基于平滑先验分析和模糊熵的滚动轴承故障诊断

由于机械系统的复杂性,振动信号的随机性表现在不同尺度上,基于对振动信号进行多尺度的模糊熵(FE)分析,提出了基于平滑先验分析(SPA)和模糊熵的滚动轴承故障诊断方法。采用SPA方法对振动信号进行自适应分解,得到振动信号的趋势项和波动项;分别计算趋势项和波动项的模糊熵;将模糊熵值作为特征向量,输入至基于优化算法的支持向量机(OSVM)。将该方法应用于滚动轴承实验数据,分析结果表明:该方法在仅提取两个分量特征的情况下即可达到100%的故障诊断精度,可有效实现滚动轴承的故障诊断。 

Rolling bearing fault diagnosis based on smoothness priors approach and fuzzy entropy

Due to the complexity of mechanical systems, the randomicity of the vibration signal on different scales, it’s necessary to analyze the vibration signal with fuzzy entropy (FE) in a multi-scale way. Based on multi-scale fuzzy entropy analysis of vibration signals, a method of rolling bearing fault diagnosis based on FE and the smoothness priors approach (SPA) was put forward. The SPA algorithm was used to decompose the vibration signal, and the trend with de-trend was obtained. Secondly, the FE of the trend and de-trend was calculated. The FE entropies were accordingly seen as the characteristic vectors, then inputed to the optimized support vector machine (OSVM). Finally, the proposed method was applied to the experimental data. The analysis results showthat the proposed approach can achieve 100% fault diagnosis accuracy when only two component features are extracted, so it can effectively achieve fault diagnosis of rolling bearings.