基于小波和径向基函数神经网络的滚动轴承故障模式识别

利用振动信号对滚动轴承的状态监测和故障诊断是工程中面临的难题之一，传统的基于平稳信号假设的方法不适于故障轴承的非平稳信号，有效提取故障轴承的故障特征和将故障特征准确分类是解决问题的两个关键。小波分析具有良好的时-频局部化特征，因而非常适于对瞬态或时变信号进行分类, 而人工神经网络可完成非线性系统辨识和模式分类。利用上述原理根据滚动轴承振动信号的频域变化特征，首先采用小波包分析对其建立频域能量特征向量，然后利用径向基函数神经网络完成滚动轴承故障模式的识别。试验结果表明，系统不仅能够检测到轴承故障的存在，而且能够比较准确地识别轴承的内外环故障模式，可以满足工程中的需要。

Pattern recognition of rolling bearing fault based on wavelet and radial basis function neural networks

State monitoring and fault diagnosing of rolling bearing by analyzing vibration signal is one of the major problems which need to be solved in engineering. The traditional analyzing method based on stable signal is not applicable for the fault bearing whose signal is unstable. Extracting the fault features of fault bearing efficiently and classifying these features correctly are the two linchpins for solving the problem. Wavelet analysis possesses excellent characteristic of time-frequency localization and is suitable for analyzing the time-varying or transient signals. Neural network is successful in recognizing non-linear system and classifying pattern. According to the vibration signal features of frequency-domain, energy eigenvector was established by means of wavelet packet, then recognition of fault pattern of rolling bearing was presented using radial basis function neural network. The experimental result shows that the system can not only detect the fault of bearing but also can recognize inner or outer rings fault pattern correctly. The results are of great significance for engineering application.