An optimal condition-based maintenance policy for a degrading system subject to the competing risks of soft and hard failure
An optimal condition-based maintenance policy for a degrading system subject to the competing risks of soft and hard failure
复制标题
DOI：
10.1016/j.cie.2015.02.003
复制
发表时间：
2015-05
期刊：
影响因子：
--
通讯作者：
D. Tang;Jinsong Yu;Xiongzi Chen;V. Makis
中科院分区：
文献类型：
--
作者：
D. Tang;Jinsong Yu;Xiongzi Chen;V. Makis
本文考虑了在等距、离散时间时期进行状态监测的退化系统存在竞争风险（软故障和硬故障）的情况下的维护问题。开发了具有时间效应的随机系数自回归模型来描述系统退化。系统年龄、先前的状态观察和退化的项目间变异性共同组合在所提出的退化模型中。与硬故障相对应的故障率的特征在于其对系统寿命和退化状态的依赖性。我们提出了一种维护策略，当硬故障的故障率达到一定阈值时启动预防性维护。用于优化维护策略的计算算法是在半马尔可夫决策过程框架中开发的，其目标是最小化长期预期平均成本。通过数值算例证明了该方法的有效性。
The paper considers a maintenance problem in the presence of competing risks (soft and hard failure) for a degrading system subject to condition monitoring at equidistant, discrete time epochs. A random-coefficient autoregressive model with time effect is developed to describe the system degradation. The system age, previous state observations, and the item-to-item variability of the degradation are jointly combined in the proposed degradation model. The failure rate corresponding to the hard failure is characterized by its dependency on the system age and the degradation state. We propose a maintenance policy which initiates preventive maintenance when the failure rate of the hard failure reaches a certain threshold. Computational algorithms for the optimization of the maintenance policy are developed in a semi-Markov decision process framework, with the objective of minimizing the long-run expected average cost. The effectiveness of the proposed method is demonstrated by numerical examples.