经验模态分解和神经网络在滚动轴承故障诊断中应用研究

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的滚动轴承故障诊断方法,对采集的信号范围进行了筛选。利用经验模态分解将振动信号分解为多个平稳的固有模态函数。选取包含主要故障信息的IMF分量分析其时域和频域特征。将时域信号特征量和频谱图峰值对应的频率归一化处理,输入Elman神经网络进行工作状态的自动判断。

Research of Application of Empirical Mode Decomposition and Neural Network into Diagnosis of Rolling Bearing Fault

According to the non-stationary characteristics of vibration signals of rolling bearing fault, a kind of fault diagnosis method of rolling bearing based on empirical mode decomposition is put forward, and signal range is screened. With the empirical mode decomposition, original signal is decomposed into several smooth intrinsic mode functions. The IMF component containing main fault information is selected, and dominate features of the time domain and frequency are analyzed. The time domain signal characteristics and the corresponding spectrum peak frequency have been handled through normalized processing, and then they have been imported into Elman neural network for automatic judgment of the working state.