Abstract
Distribution-free control charts can be useful in statistical process control (SPC) when only limited or no information about the distribution of the data of the process is available. In this paper, a linear prediction related double exponentially weighted moving average (DEWMA) sign control chart using a repetitive sampling scheme (RSNPDEBLP) has been considered for a binomially distributed process variable to improve the efficiency of detecting small drifts in its place of small changes. The proposed RSNPDEBLP control chart is assessed in average run length (ARL) for the various values of sample sizes. The efficiency of the proposed RSNPDEBLP control chart is compared with the existing EWMA and DEWMA sign control charts using single sampling and repetitive sampling schemes in terms of ARLs. When there are small changes in the process after the stabilization period, the proposed control chart is used to control small trends rather than small shifts.
Highlights
Variation exists in all types of manufacturing process and can be divided into a natural and unnatural variation [1]
We extend this idea by proposing a new double exponentially weighted moving average (DEWMA) control chart by using a repetitive group sampling (RGS) scheme under the assumption of non-normality
The OOC average run length ARL1 values under linear drift for different p1 values were used for checking the efficiency of the proposed control chart with some existing control charts
Summary
Variation exists in all types of manufacturing process and can be divided into a natural and unnatural variation [1]. The [29] context proposed a parametric DEWMA control chart based on Linear prediction for detecting the small drift instead of shifts by using the normal distribution according to the fundamental theorem of exponential smoothing proposed by [30]. Later on, [37] designed an EWMA and DEWMA control chart for the non-normal process using RGS. [29] introduced a DEWMA control chart based on linear prediction for small drift in place of shift under the assumption of normality. We extend this idea by proposing a new DEWMA control chart by using a RGS scheme under the assumption of non-normality. The proposed control chart is expected to perform better than that of other non-normality based EWMA and DEWMA control charts. The EWMA and DEWMA control charts work efficiently for small shifts, but when the procedure needs a small change with the non-normal data set, the proposed control chart work more efficiently as compared to EWMA and DEWMA control charts
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
