Scheduling preventive maintenance considering the saturation effect
Scheduling preventive maintenance considering the saturation effect
复制标题
考虑饱和效应的预防性维护计划
DOI：
10.1109/tr.2018.2874265
复制
发表时间：
2019
影响因子：
5.9
通讯作者：
Weiwen Peng
中科院分区：
文献类型：
--
作者：
Qiuzhuang Sun;Zhi-Sheng Ye;Weiwen Peng
在一个昂贵的系统的使用寿命期间，它已经是一种常见的做法，执行不完善的预防性维护（PM）的目的是预防故障和延长使用寿命。然而，即使以高频率执行不完美的PM动作，系统也不能恢复到如新的状态。这被称为饱和效应，在现有文献中通常被忽视。本研究借由一制造业公司的PM问题，提出两个PM模型来捕捉饱和效应的动态。第一种模型将系统退化分为可恢复损伤和不可逆固有疲劳。PM被假定为仅在治疗第一种类型的损伤时有效。当一些复杂系统的固有疲劳不能很好地定义，我们提出了另一种模型，概括了现有的虚拟年龄模型，允许虚拟年龄减少的比例取决于PM频率。推导了两种模型的长期平均费用，并对费用模型的优化进行了研究。提出的PM模型，然后应用到两种类型的机械系统中的制造公司。算例分析表明，忽略饱和效应会导致维修策略的劣化，从而造成重大损失。所提出的模型也被证明是强大的，在这个意义上，参数估计误差不能显着增加系统的运营成本率。
During the useful life period of a costly system, it has been a common practice to perform imperfect preventive maintenances (PMs) with the purpose of failure prevention and useful life extension. Nevertheless, a system cannot be restored to an as-good-as-new state even though the imperfect PM actions are performed with a high frequency. This is known as the saturation effect and it is commonly overlooked in the existing literature. Motivated by a PM problem in a manufacturing company, this study proposes two PM models to capture the dynamics of the saturation effect. The first model divides the system deterioration into recoverable damage and irreversible intrinsic fatigue. The PMs are assumed to be effective only in healing the first type of damage. When the intrinsic fatigue for some complex systems cannot be well defined, we propose another model that generalizes the existing virtual age models by allowing the proportion of virtual age reduction to depend on the PM frequency. The long-run average costs of the two models are derived, and optimization of the cost models is investigated. The proposed PM models are then applied to two types of mechanical systems in the manufacturing company. The case study shows that ignorance of the saturation effect will make inferior maintenance policy that incurs substantial losses. The proposed models are also shown to be robust in the sense that the parameter estimation errors cannot significantly increase the system operational cost rate.