IMF能量和RBF神经网络相结合在滚动轴承故障诊断中的应用研究

The application research on the combination of IMF energy and RBF neural network in rolling bearing fault diagnosis

针对滚动轴承的故障特点,提出了一种将IMF能量与RBF神经网络相结合的方法用于故障诊断。该方法首先利用经验模态分解(EMD)方法,把振动信号分解为若干个IMF分量,再用重要的IMF分量求得IMF能量特征向量,最后将特征向量输入RBF神经网络进行故障模式分类。通过对滚动轴承的正常状态、内圈故障、滚动体故障和外圈故障信号的分析结果表明,该方法能够准确、有效地识别这些故障。

According to the characteristics of rolling bearing fault, This paper put forward a fault diagnosis method combining IMF energy and RBF neural network. This method firstly use the empirical mode decomposition （EMD） method to decompose the vibration signal into some IMF component, then garnish with important IMF component to obtain characteristic vector of IMF energy, finally put feature vector into RBF neural network fault to classify the fault pattern. Through the signal analysis of the normal state, inner ring fault, roller ring fault and outer ring fault, showing that the method can accurately, effectively identify these fault.