基于小波包和支持向量机的滚动轴承故障诊断

Roller Bearing Fault Diagnosis Based on Wavelet Packet and Support Vector Machine

为解决滚动轴承的振动信号非平稳特性和故障样本不足的问题,构建以小波包变换、能量特征向量和支持向量机为基础的故障诊断系统。小波包变换具有时域和频域局部化的优点,可有效分解滚动轴承的非平稳信号。能量特征向量能减少故障诊断系统的样本数据,提高计算效率。支持向量机解决了滚动轴承缺少故障样本数据的问题。实验证明,该诊断模型可有效识别滚动轴承的故障类型。

In order to solve the problem of non-stationary property of the vibration signal and the lack of fault samples of roller bearing,the fault diagnosis system was structured based on wavelet packet transform,energy feature vector and support vector machine.Wavelet packet transform has the advantage of time-frequency localization,can discompose the non-stationary signal of roller bearing effectively.Energy feature vector can reduce the sample data of fault diagnosis,increase the computation efficiency.Support vector machine can solve the problem of the lack of fault sample data of roller bearing.The experiment result indicates that this model can recognize the fault type of roller bearing effectively.