Developing a CUSUM Control Chart to Monitor Reliability Data in the Presence of Competing Risk

Monitoring and improving reliability data is one of the most critical challenges in manufacturing firms and organizations. In such processes, censoring is the main issue and the observations related to the quality characteristic are often censored at fixed level to ensure the minimum desired reliability. However, the major problem is that the presence of variable censoring (competing risk) leads to an inaccurate recording of some data. This makes the application of existing monitoring schemes ineffective. To deal with the encountered problem, a cumulative sum (CUSUM) control chart is proposed to effectively consider the presence of both fixed and variable censorings. Subsequently, the performance of the proposed control scheme has been investigated in terms of average run length (ARL) criterion. The results reveal that the CUSUM control chart has a good performance for prompt detection of out-of-control conditions. Finally, the sensitivity analysis has been conducted to evaluate the effect of fixed and variable censoring proportions

Keywords:

Competing risk , Reliability data , Censoring , Cumulative sum (CUSUM) control chart