摘要:

Traditionally, control charts are developed assuming that the sequence of process observations to which they are applied are uncorrelated. Unfortunately, this assumption is frequently violated in practice. The presence of autocorrelation has a serious impact on the performance of control charts, causing a dramatic increase in the frequency of false alarms. This paper presents methods for applying statistical control charts to autocorrelated data. The primary method is based on modeling the autocorrelative structure in the original data and applying control charts to the residuals. We show that the exponentially weighted moving average (EWMA) statistic provides the basis of an approximate procedure that can be useful for autocorrelated data. Illustrations are provided using real process data.

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979321

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979322

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979323

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979324

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979325

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor

摘要:

Box proposed an empirical procedure, called thelambda plot, to search for a simplifying transformation in the context of replicated orthogonal experiments. This paper shows that, by appropriately scaling the factor effects, thelambda plotprocedure can be extended to unreplicated situations and illustrates its use on four published data sets. The scaling technique proposed can be used also to construct a simple graphical summary of the analysis of multiresponse orthogonal experiments with two-level factors. This is illustrated using data obtained from a pigment production process.

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979326

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor

摘要:

Classical control charts are designed for processes where data to estimate the process parameters and compute the control limits are available before a production run. For many processes, especially in a job-shop setting, production runs are not necessarily long and charting techniques are required that do not depend upon knowing the process parameters in advance of the run. It is desirable to begin charting at or very near the beginning of the run in these cases. We present here the needed formulas so that charts for both the process mean and variance can be maintained from the start of production, whether or not prior information for estimating the parameters is available. These Q charts are all plotted in a standardized normal scale, and therefore permit the plotting of different statistics on the same chart. This will sometimes permit savings in the chart management program.

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979327

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor

摘要:

When 100% inspection in the order of production is in progress, an alternative approach to thep-chart or the Poisson-based CUSUM chart is to monitor the lengths of runs of conforming items between successive nonconforming items. Two Shewhart-type charts and a CUSUM chart based on such run lengths are presented and comparisons are made with the performance of thep-chart and the Poisson CUSUM chart in detecting shifts in fraction nonconforming. The run-length CUSUM chart is found to be more efficient than the Poisson CUSUM chart, while the run-length Shewhart chart based on the sum of the two most recent run lengths (termed the RL2chart) is more efficient than thep-chart for detecting large shifts in fraction nonconforming.

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979328

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor

摘要:

Approximately normalized control charts, called Q charts, are proposed for charting a binomial random variable. Transformations are given for the two cases when the parameterpis known before charting is begun and when it is not known before charting is begun. These charts permit real-time charting essentially from the beginning of sampling and are especially useful for the case whenpis not known in advance. These charts are all plotted in a standard normal scale and permit a flexible chart management program. For the case whenpis assumed known, we present a table to compare the closeness of the control probabilities for these Q charts with those of the approximating normal distribution, and with those achieved by either classical 3-sigmapcharts or with charts based on a standardized arcsin transformation chart. These results show that Q charts give better approximations than the classicalpcharts to the nominal normal probabilities, and are comparable with, but differ from, the arcsin charts.

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979329

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor

摘要:

It is common practice to supplement the ShewhartX̄chart with so called“runs tests.”These tests are designed to give an earlier detection of anomalies in the process mean. Although these tests are valuable in detecting“true”problems, they also increase the probability of a false signal. In this paper the false signal rates of eight runs tests are obtained through simulation. In-control processes were generated using independent realizations of a standard normal distribution. The results show that the number of false signals can be fairly high, particularly when the number of tests applied and number of subgroups increase.

ISSN:0022-4065    

DOI:10.1080/00224065.1991.11979330

出版商:Taylor&Francis    

年代:1991

数据来源: Taylor