基于EMD和BP网络的轴承故障诊断方法

Method of bearing fault diagnosis based on EMD and BP neural network

故障轴承的振动信号是非平稳信号,传统的非平稳信号分析手段存在许多不足;BP网络能够出色地解决传统识别模式难以解决的复杂问题。提出了经验模态分解(EMD)与BP神经网络相结合的滚动轴承故障诊断方法。采用EMD方法对振动信号进行分解,得到组成信号的多个内禀模态分量(IMF),提取重要的IMF分量的能量作为信号的特征量;采用BP网络作为模式分类器,对轴承的故障类型进行分类。经试验数据分析证明,该方法能够准确地对轴承故障进行诊断。

The vibration signal of fault rolling bearing is nonstationary, traditional methods of analyzing the nonstationary signal have some deficiencies; BP neutral network can well solve complex problems that are difficult to be solved through traditional recognition mode. The method of rolling bearing fault diagnosis presented in this article combines with the empirical mode decomposition （EMD） and BP neural network. The EMD method is used to decompose the beating vibration signal, multiple intrinsic mode funetion（IMF） components composed the signal are acquired, IMF energy is used to be the characteristic quantity of signal; BP network is adapted to be the fault mode classifier and classify the bearing fault type. The analysis of experiment data shows that the method can diagnose the bearing fault accurately.