维护与备件库存管理是海上风电运维的两个密不可分的关键环节。为提高海上风电机组设计寿命周期内的运维经济性,构建状态维护与备件库存联合优化策略。首先,将海上风电机组构建为由叶片、齿轮箱、电气、偏航、轮毂、制动、传动链、发电机8个子系统组成的系统,然后将各子系统的劣化过程构建为多状态马尔可夫随机过程,建立维护与备件库存的交互模型,其中包括被动维护时间与随机故障以及备件库存的关系、备件库存对维护活动的影响等。随后,设计子系统的劣化状态与备件库存状态、状态检修动作与备件订购的表征方法,并以此形成深度强化学习Dueling DQN的框架,通过对深度网络的迭代训练,求解海上风电机组的最优维护与备件订购决策序列。最后,以某海上风电场内的风电机组为例,验证所提联合优化方法的优越性,并讨论强化学习的探索率、风电场的可达率对运维成本的影响。
Abstract
Maintenance and spare parts inventory management are two fundamental sequential procedures in offshore wind farm operation and maintenance （OM）. To improve the OM efficiency of offshore wind turbines （OWTs） in the design life cycle, a joint optimization strategy of condition-based maintenance and spare parts inventory control is proposed. Firstly, the OWT is constructed as a series system of subsystems including blades, gearbox, electrical, yaw,wheel hub, braking, transmission chain, generator, the deterioration process of each subsystem is modeled as a multi-state Markov process, and the coupling model of maintenance and spare parts inventory is established. Secondly, the representation and update method of subsystems deterioration, spare parts inventory are formulated as the framework of deep reinforcement learning. Through the iterative training of the deep networks, the optimal maintenance and spare parts ordering decision making are obtained. Finally, taking an OWT of a practical offshore wind farm as an example, the effectiveness of the proposed joint optimization method is verified. The impacts of the exploration rate and the accessibility of OWTs on the OM cost are further discussed.
关键词
海上风电机组 /
状态维护 /
库存控制 /
强化学习 /
联合优化
Key words
offshore wind turbines /
state maintenance /
inventory control /
reinforcement learning /
joint optimization
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] GWEC. Global offshore wind report[EB/OL].https://gwec.net/wp-content/uploads/2021/09/GWEC-offshore-wind-2021-updated-1.pdf.
[2] REN Z R, VERMA A S, LI Y, et al.Offshore wind turbine operations and maintenance: a state-of-the-art review[J]. Renewable and sustainable energy reviews, 2021, 144: 110886.
[3] ALGERN J, PETERS L, MADLENER R. Economic evaluation of maintenance strategies for offshore wind turbines based on condition monitoring systems[EB/OL]. FCN working papers, 2017-7: https://EconPapers.repec.org/RePEc:ris:fcnwpa:2017_008.
[4] 符杨, 许伟欣, 刘璐洁, 等. 考虑天气因素的海上风电机组预防性机会维护策略优化方法[J]. 中国电机工程学报, 2018, 38(20): 5947-5956.
FU Y, XU W X, LIU L J, et al.Optimization of preventive opportunistic maintenance strategy for offshore wind turbine considering weather conditions[J]. Proceedings of the CSEE, 2018, 38(20): 5947-5956.
[5] LI M X, WANG M, KANG J C, et al.An opportunistic maintenance strategy for offshore wind turbine system considering optimal maintenance intervals of subsystems[J]. Ocean engineering, 2020, 216: 108067.
[6] ZHU W J, CASTANIER B, BETTAYEB B.A dynamic programming-based maintenance model of offshore wind turbine considering logistic delay and weather condition[J]. Reliability engineering & system safety, 2019, 190: 106512.
[7] TIAN Z G, JIN T D, WU B R, et al.Condition based maintenance optimization for wind power generation systems under continuous monitoring[J]. Renewable energy, 2011, 36(5): 1502-1509.
[8] BYON E, DING Y.Season-dependent condition-based maintenance for a wind turbine using a partially observed Markov decision process[J]. IEEE transactions on power systems, 2010, 25: 1823-1834.
[9] ZHOU P, YIN P T.An opportunistic condition-based maintenance strategy for offshore wind farm based on predictive analytics[J]. Renewable and sustainable energy reviews, 2019, 109: 1-9.
[10] 黄玲玲, 符杨, 任浩瀚, 等. 基于状态信息的风电机组维护研究综述[J]. 中国电机工程学报, 2020, 40(21): 7065-7078.
HUANG L L, FU Y, REN H H, et al.Review of wind turbine maintenance based on condition monitoring systems[J]. Proceedings of the CSEE, 2020, 40(21): 7065-7078.
[11] ZHU X Y, WANG J, COIT D W.Joint optimization of spare part supply and opportunistic condition-based maintenance for onshore wind farms considering maintenance route[J]. IEEE transactions on engineering management, 2022, 262(2): 479-498.
[12] 胡迪, 高庆水, 张楚, 等. 基于系统动力学的风力机备件需求预测研究[J]. 太阳能学报, 2019, 40(3): 666-672.
HU D, GAO Q S, ZHANG C, et al.Research on demand forecast of spare parts of wind turbine based on system dynamics[J]. Acta energiae solaris sinica, 2019, 40(3): 666-672.
[13] 张再峰, 张琛, 郭盛, 等. 基于周期性预防维修的风电场备件成本分析[J]. 太阳能学报, 2018, 39(5): 1434-1439.
ZHANG Z F, ZHANG C, GUO S, et al.Analysis of spare parts cost for wind farm based on periodic preventive maintenance[J]. Acta energiae solaris sinica, 2018, 39(5): 1434-1439.
[14] 赵洪山, 刘宏杨, 宋鹏, 等. 风电机组大部件的备品备件区域库存优化控制策略[J]. 可再生能源, 2018, 36(3): 422-428.
ZHAO H S, LIU H Y, SONG P, et al.Regional inventory optimization control strategy of spare parts for big parts of wind turbines[J]. Renewable energy resources, 2018, 36(3): 422-428.
[15] NEVES-MOREIRA F, VELDMAN J, TEUNTER R H.Service operation vessels for offshore wind farm maintenance: optimal stock levels[J]. Renewable and sustainable energy reviews, 2021, 146: 111158.
[16] 韩梦莹, 杨建华. 考虑不完美检测的两阶段点检与备件订购策略联合优化[J]. 运筹与管理, 2021, 30(3): 27-34.
HAN M Y, YANG J H.Joint optimization of two-phase inspection and spare parts ordering policies considering imperfect inspection[J]. Operations research and management science, 2021, 30(3): 27-34.
[17] 王孟雅, 陈震, 潘尔顺. 基于马尔科夫决策的冷贮备串联系统状态维修与备件联合优化[J]. 工业工程与管理, 2022, 27(6): 14-23.
WANG M Y, CHEN Z, PAN E S.Joint optimization of condition-based maintenance and spare parts for cold standby series system considering Markov decision[J]. Industrial engineering and management, 2022, 27(6): 14-23.
[18] 杨建华, 韩梦莹. 视情维修条件下k/N(G)系统备件供需联合优化[J]. 系统工程与电子技术, 2019, 41(9): 2148-2156.
YANG J H, HAN M Y.Joint optimization of spare parts supply-demand for k/N(G) system under condition-based maintenance[J]. Systems engineering and electronics, 2019, 41(9): 2148-2156.
[19] ZHENG M M, YE H Q, WANG D, et al.Joint optimization of condition-based maintenance and spare parts orders for multi-unit systems with dual sourcing[J]. Reliability engineering & system safety, 2021, 210: 107512.
[20] ANG J, ZHU X Y.Joint optimization of condition-based maintenance and inventory control for a k-out-of-n:F system of multi-state degrading components[J]. European journal of operational research, 2021, 290(2): 514-529.
[21] KUSHWAHA A, GOPAL M, SINGH B.Q-learning based maximum power extraction for wind energy conversion system with variable wind speed[J]. IEEE transactions on energy conversion, 2020, 35(3): 1160-1170.
[22] LAMBERT N O, SCHINDLER C B, DREW D S, et al.Nonholonomic yaw control of an underactuated flying robot with model-based reinforcement learning[J]. IEEE robotics and automation letters, 2021, 6(2): 455-461.
[23] ZHAO H, ZHAO J H, QIU J, et al.Cooperative wind farm control with deep reinforcement learning and knowledge-assisted learning[J]. IEEE transactions on industrial informatics, 2020, 16(11): 6912-6921.
[24] RAUSAND M, BARROS A, HOYLAND A.System reliability theory: models, statistical methods, and applications[M]. Norway: John Wiley & Sons, 2003.
[25] 白恺, 宋鹏. 风电机组检修决策[M]. 北京: 中国电力出版社, 2021.
BAI K, SONG P.Maintenance decision of wind turbine[M]. Beijing: China Electric Power Press, 2021.
[26] SUTTON R S, BARTO A G.Reinforcement learning: an introduction[M]. 2nd ed. London: MIT Press, 2018.
[27] LE B, ANDREWS J.Modelling wind turbine degradation and maintenance[J]. Wind energy, 2016, 19: 571-591.
[28] CARROLL J, MCDONALD A, MCMILLAN D.Failure rate, repair time and unscheduled O&M cost analysis of offshore wind turbines[J]. Wind energy, 2016, 19(6): 1107-1119.
[29] BVGA. Wind farm costs[EB/OL].https://guidetoanoffsh orewindfarm.com/wind-farm-costs.
[30] SSAI C I, BOSWELL B, DAVIES I J.A Markovian approach for modelling the effects of maintenance on downtime and failure risk of wind turbine components[J]. Renewable energy, 2016, 96(PA): 775-783.
基金
电网输变电设备防灾减灾国家重点实验室开放项目《国网湖南防灾减灾中心台风灾害下高比例海上风电并网系统弹性管理》
PDF(1864 KB)
