一种风力发电机自动故障诊断及预测方法

Automatic Fault Diagnosis and Prediction of Wind Turbines

为了获得故障信号精确的时域和频域信息,提出了一种Morlet小波变换补偿方法,首先计算出故障信号的时间和频率信息,然后根据Morlet小波系数中心频率峰值对计算的故障信号的幅值进行补偿,得出故障信号的准确幅值.采用Simulink模型证明该方法的可行性,并将该方法应用到测试风力发电机和实际大型风力发电机的电功率信号分析中.结果表明:该方法可以自动获得故障信号按时序排列的振幅趋势图,显示了部件发生故障后的剩余使用寿命期限;风力发电机特别是海上风力发电机的维护维修计划可根据此时间信息进行制定,降低风电运维成本.

A Morlet wavelet-based compensated algorithm was proposed to calculate the accurate amplitudes of faulty signals.The specific way is to compute the time range and frequency values of the faulty signals at first,and then to compensate the amplitudes calculated for above faulty signals according to the center frequency values of Morlet wavelet coefficients to further obtain the accurate amplitudes.A Simulink model was used to demonstrate the feasibility and generalization of the algorithm.At the same time,the algorithm was used to analyze the electric power signals of a test rig and large turbines.Results show that this algorithm can automatically find the amplitude trend of faulty components in a time sequence,and indicate the residual service life of wind turbines after faults are generated.Based on the information of the residual service life,the maintenance and repairing plan for wind turbines,especially offshore ones,can be developed to lower the cost of wind power in operation and maintenance.