A survey of preventive maintenance models for stochastically deteriorating single-unit systems

Abstract

A survey of the research done on preventive maintenance is presented. The scope of the present survey is on the research published after the 1976 paper by Pierskalla and Voelker [98]. This article includes optimization models for repair, replacement, and inspection of systems subject to stochastic deterioration. A classification scheme is used that categorizes recent research into inspection models, minimal repair models, shock models, or miscellaneous replacement models.

The structure of optimal statin initiation policies for patients with Type 2 diabetes

“…We begin our analyses by defining the notion of an "increasing failure rate" (IFR) transition probability matrix, which has been shown to be useful in proving the structural properties of MDPs in maintenance and reliability theory (Valdez-Flores and Feldman 1989) and appears to match clinical data closely in varying contexts (Alagoz et al, 2004, Kreke et al, 2008.…”

Optimal replacement policy for a deteriorating production system

“…It tends to increase when a and 0 (Le, 7(£)) are increased and vice versa. A 2 3 Factorial-design analysis shows that this différence dépends mainly on r and, in order of importance, on j3 and a.…”

“…The différences between contributions of different authors may concern the mathematical approach (queueing theory, renewal theory, dynamic programming,...), the degree of knowledge of the system state (préventive maintenance model, preparedness model, inspection model) or different aspects of the problem (minimal repair model, shock model, miscellaneous replacement model). Références can be found in three major surveys which cover the last forty years of scientific production: MeCall [1] (up to 1964), Pierskalla and Voelker [2] (up to 1975), Valdez-Flores and Feldman [3] (up to 1989).…”

A queueing model with dependence between service and interarrival times

“…For a detailed survey on replacement policies and preventive maintenance we refer to Beichelt [1] and Voldes-Flores and Feldman [16]. According to the queueing interpretation, our model is a correlated single server queue with Markov arrivals.…”