| 引用本文: | 黄玲玲,王全德,应飞祥,何川,符杨.考虑多机会因素融合的海上风电场预测性机会维护策略[J].电力自动化设备,2025,45(12):209-217. |
| HUANG Lingling,WANG Quande,YING Feixiang,HE Chuan,FU Yang.Predictive opportunity maintenance strategy for offshore wind farm considering integration of multiple opportunity factors[J].Electric Power Automation Equipment,2025,45(12):209-217. |
|
| 摘要: |
| 海上风电场经济运维是一个复杂博弈优化问题，其面向多机组多部件，涉及海上气象条件、海上交通与吊装维护工具等约束，机组预防性维护可能造成设备剩余寿命浪费，事后维护可能导致长时间停机损失。对此，在对海上风电场机组机会维护因素进行归纳与分类的基础上，提出了一种包含机组部件故障预警与状态预测信息、海上低风速条件以及海上多类型交通与维护工具约束等的多机会维护因素模型，并建立了考虑多机会因素融合的海上风电场预测性机会维护决策优化模型。然后，通过构建动态三时间窗不断更新部件状态和外界风浪变化信息，利用粒子群优化算法对海上风电场进行维护决策优化求解。通过包含50台风电机组的海上风电场算例验证了所提维护策略模型与算法的有效性与优越性。 |
| 关键词: 海上风电场 多机会因素 故障预警 动态三时间窗 维护资源兼容性 机会维护 |
| DOI：10.16081/j.epae.202510017 |
| 分类号:TM614 |
| 基金项目:国家自然科学基金资助项目(52177097) |
|
| Predictive opportunity maintenance strategy for offshore wind farm considering integration of multiple opportunity factors |
|
HUANG Lingling1, WANG Quande2, YING Feixiang2, HE Chuan2, FU Yang3
|
|
1.Engineering Research Center of Offshore Wind Technology，Ministry of Education(Shanghai University of Electric Power),Shanghai 200090, China;2.College of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China;3.Engineering Research Center of Offshore Wind Technology Ministry of Education(Shanghai University of Electric Power),Shanghai 200090, China
|
| Abstract: |
| The economic operation and maintenance of offshore wind farm is a complex game optimization problem. It is oriented towards multiple units and components and involves constraints such as marine meteorological conditions, marine traffic, and hoisting and maintenance tools. Preventive maintenance of units may cause waste of the remaining service life of the equipment, and post-maintenance may lead to long-term downtime losses. In this regard, based on the classification of the opportunistic maintenance factors of offshore wind farm units, a multi-opportunity maintenance factor model is proposed, which includes fault warning and status prediction information of unit components, offshore low wind speed conditions, and constraints of various types of offshore traffic and maintenance tools. Additionally, a predictive opportunistic maintenance optimization model for offshore wind farm is established considering multiple opportunity factor fusion. Subsequently, by constructing a dynamic three-time window to continuously update the prediction information of component state and external wind and wave conditions, the particle swarm optimization algorithm is employed to optimize the maintenance decision. A case study of an offshore wind farm with 50 wind turbines verifies the effectiveness and superiority of the proposed model and algorithm. |
| Key words: offshore wind farm multiple opportunity factors fault warning dynamic three-time window maintain resource compatibility opportunity maintenance |
