To evaluate With the Autocorrelated Process Data by MCEWMA Control Chart

• Main Authors: Chia-an Liu, 劉家安
• Other Authors: Chau-Chen Torng
• Format: Others
• Language: zh-TW
• Published: 2004
• Online Access: http://ndltd.ncl.edu.tw/handle/11122294228295625353

碩士 === 國立雲林科技大學 === 工業工程與管理研究所碩士班 === 92 === In the fact, There are a lot of autocorrelation data in the process industry. How to solve autocorrelation data to influence process, that is very important problem. Reduced of ARL will be to increase the false alarm rate of control charts. SPC control chart’s detecting ability in autocorrelation process, that is required to deal with autocorrelation. The traditional SPC control chart detection and examine in the autocorrelation data. That is a kind of effective tool. BUT the independent character assumption in the data is violated, such a result, will make ARL while controlling shorten and cause mistake alert number of times made maps to in charge of increase obviously, Personnel will be make the mistakes in out of control to judge by accident. So, solve autocorrelation from the process to cause problem is extraordinary importance. In this paper , AR (1) and AR (2) model is discussed and use traditional three control charts：Shewhart、CUSUM、EWMA Chart. Except traditional control charts, the MCEWMA control charts be use in the autocorrelation process to detection out of control ARL. Moreover to effectively use his characteristic at the same time, that is can keep primitive predict’s error value in the control chart of efficiency. At the same time , personnel can understand data in process development and trend situation. However time series approach is general use to describe the structure of autocorrelation. Finally, MCEWMA control chart compared ARL with the way to deal with time series method.