• Communications for Statistical Applications and Methods
• /
• v.14 no.1
• /
• pp.155-167
• /
• 2007

Knowing the time of the process change could lead to quicker identification of the responsible special cause and less process down time, and it could help to reduce the probability of incorrectly identifying the special cause. In this paper, we propose the maximum likelihood estimator (MLE) for the process change point when a control chart is used in monitoring the mean of a process in which the observations can be modeled as an AR(1) process plus an additional random error. The performance of the proposed MLE is compared to the performance of the built-in estimator when they are used in EWMA charts based on the residuals. The results show that the proposed MLE provides good performance in terms of both accuracy and precision of the estimator.

• Journal of the Korea Safety Management & Science
• /
• v.12 no.4
• /
• pp.255-263
• /
• 2010

The research developes short-run standardized control charts(SSCC) and short-run acceptance control charts(SACC) under the various demand patterns. The demand patterns considered in this paper are three types such as high-variety and repetitive low-volume pattern, extremely-high-variety and nonrepetitive low-volume pattern, and high-variety and extremely-low-volume pattern. The short-run standardized control charts developed by extending the long-run ${\bar{x}}$-R, ${\bar{x}}$-s and I-MR charts have strengths for practioners to understand and use easily. Moreover, the short-range acceptance control charts developed in the study can be efficiently used through combining the functions of the inspection and control chart. The weighting schemes such as Shewhart, moving average (MA) and exponentially weighted moving average (EWMA) can be considered by the reliability of data sets. The two types according to the use of control chart are presented in the short-range standardized charts and acceptance control charts. Finally, process capability index(PCI) and process performance index(PPI) classified by the demand patterns are presented.

• Journal of the Korean Statistical Society
• /
• v.33 no.4
• /
• pp.381-399
• /
• 2004

Statistical process control (SPC) and engineering process control (EPC) are based on different strategies for process quality improvement. SPC re-duces process variability by detecting and eliminating special causes of process variation, while EPC reduces process variability by adjusting compensatory variables to keep the quality variable close to target. Recently there has been need for an integrated process control (IPC) procedure which combines the two strategies. This paper considers a scheme that simultaneously applies SPC and EPC techniques to reduce the variation of a process. The process model under consideration is an IMA(1,1) model with a step shift. The EPC part of the scheme adjusts the process, while the SPC part of the scheme detects the occurrence of a special cause. For adjusting the process repeated adjustment is applied according to the predicted deviation from target. For detecting special causes the exponentially weighted moving average control chart is applied to the observed deviations. It was assumed that the adjustment under the presence of a special cause may increase the process variability or change the system gain. Reasonable choices of parameters for the IPC procedure are considered in the context of the mean squared deviation as well as the average run length.

• The Korean Journal of Applied Statistics
• /
• v.9 no.1
• /
• pp.91-109
• /
• 1996

Exponentially weighted moving averae(EWMA) control chart has been used widely for process monitoring and process adjustment recently, but there has not been many studies about the selection of the parameters. Design of the control chart can be classified into the statistical design and the economic design. The purpose of the economic design is to minimize the cost function in which all the possible costs occurring during the process are probability given the Type I error probability. In this paper the optimal parameters of the EWMA chart are selected for the economic design as well as for the statistical design. The optimal parameters for the economic design show significantly different from those of the statistical design, and especially the weight is always larger than that used in the statistical design. In the economic design, we divide the model into the single assignable cause model and the multiple assignable causes model caacording to number of which is used as the average context of the multiple assignable causes, it shows that the selection of the parameters may be misleading when the multiple assignable causes exist in practice.

• Proceedings of the Korean Statistical Society Conference
• /
• 2004.11a
• /
• pp.179-184
• /
• 2004

Statistical process control (SPC) and engineering process control (EPC) are based on different strategies for process quality improvement. SPC reduces process variability by detecting and eliminating special causes of process variation, while EPC reduces process variability by adjusting compensatory variables to keep the quality variable close to target. Recently there has been need for an integrated process control (IPC) procedure which combines the two strategies. This article considers a scheme that simultaneously applies SPC and EPC techniques to reduce the variation of a process. The process disturbance model under consideration is an IMA(1,1) model with a location shift. The EPC part of the scheme adjusts the process, while the SPC part of the scheme detects the occurrence of a special cause. For adjusting the process repeated adjustment is applied by compensating the predicted deviation from target. For detecting special causes the two kinds of exponentially weighted moving average (EWMA) control chart are applied to the observed deviations: One for detecting location shift and the other for detecting increment of variability. It was assumed that the adjustment of the process under the presence of a special cause may change any of the process parameters as well as the system gain. The effectiveness of the IPC scheme is evaluated in the context of the average cost per unit time (ACU) during the operation of the scheme. One major objective of this article is to investigate the effects of the process parameters to the ACU. Another major objective is to give a practical guide for the efficient selection of the parameters of the two EWMA control charts.

• The Korean Journal of Applied Statistics
• /
• v.30 no.1
• /
• pp.1-12
• /
• 2017

Many stochastic processes satisfy the Markov property exactly or at least approximately. An interested property in the Markov process is the first passage time. Since the sequential analysis by Wald, the approximation of the first passage time has been studied extensively. The Statistical computing technique due to the development of high-speed computers made it possible to calculate the values of the properties close to the true ones. This article introduces an exponentially weighted moving average (EWMA) control chart as an example of the Markov process, and studied how to calculate the average run length with problematic issues that should be cautioned for correct calculation. The results derived for approximation of the first passage time in this research can be applied to any of the Markov processes. Especially the approximation of the continuous time Markov process to the discrete time Markov chain is useful for the studies of the properties of the stochastic process and makes computational approaches easy.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.11a
• /
• pp.560-570
• /
• 2006

This paper proposes a selectively cumulative sum (S-CUSUM) control chart with variable sampling intervals (VSI) for detecting shifts in the process mean. The basic idea of the VSI S-CUSUM chart is to adjust sampling intervals and to accumulate previous samples selectively in order to increase the sensitivity. The VSI S-CUSUM chart employs a threshold limit to determine whether to increase sampling rate as well as to accumulate previous samples or not. If a standardized control statistic falls outside the threshold limit, the next sample is taken with higher sampling rate and is accumulated to calculate the next control statistic. If the control statistic falls within the threshold limit, the next sample is taken with lower sampling rate and only the sample is used to get the control statistic. The VSI S-CUSUM chart produces an 'out-of-control' signal either when any control statistic falls outside the control limit or when L-consecutive control statistics fall outside the threshold limit. The number L is a decision variable and is called a 'control length'. A Markov chain model is employed to describe the VSI S-CUSUM sampling process. Some useful formulae related to the steady state average time-to signal (ATS) for an in-control state and out-of-control state are derived in closed forms. A statistical design procedure for the VSI S-CUSUM chart is proposed. Comparative studies show that the proposed VSI S-CUSUM chart is uniformly superior to the VSI CUSUM chart or to the Exponentially Weighted Moving Average (EWMA) chart with respect to the ATS performance.

• Progress in Medical Physics
• /
• v.25 no.3
• /
• pp.185-192
• /
• 2014

The purpose of this study is to evaluate the results for the quality assurance through a statistical analysis on the output characteristics of linear accelerators belonging to Yeungnam University Medical Center by using the Shewhart-type chart, Exponentially weighted moving average chart (EWMA) chart, and process capability indices $C_p$ and $C_{pk}$. To achieve this, we used the output values measured using respective treatment devices (21EX, 21EX-S, and Novalis Tx) by medical physicists every month from September, 2012 to April, 2014. The output characteristics of treatment devices followed the IAEA TRS-398 guidelines, and the measurements included photon beams of 6 MV, 10 MV, and 15 MV and electron beams of 4 MeV, 6 MeV, 9 MeV, 12 MeV, 16MeV, and 20 MeV. The statistical analysis was done for the output characteristics measured, and was corrected every month. The width of control limit of weighting factors and measurement values were calculated as ${\lambda}=0.10$ and L=2.703, respectively; and the process capability indices $C_p$ and $C_{pk}$ were greater than or equal to 1 for all energies of the linear accelerators (21EX, 21EX-S, and Novalis Tx). Measured values of output doses with drastic and minor changes were found through the Shewhart-type chart and EWMA chart, respectively. The process capability indices $C_p$ and $C_{pk}$ of the treatment devices in our institution were, respectively, 2.384 and 2.136 for 21EX, 1.917 and 1.682 for 21EX-S, and 2.895 and 2.473 for Novalis Tx, proving that Novalis Tx has the most stable and accurate output characteristics.

• Journal of the Korea Society for Simulation
• /
• v.18 no.3
• /
• pp.103-112
• /
• 2009

In a nuclear power plant (NPP), periodic sensor calibrations are required to assure sensors are operating correctly. However, only a few faulty sensors are found to be calibrated. For the safe operation of an NPP and the reduction of unnecessary calibration, on-line calibration monitoring is needed. In this paper, principal component-based Auto-Associative support vector regression (PCSVR) was proposed for the sensor signal validation of the NPP. It utilizes the attractive merits of principal component analysis (PCA) for extracting predominant feature vectors and AASVR because it easily represents complicated processes that are difficult to model with analytical and mechanistic models. With the use of real plant startup data from the Kori Nuclear Power Plant Unit 3, SVR hyperparameters were optimized by the response surface methodology (RSM). Moreover the statistical techniques are integrated with PCSVR for the failure detection. The residuals between the estimated signals and the measured signals are tested by the Shewhart Control Chart, Exponentially Weighted Moving Average (EWMA), Cumulative Sum (CUSUM) and generalized likelihood ratio test (GLRT) to detect whether the sensors are failed or not. This study shows the GLRT can be a candidate for the detection of sensor drift.