基于LabVIEW的滚动轴承故障智能诊断系统

摘要

Rolling bearing fault diagnosis system is developed by LabVIEW platform, in which it includes resonance demodulation diagnosis and BP neural network diagnosis. The fault frequency identification of resonance demodulation diagnosis is achieved by Hilbert demodulation and wavelet packet demodulation. For the BP neural network diagnosis, features from the dimensions, dimensionless parameters and wavelet relative energy can be taken as the input vector of neural network. Type of bearing failure can be taken as the output vector of neural network, and the neural network completes the fault diagnosis. The experimental result proves the effectiveness of the intelligent diagnosis system for rolling bearing faults and determines the type of fault.%利用LabVIEW平台开发了齿轮故障诊断系统。系统主要采用共振解调诊断和BP神经网络诊断两种方法。共振解调诊断由Hilbert解调和小波包解调实现故障频率识别；BP神经网络诊断由对有量纲和无量纲参量提取的特征以及根据小波相对能量提取的特征作为神经网络的输入向量，轴承的故障类型作为输出向量，采用神经网络对轴承进行诊断，实验结果表明：通过解调和神经网络诊断，该系统能有效识别齿轮故障，确定故障类型。