【作者】 李萌； 陆爽； 陈岱民；

【Author】 Li Meng Lu Shuang Chen Daimin (College of Mechanical Engineering, Changchun University, Changchun 130022, China)

【机构】 长春大学机械工程学院；

【摘要】 通过对滚动轴承振动信号特征分析,采用小波包变换方法对其建立频域能量特征向量以减少输入维数,进而构造出了轴承特征空间和故障空间的模式,然后采用径向基函数人工神经网络,通过该网络的学习和训练,实现了两个空间之间的非线性映射,完成了滚动轴承故障模式的识别。同时应用Matlab软件强大的计算功能,设计建立了滚动轴承智能故障诊断系统。理论和实验证明了该系统的有效性,且具有较高的识别精度。更多还原

【Abstract】 State monitoring and fault diagnosing of rolling hearing 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 in not applicable for the fault bearing whose signal is unstable. Aceording to the vibration signal features of frequency-domain, the energy eigenveetor using wavelet packet transform is established to reduce the input dimension. The patterns of characteristic space and fault space of rolling bearings are presented. Radial basis function neural networks is employed and the learning and training are achieved. Nonlinear mapping between the two spaces and the recognition of fault patterns are derived. An intelligent fault recognition system of rolling bearings is established by using Matlab. Theory and experiment show that the system is available and precise.更多还原