数字孪生驱动的风电机组变桨系统故障诊断  

Fault Diagnosis of Pitch System of Digital Twins Driven Wind Turbines

作　　者：伍云浩 滕伟[1] 王罗 彭迪康 武鑫[1] 柳亦兵[1] Yun-hao Wu;Wei Teng;Luo Wang;Di-kang Peng;Xin Wu;Yi-bing Liu(Key Laboratory of Power Station Energy Transfer Conversion and System Ministry of Education,North China Electric Power University;China Three Gorges Corporation)

机构地区：[1]华北电力大学电站能量传递转化与系统教育部重点实验室 [2]中国长江三峡集团有限公司

出　　处：《风机技术》2023年第2期63-69,共7页Chinese Journal of Turbomachinery

基　　金：国家自然科学基金资助项目(51775186)。

摘　　要：数字孪生作为连接物理世界和数字世界的纽带,其融合机理与数据的建模方式在时效性和准确性等方面有着超出以往模型的潜力。文中首先针对风电机组变桨系统故障诊断问题,结合多体动力学提出了一种风电机组数字孪生模型的建立方法;其次,利用机组运行信息与机理先验知识,并通过历史数据进行风电机组控制逻辑反演;再次,以上述模型对风电机组历史监测数据进行仿真分析,将仿真结果与历史监测数据进行对比,迭代修正数字孪生模型,并验证所建立的数字孪生模型的准确性;最后,在所建立模型的基础上构建仿真结果与实际监测数据的残差值,使用该残差值作为故障特征变量对该风电机组变桨系统故障进行诊断分析,其结果验证了上述方法的有效性和可行性。As a link connecting the physical world and the digital world,digital twins undoubtedly has more potential than previous models in terms of timeliness and accuracy.Firstly,aiming at the problem of wind turbine pitch system fault diagnosis,combined with multi-body dynamics,this paper proposes a method to establish the digital twins model of wind turbines;Secondly,the control logic of the wind turbine is deduced through the historical data on the basis of the prior knowledge of the operation information and mechanism;Thirdly,the above model is used to simulate and analyze the historical monitoring data of wind turbine.The simulation results are compared with the historical monitoring data to iteratively modify the digital twin model;Finally,based on the established model,the residual error between the simulation results and monitoring data is constructed,which is regarded as the fault characteristic variable to diagnose the fault of the wind turbine pitch system,and the results prove the effectiveness and feasibility of the above methods.

关 键 词：风电机组 故障诊断 变桨系统 数字孪生 

分 类 号：TK83[动力工程及工程热物理—流体机械及工程]