It appears you don't have support to open PDFs in this web browser. To view this file, Open with your PDF reader
Abstract
In this paper we present a proposal of statistical control chart modified with asymmetric limits that use multiple sampling to decide the state of control of the process. Two related themes established the theoretical bases of the presented proposal control charts designs with variable parameters (pV); and, control charts with fixed parameters (pF). The use of multiple sampling improves the power of detection of special causes and minimizes the risk of stopping the process unduly by the occurrence of type I (false positive) error. It is proposed to use a statistical control chart with asymmetric limits using a non-linear (non-fixed) sampling procedure with three possible decision regions. The proposal considers the possibility of resampling the process. The effects of statistical parameter estimates were also considered in the performance analysis of the proposed chart. The performance metric considered was the mathematical expectation on the average number of samples until detecting a point outside the control limits. Numerical methods were used to find the statistical control limits for a type I error of 0.27%.