Search

Traditional control charts depend on the process parameters that are used to monitor the shifts in the process. The adaptive control charts are used to adapt a process parameter during the online monitoring. This research introduces a support vector regression (SVR) based adaptive exponentially weighted moving average control chat to enhance the monitoring of the mean in industrial processes. The study systematically investigates the comparative efficiency of linear, radial basis function (RBF), and polynomial functions within the SVR framework. The proposed SVR‐based AEWMA control chart leverages the strengths of the RBF kernel, providing a robust mechanism for detecting shifts in the process mean by adapting the smoothing constant according to the size of the shift. To validate the efficacy of the proposed methodology, a practical application is presented by using real‐life data. The application showcases the adaptability and reliability of the SVR‐based adaptive EWMA control chart in effectively monitoring location shifts. [ABSTRACT FROM AUTHOR]

Monitoring the stability of measured dispersion in a process quality parameter is one of the critical steps in statistical process control (SPC) and is a paramount activity carried out by specialists. For this purpose, the current research presents a promising and computationally effective tool where the exponentially weighted moving average (EWMA) statistic utilizes the quadratic sigmoid function by incorporating sample size leading to the Quadratic Sigmoid Exponential weighted Moving Average (QSEWMA) control chart. The adaptive sample size is a strategy that increases or decreases the sample size according to the conditions of the process and accordingly, increases the sensitivity and response of the control chart. The proposed strategy improves the detection of process dispersion changes, making it a more efficient and effective way of quality assurance. Our proposed control chart is superior to the EWMA‐S2 chart, HHW‐EWMA chart CUSUM‐S2chart, and parametric free adaptive EWMA (AEWMA) charts for dispersion through extensive Monte Carlo simulations. The proposed QSEWMA chart has better detection sensitivity and fewer false alarms, and is, in general, more effective comparatively. At last, a real data application test is done to measure the practicability and highest accuracy of the above chart. [ABSTRACT FROM AUTHOR]

In health care centers, monitoring the medical outcomes is desirable to quickly detect performance changes. In recent years, monitoring the surgical process has gained eminence by accounting for patients' health conditions before cardiac surgery where the data is heterogeneous with respect to patients' health conditions. In the current study, we focus on risk-adjusted moving average-exponentially weighted moving average (RAMA-EWMA) control chart to identify the survival time after cardiac surgery. For this purpose, we used two years data set of the cardiac surgery. The performance of the control chart is evaluated by the average run length. Based on the extensive simulation, the average run length properties are computed. It is revealed that the proposed control chart has better shift diagnostic ability than the control chart considers in this study. [ABSTRACT FROM AUTHOR]

A new coefficient of variation (CV) functionally adaptive exponentially weighted moving average control chart is presented by considering the influence of the measurement error (ME) and named the "FAEWMA-ME-CV" control chart. The linear covariate model and the multiple measurements method are used to present the control chart. The designed function is efficient to detect the infrequent process changes in the form of parametric shifts in the process CV. The proficiency of the design is evaluated by analyzing the run-length values which are determined by the Monte Carlo simulation runs shown for the various parametric settings in extensive tables. The analysis depicts that the presence of the ME plays a significant role in the performance of a control chart. Moreover, a real-life dataset explained the application of the proposed FAEWMA-ME-CV chart to support the argument. [ABSTRACT FROM AUTHOR]

In this study, a variance control chart is proposed with some modifications in terms of the rapid detection of process shifts by using the homogenously weighted moving average ( HWMA) statistic by using the information from an auxiliary variable. The proposed HWMA chart is a new memory type variance control chart with a three-parameter log transformation that operates by assigning the specified weights to the most recent value. All previous samples are allotted with an equal proportion of the remaining smoothing parameter weight. The remaining weights put their effect as a counterpart within the smoothing parameter and the current observations take the maximum of it. To study the performance of the proposed chart the respective run length properties are determined by Monte Carlo simulations and extensively presented in the tables. The comparison has been made with the existing exponentially weighted moving average ( EWMA) variance control chart. It is figured out that the proposed control chart is sensitive to process shift by using the auxiliary information with a high degree of correlation. The real-life dataset is selected from an industrial production environment to demonstrate the implementation of the proposed chart. [ABSTRACT FROM AUTHOR]