Showing papers by "Dragan Banjevic published in 2002"
TL;DR: The Weibull proportional-hazards model is used to determine the optimal replacement policy for a critical item which is subject to vibration monitoring, and the policy is validated using data that arose from subsequent operation of the plant.
Abstract: This paper describes a case study in which the Weibull proportional-hazards model is used to determine the optimal replacement policy for a critical item which is subject to vibration monitoring. Such an approach has been used to date in the context of monitoring through oil debris analysis, and this approach is extended in this paper to the vibration monitoring context. The Weibull proportional-hazards model is reviewed along with the software EXAKT used for optimization. In particular the case considers condition-based maintenance for circulating pumps in a coal wash plant that is part of the SASOL petrochemical company. The condition-based maintenance policy recommended in this study is based on histories collected over a period of 2 years, and is compared with current practice. The policy is validated using data that arose from subsequent operation of the plant.
157 citations
Journal Article•
TL;DR: In this paper, a simple recursive method for characterizing Poisson process functionals that requires only the use of conditional probability is described, which is useful for convex hulls, extremes, stable measures, infinitely divisible random variables and Bayesian nonparametric priors.
Abstract: Functionals of Poisson processes arise in many statistical problems. They appear in problems involving heavy-tailed distributions in the study of limiting processes, while in Bayesian nonparametric statistics they are used as constructive representations for nonparametric priors. We describe a simple recursive method that is useful for characterizing Poisson process functionals that requires only the use of conditional probability. Applications of this technique to convex hulls, extremes, stable measures, infinitely divisible random variables and Bayesian nonparametric priors are discussed.
16 citations
TL;DR: In this paper, the authors considered estimating the coefficient of a maximum autoregressive process of order one under a parametric assumption for innovations and derived its limiting distribution under the assumption that the distribution for the innovations has a regularly varying tail at infinity.
Abstract: We consider estimating the coefficient of a maximum autoregressive process of order one. Under a parametric assumption for innovations, the exact distribution of this estimate is calculated using a recursion method while, under the assumption that the distribution for the innovations has a regularly varying tail at infinity, we derive its limiting distribution.
1 citations
Posted Content•
TL;DR: In this paper, the authors considered estimating the coefficient of a maximum autoregressive process of order one under a parametric assumption for innovations and derived its limiting distribution under the assumption that the distribution for the innovations has a regularly varying tail at infinity.
Abstract: We consider estimating the coefficient of a maximum autoregressive process of order one. Under a parametric assumption for innovations, the exact distribution of this estimate is calculated using a recursion method while, under the assumption that the distribution for the innovations has a regularly varying tail at infinity, we derive its limiting distribution.
1 citations