基于EMD的奇异值分解技术在滚动轴承故障诊断中的应用

针对滚动轴承故障振动信号的非平稳特征,提出了一种基于经验模态分解(EmpiricalModeDecomposition,简称EMD)和奇异值分解技术的滚动轴承故障诊断方法。该方法首先采用EMD方法将滚动轴承振动信号分解为多个平稳的内禀分量(IntrinsicModefunction,简称IMF)之和,并形成初始特征向量矩阵。然后对初始特征向量矩阵进行奇异值分解得到矩阵的奇异值,将其作为滚动轴承振动信号的故障特征向量,并输入神经网络来识别滚动轴承的工作状态和故障类型。实验分析结果表明,本文方法能有效地应用于滚动轴承故障诊断。

Application of EMD Based Singular Value Decomposition Technique to Fault Diagnosis for Roller Bearing

According to the non-stationary characteristics of vibration signals from fault roller bearing a fault diagnosis approach for roller bearings based on EMD (Empirical Mode Decomposition)method and singular value decomposition technique is proposed. The EMD method is used to decompose the vibration signal of a roller bearing into a number of IMF (Intrinsic Mode Function) components from which the initial feature vector matrix is formed. By applying the singular value decomposition technique to the initial feature vector matrix, the decomposed singular values serve as the fault characteristic vector and are input into the neural network, and then the work condition and fault patterns are identified by the output of the neural network. The experimental results show that the proposed approach can be applied to the roller bearings fault diagnosis effectively.