Optimal preventive maintenance scheduling for wind turbines under condition monitoring

关于发电机检修调度问题的交替混合整数规划模型线性松弛紧性的研究

On the tightness of linear relaxations of alternative mixed integer programming formulations for the generator maintenance scheduling problem

本文针对预防性发电机检修调度问题的六种混合整数规划模型展开线性松弛紧性分析，识别出对偶界更优、计算性能更好的模型，为改进检修调度过程的模型选择提供理论依据。

Leaf It to Renewal: 通过更新理论与决策树改进预测性维护策略

Leaf It to Renewal: Improved Predictive Maintenance Policies via Renewal Theory and Decision Trees

提出一种混合规划方法，基于更新-奖励过程成本与预后模型信息，推导仅含少量参数的预测性维护策略，在预防性更换与订购中表现高效且抗过拟合。

面向可持续城市的气候适应性电动汽车充电基础设施：用于预防性维护和低碳出行的可解释因果集成框架

Climate-resilient electric vehicle charging infrastructure for sustainable cities: An interpretable causal-ensemble framework for preventive maintenance and low-carbon mobility

研究针对城市气候压力增加电动汽车充电设施故障风险问题，开发FGDSE框架，通过划分特征家族、添加专家及门控机制预测故障风险，经SHAP归因等扩展为因果决策支持，实验表明其性能优越，能助力气候适应性维护与低碳出行。

Seizing Opportunity: Maintenance Optimization in Offshore Wind Farms Considering Accessibility, Production, and Crew Dispatch

Operations and Maintenance (O&M) constitute a major contributor to offshore wind's cost of energy. Due to the harsh and remote environment in which offshore turbines operate, there has been a growing interest in opportunistic maintenance scheduling for offshore wind farms, wherein grouping maintenance tasks is incentivized at times of opportunity. Our survey of the literature, however, reveals that there is no unified consensus on what constitutes an "opportunity" for offshore maintenance. We therefore propose an opportunistic maintenance scheduling approach which defines an opportunity as eit…

分支扩展：面向串联系统的基于 prognostics 的更换策略

Branching out: Prognostics-Based Replacement Policies for Series Systems

该研究提出一种混合规划方法，用于推导串联系统的基于 prognostics 的预测性维护策略，该策略参数少、效率高且抗过拟合能力强，在预防性更换和订购场景中性能可媲美优化基准策略。

定期和不定期的基于状态的维护

Condition-based maintenance at both scheduled and unscheduled opportunities

出于原始设备制造商（OEM）的服务和维护的做法，我们认为一个单一的组件在故障情况下更换和两种类型的预防性维护的机会：计划，这是由于定期系统审查的设备，和不定期的，这是由于系统中的其他组件的故障发生。适当地模拟组件的状态，并结合一个现实的费用结构的纠正性维护以及基于状态的维护（CBM），我们得出最佳的CBM政策。特别是，我们表明，最佳的长期平均成本的政策，手头的模型是一个控制限制政策，控制限制取决于时间，直到下一个预定的机会。此外，我们明确地计算长期的平均成本为任何给定的控制限制不定常政策和比较各种政策的数字。

Optimization of On-condition Thresholds for a System of Degrading Components with Competing Dependent Failure Processes

An optimization model has been formulated and solved to determine on-condition failure thresholds and inspection intervals for multi-component systems with each component experiencing multiple failure processes due to simultaneous exposure to degradation and shock loads. In this new model, we consider on-condition maintenance optimization for systems of degrading components, which offers cost benefits over time-based preventive maintenance or replace-on-failure policies. For systems of degrading components, this can be a particularly difficult problem because of the dependent degradation and d…

A Decomposition Method by Interaction Prediction for the Optimization of Maintenance Scheduling

Optimizing maintenance scheduling is a major issue to improve the performance of hydropower plants. We study a system of several physical components of the same family: either a set of turbines, a set of transformers or a set of generators. The components share a common stock of spare parts and experience random failures that occur according to known failure distributions. We seek a deterministic preventive maintenance strategy that minimizes an expected cost depending on maintenance and forced outages of the system. The Auxiliary Problem Principle is used to decompose the original large-scale…

具有发布日期和截止日期的网络维护作业调度：边界和求解策略

Scheduling Network Maintenance Jobs with Release Dates and Deadlines to Maximize Total Flow Over Time: Bounds and Solution Strategies

我们考虑一个问题，结婚的网络流和调度，出于需要安排维护活动的基础设施网络，如铁路或一般的物流网络。网络元件必须进行定期的预防性维护，在活动期间关闭电弧。仔细协调这些电弧维护作业可以显著降低这种关闭作业对网络所承载的流量的影响。在给定的发布日期和最后期限之间调度这些作业，以使总流量随时间最大化，这是研究时间离散化作用的一个有趣的案例。在这里，我们证明，如果问题数据是整数，没有流可以存储在节点，我们可以限制注意整数作业开始时间。然而，如果可以存储流量，则可能需要部分开始时间。这使得传统的强整数规划调度模型难以应用。在这里，我们制定了一个精确的整数规划模型的连续时间问题，以及整数规划模型的基础上的时间离散化，可以提供双重界限，并可以-与微小的修改-也产生原始的界限。由此产生的边界上的测试实例证明有小的差距，并提供了一个很好的权衡约束质量对计算时间。

满载工况下变速变桨操纵风力机的线性变参数功率调节

Linear Parameter Varying Power Regulation of Variable Speed Pitch Manipulated Wind Turbine in the Full Load Regime

针对满载工况下风速湍流变化导致的功率波动与机械载荷问题，提出LPV H_inf变桨控制器，相较PI-Fuzzy提升鲁棒稳定性、瞬态稳态性能并降低载荷。

维护与备件供应的数据驱动联合优化：一种分布鲁棒方法

Data-driven joint optimization of maintenance and spare parts provisioning: A distributionally robust approach

针对预测模型估计的剩余寿命分布不准确问题，提出分布鲁棒机会约束（DRCC）公式及MILP重构，协调状态维护与备件供应，在风电案例中优于随机规划和鲁棒优化基准。

注意力机制是优化风电场运维所需的全部方法

Attention is All You Need to Optimize Wind Farm Operations and Maintenance

针对风电场运维优化中传统混合整数规划求解耗时长的问题，提出嵌入MIP模型的多头注意力决策框架，实现秒级求解、保证可行解、提升解质量并具备强迁移能力。