A CONTROL CHART BASED ON MOVING AVERAGE AND MOVING RATIO FOR MONITORING WEIBULL DATA

應用移動平均與移動比值監控韋伯資料之研究

陳榮泰(Jung-Tai Chen)

《品質學報》 25卷4期 (2018/08) Pp. 211-240

https://doi.org/10.6220/joq.201808_25(4).0001

摘要

This study focuses on monitoring the joint shifts of the shape parameter c and the scale parameter θ for Weibull data. Previous work on this issue demonstrated an undesired phenomenon, the so-called average run length-biasedness (ARL-biasedness). To eliminate this phenomenon, this study proposes a novel control scheme, the MA-MRa chart: a moving average (MA) chart combined with a moving ratio (MRa) chart. An analytical approach is developed to compute the performance of the proposed chart. A simulation study shows that the analytical approach is reasonably accurate in estimating the performance of the proposed chart. In addition, a comparative study is conducted to show that the proposed chart outperforms the other charts. Finally, an example demonstrates how to apply proposed chart.

關鍵字

Weibull distribution ； moving average ； moving ratio ； shape parameter ； scale parameter

並列摘要

本研究旨在探討同時偵測韋伯資料其型態參數c與尺度參數θ之偏移，文獻有關此議題的研究呈現出所謂的平均連串長度偏誤(average run length-biasedness, biasedness)的情形，此一情形將對管制圖的管制效果產生不利的影響。為了解決此問題，本研究提出以一新的移動平均管制圖，搭配移動比值管制圖，來同時管制韋伯資料其型態參數與尺度參數；並提出一解析方法以計算此管制圖之管制績效，模擬結果顯示此解析方法有非常合理的準確性，之後應用此解析方法並配合窮舉搜尋求出此管制圖的管制界限，以供實務界參採。研究結果顯示，在與文獻所提的方法相較之下，本研究有較好的管制效果。最後以一例子，示範如何使用本研究所提出的管制圖。

並列關鍵字

韋伯分配 ； 移動平均 ； 移動比值 ； 型態參數 ； 尺度參數

參考文獻

Chen, J.-T.(2014).A study on using the moving average chart for monitoring time-between-events.Journal of Quality.21(6),479-500.

Acosta-Mejia, C. A.,Pignatiello, J. J., Jr.(2000).Monitoring process dispersion without subgrouping.Journal of Quality Technology.32(2),89-102.

Basu, B.,Tiwari, D.,Kundu, D.,Prasad, R.(2009).Is Weibull distribution the most appropriate statistical strength distribution for brittle materials?.Ceramics International.35(1),237-246.

Chen, F. L.,Yeh, C. H.(2011).Economic statistical design for x-bar control charts under non-normal distributed data with Weibull in-control time.Journal of the Operational Research Society.62(4),750-759.

Chen, H.,Cheng, Y.(2007).Non-normality effects on the economic-statistical design of X charts with Weibull in-control time.European Journal of Operational Research.176(2),986-998.