小波包变换和隐马尔可夫模型在轴承性能退化评估中的应用

Wavelet packet transform and hidden Markov model based bearing performance degradation assessment

轴承是旋转机械中的关键部件,有效地对其进行性能退化评估对指导设备维护、防止设备意外失效有非常重要的意义。为此提出了一种基于小波包变换和隐马尔可夫模型(HMM)的轴承性能退化评估方法。该方法使用小波包变换对轴承振动信号进行分析,并提取节点能量及其总能量作为特征,仅使用正常状态下的数据训练HMM,建立性能退化评估模型,然后使用该模型对轴承的退化程度进行定量评估。最后,通过对轴承加速疲劳寿命试验的研究,验证了所提出的方法的可行性和有效性。

It is important to assess the performance degradation degree of bearings in rotating machinery for making maintenance plans and preventing unexpected defects and breakdowns during operation. A novel bearing performancc degradation assessment methodology was presented based on wavelet packet transform （WPT） and hidden Markov models （HMMs）. The WPT was used to extract features from vibration signals of bearings, while the node energies and the total energy were selected as feature parameters. An HMM was trained using the data under normal condition and then tile trained HMM was used to assess the performance degradation degree of bearings quantitatively. A bearing accelerated life test was performed to validate the proposed methodology. The experimental resuhs show that the proposed methodology i,- feasible and effective.