基于温度参数的风电机组异常识别  

On line optimization of wind turbine based on temperature

作　　者：邢月 顾煜炯[1,2] 马丽[1] Xing Yue;Gu Yujiong;Ma Li(School of Energy,Power and Mechanical Engineering,North China Electric Power University,Beijing 102206,China;State Key Laboratory for New Energy Power Systems,North China Electric Power University,Beijing 102206,China)

机构地区：[1]华北电力大学能源动力与机械工程学院,北京102206 [2]华北电力大学新能源电力系统国家重点实验室,北京102206

出　　处：《可再生能源》2019年第5期743-749,共7页Renewable Energy Resources

基　　金：中央高校基本科研业务费专项资金资助项目(2017XS038)

摘　　要：文章针对风电机组运行过程中机组早期的异常状态识别问题,提出一种考虑有功功率的基于机组温度参数变化特性的风电机组异常识别模型。首先,分析风电机组各系统与温度相关的参数。然后,利用相关性理论,确定了与有功功率相关的温度参数:齿轮箱高速轴轴承前端温度、齿轮箱高速轴轴承后端温度、齿轮箱油温、发电机驱动端轴承温度、发电机非驱动端轴承温度、发电机定子绕组温度,形成了异常检测的参数体系。再次,以正常状态下机组温度参数的偏度和峰度的最大区间作为阈值,建立风电机组异常识别模型。最后,采用滑动窗口对机组运行状态进行在线监测。通过实例研究发现,当机组发生异常状态时,温度参数的偏度或者峰度超过了阈值,比警报提前了15 d。该识别模型为风电机组的早期故障预警提供了参考。In order to identify the early abnormal state of the wind turbine during operation, an online anomaly identification model based on the variation characteristics of temperature parameters was proposed. Firstly, the temperature related parameters of the wind turbine were analyzed. Secondly, the Correlation theory was used to determine the temperature parameters related to the active power.The parameter system of abnormal detection consists of the gearbox high speed bearing back end temperature, the gearbox high speed bearing front end temperature, the gearbox oil temperature, the temperature of the drive end bearing, the temperature of the non-drive end bearing,the temperature of the stator winding. Thirdly, an anomaly identification model of wind turbine was established by taking the maximum interval of the skewness and kurtosis of the unit parameters as the threshold value.Finally, the sliding window was used to monitor the running status of the unit online. It is found that the skewness or kurtosis of the temperature parameter exceeds the threshold when the unit is abnormal,which is 15 days earlier than the alarm. The wind turbine abnormality recognition model based on temperature parameters lays the foundation for early failure warning of wind turbines.

关 键 词：风电机组 有功功率 异常识别 相关性理论 偏度和峰度 

分 类 号：TK83[动力工程及工程热物理—流体机械及工程]