y - JOUR A2 - Krolczyk, Grzegorz M. AU - Li，姚龙AU - Li，洪儒AU - Wang, Bing AU - Gu，Hongqiang PY - 2017 DA - 2017/10/12 TI - Rolling Element Bearing Performance Degradation Assessment Using Variational Mode Decomposition and Gath-Geva Clustering Time Series Segmentation SP - 2598169 VL - 2017 AB -提出了一种基于变分模式分解(VMD)和Gath-Geva聚类时间序列分割(GGCTSS)的方法。VMD是一种新的分解方法。由于与经验模态分解(EMD)、局部均值分解(LMD)、局部特征尺度分解(LCD)等递归分解方法不同，VMD需要先验参数。在本文中，我们将提出一种基于遗传算法的VMD参数优化方法，即分解模式个数和适度带宽约束。利用所获得的参数执行VMD，得到blimf。通过计算结构的包络线，选取敏感结构。然后将缺陷频率(ADF)的幅值作为退化特征。为了得到性能退化评估，我们将使用Gath-Geva聚类时间序列分割方法。 Afterwards, the method is carried out by two pieces of run-to-failure data. The results indicate that the extracted feature could depict the process of degradation precisely. SN - 1023-621X UR - https://doi.org/10.1155/2017/2598169 DO - 10.1155/2017/2598169 JF - International Journal of Rotating Machinery PB - Hindawi KW - ER -