【作者】 郭树言； 王国锋； 户满堂； 张旭东；

【Author】 Shuyan Guo;Guofeng Wang;Mantang Hu;Xudong Zhang;School of Mechanical Engineering,Tianjin University;

【机构】 天津大学机械工程学院；

【摘要】 为了更好地描述滚动轴承的性能退化趋势,提出了一种基于小波包分解(WPD)、主成分分析(PCA)、近邻传播聚类(AP)的滚动健康评估方法。首先,使用WPD对滚动轴承振动信号进行分解,然后,提取原始信号的时域特征、频域特征和小波包节点能量构造高维特征向量,使用PCA对提取的高维特征向量进行特征融合。以正常和最终失效数据为训练样本,利用近邻传播聚类建立评价模型,将被测数据相对于正常状态隶属度定义为退化指标。在加速轴承寿命试验中的应用结果表明,该指标能有效地反映轴承的性能退化情况。更多还原

【Abstract】 In order to better characterize the performance degradation trend of rolling bearings,a new performance degradation assessment method based on wavelet packet decomposition(WPD),principal component analysis(PCA) and affinity propagation clustering(AP) was proposed.First,the rolling bearing vibration signal is decomposed using WPD.Then,the time domain features,frequency domain features and wavelet node energy structure high-dimensional feature vectors of the original signal are extracted,Then PCA is used to reduce the dimension of the high-dimensional feature vectors.Normal and final failure data are used as training samples to build assessment model utilizing affinity propagation,and the subjection of tested data to normal state is defined as the degradation indicator.Results of its application to accelerated bearing life test show that this indicator can reflect effectively performance degradation of bearing.更多还原