基于改进小波包的风电机组齿轮箱复合故障特征提取研究

针对小波包分解振动信号时会产生频谱混叠从而导致齿轮箱复合故障特征能量谱提取困难的问题,提出基于旁路滤波改进小波包的方法对双馈风电机组齿轮箱复合故障振动信号进行研究,并以风电场的大量齿轮箱振动信号为基础,运用传统小波包及旁路滤波改进小波包分别对齿轮箱振动信号提取特征能量谱。实验结果表明：运用旁路滤波改进小波包对双馈风电机组齿轮箱复合故障振动信号进行分析,可有效避免传统小波包分析振动信号的频谱混叠现象,准确提取每种故障状态的特征能量谱。

RESEARCH ON COMPOSITE FAULT FEATURE EXTRACTION OF WIND TURBINE GEARBOX BASED ON IMPROVED WAVELET PACKET

For the wavelet packet decomposition, the spectrum aliasing will occur, which will lead to the difficulty in extracting the energy spectrum of the composite fault feature of the gearbox. A method based on bypass filter to improve the wavelet packet is proposed to study the composite fault vibration signal of the doubly-fed wind turbine gearbox. Based on the vibration signal of a large number of gearboxes in the wind farm, the traditional wavelet packet and bypass filter are used to improve the wavelet packet to extract the characteristic energy spectrum of the gearbox vibration signal. Experimental results show that the bypass filter is used to improve the wavelet packet's composite fault vibration signal analysis of the doubly-fed wind turbine gearbox, which can effectively avoid the spectral aliasing of the traditional wavelet packet analysis vibration signal and accurately extract the characteristic energy spectrum of each fault state.