摘要
近年来,随着风电机组向大型化快速发展,其偏航对风不准问题越来越引起关注,偏航对风不准会降低机组的发电量,影响叶片的疲劳载荷。最先进的校正方法是采用激光雷达测风,但由于成本过高,不适合长期操作和大规模实施。围绕数据驱动的方式展开研究,无须加装额外的仪器,通过机组的SCADA数据实现偏航对风不准的检测。首先介绍了现有的偏航对风不准识别方法的特点,在此基础上提出了一种基于分区统计异常率的方法,根据机组的偏航控制策略,将对风误差-风速的二维区间进行分区划分,通过计算风向标异常率识别由于风向标零点漂移导致的偏航对风不准;然后采用多个风电机组的SCADA数据进行效果验证。结果表明:基于分区统计异常率的方法对实际的生产数据适用性和通用性更强,检测结果与风电场检修人员反馈结果可以实现良好的匹配,验证了方法的有效性。
In recent years,wind turbine yaw misalignment that tends to degrade the turbine power production and impact the blade fatigue loads raises more attention along with the rapid development of large-scale wind turbines.The state-of-the-art correction methods require additional instruments such as LiDAR to provide the ground truths and are not suitable for long-term operation and large-scale implementation due to the high costs.This paper focuses on the data-driven way to carry out research,without additional instruments,through the SCADA data to achieve yaw misalignment detection.Firstly,the characteristics of the existing methods of yaw misalignment identification are introduced.Then,the method based on zoning statistical anomaly rate was proposed,according to the yaw control strategy of the wind turbine,the two-dimensional interval of yaw misalignment-wind speed will be partitioned.Zero drift of wind direction is identified by calculating wind direction sensor anomaly rate.Then,the SCADA data of several wind turbines were used to verify the effectiveness.The results show that the method based on zonal statistical anomaly rate has stronger applicability and universality to the actual production data,and the detection results can be well matched with the feedback results of maintenance personnel,which verifies the effectiveness of the method.
作者
徐鹤
曹彬
王俊峰
岳文彦
杨宇凡
Xu He;Cao Bin;Wang Junfeng;Yue Wenyan;Yang Yufan(CECEP Wind-power Corporation Co.,Ltd,Beijing 100034,China)
出处
《环境工程》
CAS
CSCD
北大核心
2023年第S02期982-986,共5页
Environmental Engineering
基金
中国节能环保集团重大科技创新项目“基于风电场数据的人工智能和大数据挖掘”(cecep-zdkj-2020-010)
关键词
风电机组
偏航对风不准
数据驱动
基于分区统计
风向标异常率
wind turbines
yaw misalignment
data-driven
based on partition statistics
anomaly rate of wind direction sensor
作者简介
第一作者:徐鹤(1994-),女,工程师,主要研究方向为风电大数据挖掘。xuhe01@cecepc.cn;通信作者:岳文彦(1986-),男,高级工程师,主要研究方向为大数据技术、工业物联网技术。yuewenyan@cecwpc.cn
