Abstract
The cumulative sum (CUSUM) control chart is widely used in industry for the detection of small and moderate shifts in process location and dispersion. For efficient monitoring of process variability, we present several CUSUM control charts for monitoring changes in standard deviation of a normal process. The newly developed control charts based on well-structured sampling techniques - extreme ranked set sampling, extreme double ranked set sampling and double extreme ranked set sampling, have significantly enhanced CUSUM chart ability to detect a wide range of shifts in process variability. The relative performances of the proposed CUSUM scale charts are evaluated in terms of the average run length (ARL) and standard deviation of run length, for point shift in variability. Moreover, for overall performance, we implore the use of the average ratio ARL and average extra quadratic loss. A comparison of the proposed CUSUM control charts with the classical CUSUM R chart, the classical CUSUM S chart, the fast initial response (FIR) CUSUM R chart, the FIR CUSUM S chart, the ranked set sampling (RSS) based CUSUM R chart and the RSS based CUSUM S chart, among others, are presented. An illustrative example using real dataset is given to demonstrate the practicability of the application of the proposed schemes.
Highlights
Cumulative sum (CUSUM) control charts have received a great deal of attention in modern industries to monitor unusual variations in manufacturing and service processes
In the same line with the ranked set sampling (RSS) based CUSUM R chart, we studied the performance of the CUSUM of S chart using ranked set samples, and the results obtained for detection of increases and decreases in process standard deviation are displayed in column five of Tables 7 and 8, respectively
This article proposed some enhanced CUSUM of R and S control charts based on extreme RSS (ERSS), extreme double RSS (EDRSS) and double ERSS (DERSS) sampling techniques for monitoring process dispersion
Summary
The cumulative sum (CUSUM) control chart is widely used in industry for the detection of small and moderate shifts in process location and dispersion. For efficient monitoring of process variability, we present several CUSUM control charts for monitoring changes in standard deviation of a normal process. The newly developed control charts based on wellstructured sampling techniques - extreme ranked set sampling, extreme double ranked set sampling and double extreme ranked set sampling, have significantly enhanced CUSUM chart ability to detect a wide range of shifts in process variability. The relative performances of the proposed CUSUM scale charts are evaluated in terms of the average run length (ARL) and standard deviation of run length, for point shift in variability.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have