Enhanced Robust Auxiliary Information Based Memory-Type Control Charts In Statistical Process Control

Statistical process control(SPC)is a method for the monitoring of manufacturing and non-manufacturing processes through statistical analysis.Process monitoring is a continuous procedure used for improving the quality of product or service.Variations are an integral part of every process and these variations need our attention to improve the quality of the process.All production processes are subject to variations which can be categorized into two categories namely,common cause of variations and special cause of variations.A timely detection of special cause variations plays a significant role in the performance of any process.To examine whether manufactured products meet the quality standards,control charts are particularly helpful.Control charts are the most important and commonly used tools of SPC to identify the presence of special cause variations.Monitoring of any manufacturing,production or industrial process can be controlled and improved by removing these special cause variations using control charts.Shewhart-type control charts are efficient to control or detect a large amount of special variations in the process,while,exponentially weighted moving average(EWMA)and cumulative sum(CUSUM)type control charts are better to detect moderate and small variations in the process parameters.The common assumption is that the parameters are known or correctly estimated from in-control samples and data is free from outliers.So with these assumptions,mostly monitoring of location and scale parameters is done with mean and variance(or standard deviation)control charts.But in practice,these assumptions are not true and processes are likely to have outliers.In such situations,median and interquartile-range serve as a better alternative when processes face sudden outliers.Moreover,information about auxiliary variables helps to enhance the precision of the estimators and,hence,the charting structure.This thesis contributes some improved control charting structures to be used as add-in for SPC toolkit.The proposed charting structures are designed for location and variability parameters using the information on single and dual use of auxiliary characteristics.We have covered some selective distributions including normal,lognormal and student's t distributed process environments(with and without contaminations).The performance ability of the proposals is assessed in terms of some useful measures including average run length(ARL),extra quadratic loss(EQL),relative average run length(RARL)and performance comparison index(PCI).We have investigated the efficiency of different proposed charting structures using extensive Monte Carlo simulations,and carried out extensive comparisons with their existing counterparts.We have also included some real situations in order to highlight the practical application of the proposals covered in this study.