Monitoring the alternating renewal processes with Weibull window-censored data

ABSTRACT

Many applications, especially in the industrial or medical fields, frequently encounter window-censored alternating renewal process (ARP). Process monitoring for window-censored ARP observations has received increasing attention recently. However, some conventional methods are inadequate as they are mainly designed considering only one censoring mechanism. In this paper, we utilize a ‘residual life’ distribution, and propose a novel online monitoring strategy that combines the likelihood with all kinds of censoring information, along with a modified conditional expected value exponentially weighted moving average control chart. The construction and implementation of these control schemes are studied by simulations which give desirable in-control and out-of-control performances and are robust under various scenarios. Finally, this paper shows by example based on driver’s glance data that the proposed methods have a good monitoring effect in practical scenarios.

KEYWORDS:

• Alternating renewal process
• online monitoring
• residual life
• window-censored data

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the National Natural Science Foundation of China under Grant [number 11871324]; Bureau of Statistics of China under Grant [number 2020LD03].