以特别适用于像预分析过程中这样的对分布信息知之甚少的情形.     

可变抽样区间几何EWMA控制图的经济设计

为了降低生产过程周期成本,本文对单位缺陷数服从几何分布时,可变抽样区间的指数加权移动平均(EWMA)控制图进行经济设计。首先建立可变抽样区间几何EWMA控制图的经济模型,使单位时间期望费用最小来确定参数的最优值;其次用遗传算法来寻找经济模型的最优解;最后对可变抽样区间几何EWMA控制图的经济模型进行灵敏度分析和最优性分析。研究结果表明单位时间期望费用分别随着异常原因发生的频率、过程失控时单位时间的质量费用、发现异常原因的时间期望值和纠正过程的时间期望值的增大而增大。     

可变抽样区间的多变量自相关过程VAR控制图

基于批量-均值法的思想,向量自回归(VAR)控制图对多变量自相关过程的较小偏移可以进行有效控制。为了提高多变量自相关过程监控效率,本文研究可变抽样区间的VAR控制图。首先,对多变量自相关过程的VAR控制图进行可变抽样区间设计;然后,用蒙特卡洛模拟方法计算其平均报警时间;最后,以平均报警时间为评价准则,对所设计的可变抽样区间VAR控制图与固定抽样区间的VAR控制图进行比较研究。研究结果表明:所设计的可变抽样区间多变量自相关过程VAR控制图较固定抽样区间的多变量自相关过程VAR控制图能更好的监控过程的变化。     

复杂机电产品多元FT VSI贝叶斯控制图性能研究

针对复杂机电产品质量控制与预警困难的问题,构建一种将多元贝叶斯统计方法与经济性能分析相结合的多元贝叶斯控制图性能分析模型.在求解模型中,多元贝叶斯控制图采用固定时间变抽样区间(Fixed Time Variable Sample Interval, FT VSI)策略,若非随机故障小概率发生,则选择宽松抽样方案;若非随机故障大概率发生,则选择严抽样方案.为量化多元贝叶斯控制图经济性能与统计性能的相关度,利用蒙卡罗模拟分析的质量控制模型进行仿真,并在不同经济性参数下,得到采样单位平均数(Average Number of Observations to Signals or End of the production run, ANOSE)对于控制图统计性能的影响程度,进而引出多元贝叶斯控制图的质量控制成本与其误报率的影响程度,并以某型号汽车自动变速器多元质量控制过程为例对多元FT VSI贝叶斯控制图性能评价与优化成果进行验证,结果证明该方法具有较好的应用性.     

多元统计过程控制中的投影寻踪方法

投影寻踪（projection pursuit,简称PP）方法是通过高维数据在低维投影上的统计分析,由此充分获取高维数据本身的统计和信息的一类统计方法,并在统计过程控制中得到广泛应用,本文主要介绍利用投影寻踪方法在统计过程控制中所构造的新控制图及其优良性质,它们包括：监测线性趋势的M控制图,监测均值微小飘移的PP－CUSUM控制图以及矩链过程的多元控制图。     

可变参数的联合中位值和极差控制图

最近设计了可变样本容量和抽样区间的联合中位值$(\wt{x})$和极差$(R)$控制图$^{[1]}$, 本文利用Costa的可变参数控制图的方法$^{[2]}$, 设计包括可变控制限的可变参数的联合$\wt{x}$和$R$图(CVP $\wt{x}$--$R$图). 计算了在可变参数下发信号前的平均时间, 并同联合常规$\wt{x}$--$R$图(CFSSI图)和可变样本容量和抽样区间的联合$\wt{x}$--$R$图(CVSSI图)作比较, 所设计的控制图能较快地发现过程平均值和方差的小变化, 提高CVSSI图的效率     

Dynamic sample budget allocation in model-based optimization

Model-based search methods are a class of optimization techniques that search the solution space by sampling from an underlying probability distribution “model,” which is updated iteratively after evaluating the performance of the samples at each iteration. This paper aims to improve the sampling efficiency of model-based methods by considering a generalization where a population of distribution models is maintained and subsequently propagated from generation to generation. A key issue in the proposed approach is how to efficiently allocate the sampling budget among the population of models to maximize the algorithm performance. We formulate this problem as a generalized max k-armed bandit problem, and derive an efficient dynamic sample allocation scheme based on Markov decision theory to adaptively allocate computational resources. The proposed allocation scheme is then further used to update the current population to produce an improving population of models. Our preliminary numerical results indicate that the proposed procedure may considerably reduce the number of function evaluations needed to obtain high quality solutions, and thus further enhance the value of model-based methods for optimization problems that require expensive function evaluations for performance evaluation.     

Steady-state-optimal adaptive control charts based on variable sampling intervals

Variable sampling interval (VSI) control charts vary the sampling rate adaptively as a function of the data coming from the process in order to reduce the detection delay of process changes. Zero-time performance refers to the detection delay of a process change that is present during the onset of the chart at time zero. Steady-state performance refers to the detection delay of a process change that occurs after the chart has been operating for some time. The zero-time performance of a VSI control chart can differ considerably from the chart's steady-state performance, which is generally more important than the zero-time performance. We develop an efficient quadratic-programming algorithm for the construction and investigation of steady-state-optimal sampling policies for various VSI charts. We show that a steady-state-optimal VSI scheme is fundamentally different from the respective zero-time-optimal VSI scheme, and recommend VSI policies based on two sampling intervals for the various types of control charts considered.     

A theory of motivation and satisfaction with application to decision support

The paper deals with optimization of allocation of human resources among different activities. It is assumed that an individual is characterized by a risk averse and constant return to scale utility function of two variables: motivation to perform and reward following the performance. The individual is trying to maximize the utility by the best allocation of his time resources among the activities and by selecting the best portfolio of activities. Motivations are regarded, generally, as the product of the individual's preferences (i.e. subjective choice probabilities), productivities of time, output prices, performance and access probabilities, etc., while the rewards are profits or salaries connected with each activity. Satisfaction is defined as the maximum of utility attained for the optimum allocation and selection strategies. It is shown that for the given equitable reward rate, the optimum allocation and portfolio selection strategies can be derived explicitly and the derivation does not require the explicit knowledge of the individual's utility function.     

Arrangement Increasing Resource Allocation

Consider a system composed of several units. The performance of each unit can be affected by providing a portion of a limited amount of costly resources available. An allocation of resources to a unit results in a unit’s response that depends on the level of resources allocated to it and some of its random parameters. In this paper we consider cases where each unit has one or two random parameters. The overall performance of the system is mapped by a function on the vector of responses generated by all the units in the system. Our interest is in identifying the conditions on the response function of the units, the system performance function and the random parameters under which the random system performance as a function of the resource allocation has stochastic arrangement increasing property. This allows one to substantially reduce the number of allocation that needs to be searched to identify an optimal allocation that maximizes the expected utility derived from the system response as a result of the resource allocation.     

可变抽样区间的单边控制图

利用质量控制图监督生产过程时 ,通常每隔固定时间从过程抽取固定容量的样本。本文在前文[1] 的基础上设计具有可变抽样区间的单边标准差 (S)图、极差 (R)图和不合格品数 (np)图。计算了这三个图发信号前的平均样本数和平均时间 ,并同固定抽样区间的常规控制图作比较。所设计的控制图能缩短过程失控时间从而减少不合格品数。     

基于测量质量损失函数的控制图控制界限的优化

控制界限和抽样间隔是控制图的两个基本参数。常规控制图是基于3σ原理确定的控制界限,该控制界限是在大量试验基础上依据经验确定的,并没有精确的公式推导.对于抽样间隔,常规控制图也没有明确的规定。田口博士的质量损失函数可以很好的解决质量经济性方面的一些问题.利用田口博士的理论,通过确定适宜的二次测量质量损失函数,可以确定控制图的最佳控制界限和最佳抽样间隔.文章简要介绍了常规控制图原理和田口博士的质量损失函数,重点叙述了田口博士反馈控制系统的测量质量损失函数,在此基础上,研究了控制图最佳控制界限和最佳抽样间隔,并且通过具体实例验证了该控制图良好的经济性.     

Joint economic design of EWMA control charts for mean and variance

Control charts with exponentially weighted moving average (EWMA) statistics (mean and variance) are used to jointly monitor the mean and variance of a process. An EWMA cost minimization model is presented to design the joint control scheme based on pure economic or both economic and statistical performance criteria. The pure economic model is extended to the economic-statistical design by adding constraints associated with in-control and out-of-control average run lengths. The quality related production costs are calculated using Taguchi’s quadratic loss function. The optimal values of smoothing constants, sampling interval, sample size, and control chart limits are determined by using a numerical search method. The average run length of the control scheme is computed by using the Markov chain approach. Computational study indicates that optimal sample sizes decrease as the magnitudes of shifts in mean and/or variance increase, and higher values of quality loss coefficient lead to shorter sampling intervals. The sensitivity analysis results regarding the effects of various inputs on the chart parameters provide useful guidelines for designing an EWMA-based process control scheme when there exists an assignable cause generating concurrent changes in process mean and variance.     

可变抽样区间的非参数控制图

最近几年一些学者研究了可变抽样区间的质量控制图。Amin等提出了可变抽样区间(VSI)的非参数控制图———符号 (Sign)统计量图〔1〕。本文在此基础上研究位置VSI符号控制图的制定方法 ,并设计离散VSI符号控制图。符号控制图的优点是对非正态总体亦可应用 ,并且不需要过程方差的信息。本文将所设计的VSI符号控制图同固定抽样区间 (FSI)的常规图作比较 ,并举实例说明符号控制图的应用     

The efficiency of CUSUM schemes for monitoring the coefficient of variation

Continuous surveillance of the coefficient of variation is a quality control issue worthy of consideration in several manufacturing and service‐oriented companies. In this paper, we present a new method to monitor the squared coefficient of variation by means of two one‐sided cumulative sum‐type control charts. We study the run length properties of the proposed charts using a Markov chain approach. Several tables are given in order to show the sensitivity of the proposed charts for different deterministic shift sizes and their performance for the random shift size condition. The results show that the proposed control charts have attractive performance compared with some competing charts and are better in many cases. An illustrative example is discussed on a real dataset. Copyright © 2016 John Wiley & Sons, Ltd.