基于SCADA运行数据的风电机组发电性能劣化监测研究

风电机组的发电效率和发电性能对风电场的运行水平和经济效益有重要影响。文章采用风电机组SCADA运行数据对机组发电性能劣化进行监测。首先,采用偏最小二乘方法确定对风电机组发电功率有密切影响的多个变量;然后,采用高斯过程回归方法建立反映机组发电性能的功率曲线模型,有效提高建模精度;在监测阶段,引入指数加权移动平均值控制图(EWMA)分析功率曲线模型的功率预测残差,及时准确地发出风电机组发电性能劣化预警;最后,以某风电机组叶轮转速传感器故障导致的发电性能劣化实例,验证了该方法的有效性。

Wind turbine performance degradation monitoring with SCADA data

Wind turbine power generating efficiency and performance have great impact to operating level and economic profit of wind farm.This paper uses the SCADA data to monitor the wind turbine performance degradation.Firstly,PLS method is used to select the variables which have close relationship with the wind turbine power.Gaussian Process Regression(GPR)is introduced to construct the power curve model with a satisfied modeling accuracy.In the monitoring period,the EWMA control chart is used to analyze the prediction residual of power curve model and gives the performance degradation alarm.With a wind turbine performance degradation example caused by rotor speed sensor failures,the method proposed in this paper is proved to be effective.