首页|Bearing performance degradation assessment based on the continuous-scale mathematical morphological particle and feature fusion

Bearing performance degradation assessment based on the continuous-scale mathematical morphological particle and feature fusion

扫码查看
原文链接
  • NSTL
  • Elsevier
The partial differential equations (PDEs) driven mathematical morphology operation relates the differential evolution of the whole signal in scale space to the continuous-scale morphological operations applied to signal space. In this paper, an algorithm based on continuous-scale mathematical morphological particle (CMMP) and feature fusion is proposed for bearing performance degradation assessment. Firstly, the bearing performance degradation features are extracted based on the PDEs-driven CMMP. The CMMP features at different scales perform variously on the bearings at different degradation stages. Subsequently, the CMMP features are divided into three categories according to their sensitivity to degradation of bearing. After that, the embedded hidden Markov model (EHMM) is introduced to fuse three kinds of features into the global model. Finally, the entire life-cycle failure data sets of bearing are assessed by the proposed method and the comparing method. The results validate the superiority of the proposed method.

Rolling bearingContinuous-scale mathematical morphological particle (CMMP)Performance degradation assessment (PDA)Feature fusionEmbedded hidden Markov model (EHMM)EMPIRICAL MODE DECOMPOSITIONROLLING ELEMENT BEARINGUSEFUL-LIFE ESTIMATIONPATTERN SPECTRUMDIAGNOSISFAULTCLASSIFICATIONPREDICTIONEQUATIONSVIBRATION

Yan, Xiaoli、Tang, Guiji、Wang, Xiaolong

展开 >

Hebei Univ

North China Elect Power Univ

2022

10.1016/j.measurement.2021.110571

Measurement

Measurement

SCI
ISSN：0263-2241
年,卷(期)：2022.188
  • 4
  • 46