基于SCADA数据分析的风机变桨故障诊断

摘要

In order to diagnose the wind turbine pitch fault quickly and effectively,and avoiding the limitations of the traditional fault diagnosis method,according to massive SCADA data on a wind field,this paper choose wind speed,pitch angle and power for the research,the three parameters are closely related with the pitch fault.First of all,the related original SCADA data are processed using an effective data pre-processing method and get the features of the SCADA data.Then,a fault diagnosis method based on analyzing the correlation of the SCADA data is investigated to diagnose the pitch faults in a wind turbine.The experimental results show that this method can not only diagnose the wind turbine pitch faults effectively but also distinguish two common types of pitch faults.%为了及时有效地检测出风电机组的变桨故障,同时避免传统故障诊断方法的局限性,该文基于某风场的海量SCADA数据,选择与变桨故障密切相关的3个参数:风速、桨距角和功率进行研究.首先,利用一种有效的数据预处理方法来处理SCADA原始数据并提取出能够反映故障信息的特征值.然后,基于分析SCADA数据之间的相关性研究变桨故障诊断方法.最后,通过实验验证了此方法不但可以有效地对风电机组进行变桨故障诊断而且可以判断出2种常见的变桨故障类型.