论文部分内容阅读
针对滚动轴承振动信号的非平稳特性和在现实条件下难以获取大量故障样本的实际情况,提出一种经验模态分解、非线性动力学方法—样本熵和支持向量机相结合的故障诊断方法。运用经验模态分解方法对其去噪信号进行分析,利用互相关系数准则对固有模式分量进行筛选,再计算所选分量的样本熵以组成故障特征向量,并将其作为支持向量机的输入以识别滚动轴承的状态。利用实际滚动轴承试验数据的诊断与对比试验验证了该方法的有效性和泛化能力。
Aiming at the non-stationary characteristics of rolling bearing vibration signal and the fact that it is difficult to obtain a large number of fault samples under realistic conditions, a fault diagnosis method based on empirical mode decomposition and nonlinear dynamics method, ie, sample entropy and support vector machine, is proposed. Empirical mode decomposition method is used to analyze the de-noised signals. The inherent mode components are screened by the cross-correlation coefficient criterion. Then the sample entropy of the selected components is calculated to form the fault eigenvector, which is used as the input of the support vector machine Identify the condition of the roller bearing. The actual rolling bearing test data diagnosis and comparative tests verify the effectiveness and generalization ability of the method.