基于DEMD局部时频熵和SVM的风电齿轮箱故障诊断方法研究

为了有效地从非线性、非平稳性的风电齿轮箱故障信号中提取有用的信息成分,将微分经验模式分解、局部时频熵和支持向量机相结合,提出了一种微分经验模式分解局部时频熵和支持向量机的风电齿轮箱故障诊断方法。采用自适应多尺度的数学形态学对故障信号进行滤波;将滤波后的信号进行微分经验模式分解,获得齿轮振动信号的若干IMF分量;把每一个IMF进行分块,计算每一块的局部时频熵值;把局部时频熵值作为支持向量机的输入参数,通过支持向量机进行故障识别与诊断。实验结果表明,基于微分经验模式分解局部时频熵和支持向量机相结合的方法能够对风电齿轮箱故障信号进行准确有效地识别分类。

Wind Power Gear Box Fault Diagnosis Based onDEMD Local Frequency Entropy and SVM

In order to extract the constituent of useful information from the nonlinear and non-stationary wind gearbox fault signal.A new approach for wind power gear box fault diagnosis based on the combination of differential-based empirical mode decomposition(DEMD), local frequency entropy and support vector machine(SVM) is proposed.Firstly, fault vibration signal is filtered with adaptive multi-scale mathematical morphology.Then mechanical vibration signal is decomposed with DEMD to obtain a certain number of intrinsic mode functions(IMF).Then the local time-frequency entropy of the IMF components are calculated and used as the eigenvectors of SVM.Finally, the eigenvectors are put into SVM to identify the state of the wind power gear box.The experimental results show that the method based on the combination of DEMD, local time-frequency entropy and SVM can be used to recognize and classify rolling bearing fault signals accurately and effectively.