Search

Statistical process control provides package of statistical tools applied for improving quality of manufacturing, production and services processes. Cumulative sum, exponentially weighted moving average (EWMA) and progressive mean charts belong to family of memory-type charts which effectively spot small and persistent shifts in the process parameter(s). EWMA chart requires normality and a proper choice of smoothing parameter to perform efficiently. Any deviation from these conditions affects its performance in terms of efficacy and robustness. For the said concerns, progressive exponentially weighted moving average (PEWMA) chart is developed to monitor the shifts in the process location. The performance of the proposed PEWMA chart is evaluated in terms of average run length and some other metrics of run length distribution. The assessment of the proposed chart has been made under standard normal, Student's t, gamma, Laplace, logistic, exponential, contaminated normal and lognormal distributions. The performance of the proposed PEWMA chart is also compared with some existing competitors including the classical EWMA, classical CUSUM, HWMA, MEC, MCE and DEWMA charts. The analysis reveals that the proposal offers a design structure which has high sensitivity to small and persistent drifts in the process mean and has advantage of robustness under non-normal scenarios. An application from substrates manufacturing process (in which flow width of the resist is the key quality characteristic) is also provided for practical implementations. [ABSTRACT FROM AUTHOR]

Statistical quality control is an integral part of modern manufacturing, and control charts are widely used to improve and control the performance of a process. However, much of the work related to process monitoring has been done using frequentist approaches, whereas the Bayesian methodology has a practical advantage in process monitoring; that is, it can be used with a small phase-I dataset. In this article, we considered different symmetric and asymmetric loss functions for designing Bayesian control charts and noticed that the performance of the Bayesian charts is biased, i.e., in-control performance of the charts is not equal to the desired value for some loss functions and comparison among different Bayesian charts can be misleading. Therefore, to get the desired in-control performance under different loss functions, we propose a corrected design of the Bayesian control charts. In addition to posterior charts, we also discuss a predictive control chart to monitor the future observations in this study. Besides a simulation study, we also present two real data examples: the first example is to monitor the surface roughness of reamed holes in a particular metal part while the second is about monitoring the measurements of a diameter. [ABSTRACT FROM AUTHOR]

Multivariate autoregressive (MAR) models are an attractive choice for applications in the processes related to finance, medical, and industry. For the monitoring of such processes, control chart is the most important and widely used tool of statistical process control tool kit. Moreover, the presence of auxiliary information helps in better estimation of different process parameters. The literature on use of auxiliary variables in control charts assumes independence of observations. In practice, we may come across processes dealing with autocorrelated outcomes. In such situations, a control chart usually produces high false alarms and exhibits slow detection of shifts when the process is out-of-control. This study intends to suggest some auxiliary information-based Shewhart charts for autocorrelated univariate and bivariate AR(1) processes. The proposed structures take into account the autocorrelation structure and offer more effective designs of control charts for efficient process monitoring. The performance measures used in this study are based on run length measures such as average run length, extra quadratic loss, relative average run length and performance comparison index. A detailed performance analysis is carried out to sort out the best performing charts. In addition, we have considered an application from a manufacturing process to demonstrate the implementation of the proposed charting structures in real scenario. [ABSTRACT FROM AUTHOR]

Control charts act as the most effective statistical process control (SPC) tools for the monitoring of manufacturing processes. In this study, we propose and investigate a set Shewhart-type variability control chart based on the utilization of auxiliary information for efficient phase II process monitoring. The design parameters of the proposals are derived under correlated setups for the monitoring of variability parameter. The properties of these charting structures are evaluated in terms of average run length and some other related measures. The performance abilities of these charts are compared with each other and also with some existing counterparts. The comparisons revealed that the proposed charts are very efficient at detecting shifts in the variability parameter and have the ability to perform better than the competing charts in terms of run length characteristics. We have also used real datasets to illustrate the application of the proposed structures in practical situations. [ABSTRACT FROM AUTHOR]

In this article we develop a power computation code in the R language which provides an easy to use tool to researchers in designing Shewhart control charts. It enables researchers to use different existing and newly introduced sensitizing rules and runs rules schemes designed for Shewhart-type control charts for location and spread. The code provides researchers to compute the power for different options of r out of m rules/schemes. The code is flexible to apply for any sample size, false alarm rate, type of control limits (one- or two-sided), amount of shift in the process parameters and a variety of popular distributions for commonly used Shewhart-type control charts (i.e. $${\bar{{X}} ,R ,S}$$ and S charts). These mentioned benefits of the developed functional code are only partially found in features of the existing software packages and these programs may be enhanced by adding the features of the developed code as a function in their libraries dealing with quality control charting. [ABSTRACT FROM AUTHOR]