Abstract:

In order to improve the fault diagnosis efficiency of the inner ring, rolling element and outer ring of rolling bearings, a method of fault diagnosis is proposed based on dual-tree complex wavelet packet transform and Support Vector Machine（SVM）. The vibration signal is decomposed and reconstructed through dual-tree complex wavelet packet. The energy features are extracted in the reconstructed signal and taken as input of the support vector machine. The parameters of the support vector machine are not easy to determine, which reduces the accuracy of fault diagnosis, so artificial fish swarm algorithm is employed to optimize the coefficients. The better support vector machine is used to identify the fault type of rolling bearings. The experimental results prove that the de-noising effect of the proposed method is better than the traditional method and it can extract fault characteristic effectively, which can improve the accuracy of fault diagnosis.

Key words: roller bearings, Support Vector Machine（SVM）, fault diagnosis, dual-tree complex wavelet package, artificial fish swarm algorithm

摘要：

为了提高滚动轴承内圈、滚动体、外圈等故障诊断效率，提出了将双树复小波包和支持向量机（Support Vector Machine，SVM）结合的故障诊断方法。采用双树复小波包对轴承振动信号分解和重构，提取重构信号中的故障能量特征并构造特征样本作为支持向量机诊断模型的输入。针对支持向量机的参数选取没有固定方法而导致故障诊断的准确性降低的问题，采用人工鱼群算法对支持向量机的惩罚系数和核参数进行寻优。用寻优得到的参数建立支持向量机诊断模型对特征样本进行故障诊断。仿真结果表明提出的方法不仅可以提高降噪效果从而得到滚动轴承故障振动的特征信号，而且能实现更高精度的故障诊断。

关键词: 滚动轴承, 支持向量机, 故障诊断, 双树复小波包, 人工鱼群算法