Modified One-Sided EWMA Charts without- and with Variable Sampling Intervals for Monitoring a Normal Process

Much research has been conducted on two-sided Exponentially Weighted Moving Average (EWMA) control charts, while less work has been devoted to the one-sided EWMA charts. Traditional one-sided EWMA charts involve resetting the EWMA statistic to the target whenever it falls below or above the target, or truncating the observations above or below the target and further applying the EWMA statistic to the truncated samples. In order to further improve the performance of traditional one-sided EWMA mean (X¯) charts, this paper studies the performance of the Modified One-sided EWMA (MOEWMA) X¯ charts to monitor a normally distributed process. The Monte-Carlo simulation method is used to obtain the zero- and steady-state Run Length (RL) properties of the proposed control charts. Through extensive simulations and comparisons with other charts, it is shown that the proposed MOEWMA X¯ charts compare favorably with some existing competing charts. Moreover, by attaching the variable sampling intervals (VSI) feature to the MOEWMA X¯ charts, it is shown that the VSI MOEWMA charts outperform the corresponding charts without the VSI feature. Finally, a real data example from manufacturing process shows the implementation of the proposed one-sided charts.

On Enhanced GLM-Based Monitoring: An Application to Additive Manufacturing Process

Innovations in technology assist the manufacturing processes in producing high-quality products and, hence, become a greater challenge for quality engineers. Control charts are frequently used to examine production operations and maintain product quality. The traditional charting structures rely on a response variable and do not incorporate any auxiliary data. To resolve this issue, one popular approach is to design charts based on a linear regression model, usually when the response variable shows a symmetric pattern (i.e., normality). The present work intends to propose new generalized linear model (GLM)-based homogeneously weighted moving average (HWMA) and double homogeneously weighted moving average (DHWMA) charting schemes to monitor count processes employing the deviance residuals (DRs) and standardized residuals (SRs) of the Poisson regression model. The symmetric limits of HWMA and DHWMA structures are derived, as SR and DR statistics showed a symmetric pattern. The performance of proposed and established methods (i.e., EWMA charts) is assessed by using run-length characteristics. The results revealed that SR-based schemes have relatively better performance as compared to DR-based schemes. In particular, the proposed SR-DHWMA chart outperforms the other two, namely SR-EWMA and SR-HWMA charts, in detecting shifts. To illustrate the practical features of the study’s proposal, a real application connected to the additive manufacturing process is offered.

MONITORING PROCESS LOCATION AND DISPERSION SIMULTANEOUSLY USING A CONTROL REGION

Control charts are effective tools for detecting out-of-control conditions of process parameters in manufacturing and service industries. The development of distribution-free control charts is important in statistical process control when the process quality variable follows an unknown or a non-normal distribution. This research thus proposes to use a distribution-free technology to establish a new control region based on the exponentially weighted moving average median statistic and exponentially weighted moving average interquartile range statistic for simultaneously monitoring the process location and dispersion and further sets up a corresponding new control chart. We compute the out-of-control average run length to evaluate out-of-control detection performance of the proposed control region and also compare the proposed control region with some existing location and dispersion control charts. Results show that our proposed chart always exhibits superior detection performance when the shifts in process location and/or dispersion are small or moderate. The new control region is thus recommended. Keywords: control chart, distribution-free, dispersion and location, EWMA, kernel control region, kernel density estimation.

Penerapan Peta Kendali Neutrosophic Exponentially Weighted Moving Average (NEWMA) X dalam Monitoring Rata-Rata Proses Ketebalan Kaca

In the industrial sector, the measurement results of a quality characteristic often involve an uncertainty interval (interval indeterminacy). This causes the classical control chart to be less suitable for monitoring quality. Currently, a control chart with a neutrosophic approach has been developed. The neutrosophic control chart was developed based on the concept of neutrosophic numbers with control charts. One of the control charts that have been developed to monitor the mean process is the Neutrosophic Exponentially Weighted Moving Average (NEWMA) X control chart. This control chart is a combination of neutrosophic with classical EWMA control chart. The neutrosophic control chart consists of two control charts, namely lower and upper, each of which consists of upper and lower control limits. Therefore, NEWMA X is more sensitive to detect out-of-control observations. In this research, the NEWMA X control chart will be used to monitor the average process of the thickness of the panasap dark grey 5mm glass produced by a glass industry. Through the analysis in this research, it was found that by using weighting λN [0, 10; 0, 10] and constant value kN [2, 565; 2, 675], the average process of the thickness of panasap dark grey 5mm glass has not beet controlled statistically because 21 observations were identified that were outside the control limits (out of control). When compared with the classical EWMA control chart with the same weighting λ, 17 observations were detected out of control. This proves that the NEWMA X control chart is more sensitive in detecting observations that are out of control because the determination of the in-control state is based on two values, lower and upper, both at the lower and upper control limits.

A New Hybrid Exponentially Weighted Moving Average control chart using Mixture Ratio Estimator of Mean

In this paper, we propose a Hybrid Exponentially Weighted Moving Average (HEWMA) control chart based on a mixture ratio estimator of mean using a single auxiliary variable and a single auxiliary attribute (Moeen et al., [1]). We call it as Z- HEWMA control chart. The proposed control chart performance is evaluated using outof- control-Average Run Length (ARL1). The control limits of the proposed chart is based on estimator, its mean square errors. A simulated example is used to compare the proposed Z-HEWMA, traditional/simple EWMA chart and CUSUM control chart. From this study the fact is revealed that Z-HEWMA control chart shows more efficient results as compared to traditional/simple EWMA and CUSUM control charts. The Z-HEWMA chart can be used for efficient monitoring of the production process in manufacturing industries where auxiliary information about a numerical variable and an attribute is available.

Implementasi Metode Weighted Moving Average Untuk Sistem Peramalan Penjualan Markas Coffee

Headquarters Coffee is one of the businesses engaged in the culinary field of coffee drinks. The problem that occurs at the Coffee Headquarters is that business activities are still carried out manually. In addition, determining sales in the next period only refers to the sales data of the previous period, resulting in owners often experiencing shortages or excess stocks of coffee to be sold due to uncertain sales. Therefore we need a forecasting method (Forecasting) that is appropriate and can be applied to an Information System in the form of a Website. The purpose of making this forecasting information system is to assist companies in recording sales to make it more practical by applying the Weighted Moving Average (WMA) method. From the results of the calculation of the WMA method, the level of accuracy will then be calculated using the Mean Absolute Percentage Error (MAPE) method. The results of forecasting by applying the WMA method and MAPE calculations on weights 3, 4 and 5 show that the Robusta coffee on the Robusta menu which has the smallest MAPE is weight 3 with a calculation result of 19.2499 and the Robusta Milk menu which has the smallest MAPE is weight 4 with the calculation result is 15.21879166 and Excelsa coffee on the excelsa menu which has the smallest MAPE is weight 3 with a calculation result of 19.1538 and the Excelsa Susu menu which has the smallest MAPE is weight 5 with a calculation of 17.27650182 while for Arabica coffee on the Arabica menu which has the smallest MAPE is weight 4 with a calculation result of 18.1735 and the Arabica Susu menu which has the smallest MAPE is weight 5 with a calculation result of 16.24012072. Where the Mape value produced by each type of coffee is still below 20%, which means the forecasting results can be categorized as good.