摘要
以风电机组机载风速仪为例,提出一种传感器状态自确认方法。利用多台风电机组风速的相关性,通过动态时间规整算法,选定一组风电机组群。构建基于自联想神经网络的风电机组群风速仪预测模型,采用历史正常数据通过麻雀搜寻优化算法对模型进行训练,根据实际值与预测值的关系对风速仪状态进行识别。通过仿真实验证明该方法可识别风速仪模拟异常状态,最后对某风场实际风速进行检测,结果显示能有效识别出风速仪的状态,实现风电机组风速仪状态的自确认。
In this study,a method of sensor status self-confirmation is proposed,taking the wind turbine airborne anemometer as an example. A group of wind turbines is selected by a dynamic time warping algorithm,following the correlation of wind speed of multiple wind turbines. The prediction model of the wind turbine group anemometer based on an auto-association neural network is constructed.The model is trained by the sparrow search optimization algorithm with normal historical data,and the state of the anemometer is determined according to the relationship between the actual value and the predicted value. The simulation experiment proves that the method can identify the abnormal state of anemometer simulation. Finally,the actual wind speed of the wind farm is detected. The results show that this method can reliably identify the state of the anemometer and acquire the self-confirmation of the state of the anemometer of the wind turbine.
作者
周凌
赵前程
石照耀
王宪
阳雪兵
Zhou Ling;Zhao Qiancheng;Shi Zhaoyao;Wang Xian;Yang Xuebing(Engineering Research Center of Hunan Province for the Mining and Utilization of Wind Turbines Operation Data,Hunan University of Science and Technology,Xiangtan 411201,China;Hunan University of Technology College of Electrical and Information Engineering,Zhuzhou 412002,China;Beijing Engineering Research Center of Precision Measurement Technology and Instruments,Beijing University of Technology,Beijing 100124,China;Hadian Wind Energy Co.,Ltd.,Xiangtan 411102,China)
出处
《太阳能学报》
EI
CAS
CSCD
北大核心
2022年第11期172-178,共7页
Acta Energiae Solaris Sinica
基金
国家自然科学基金(51875199,51905165)
湖南自然科学基金(2019JJ50186)。
关键词
风电机组
风速仪
自联想神经网络
麻雀搜寻算法
状态自确认
wind turbine
anemometer
auto-associative neural network
sparrow search algorithm
state self-confirmation
