A fault diagnosis scheme for planetary gearboxes using modified multi-scale symbolic dynamic entropy and mRMR feature selection

Yongbo Li, Yuantao Yang, Guoyan Li, Minqiang Xu, Wenhu Huang

Research output: Contribution to journalArticlepeer-review

247 Scopus citations

Abstract

Health condition identification of planetary gearboxes is crucial to reduce the downtime and maximize productivity. This paper aims to develop a novel fault diagnosis method based on modified multi-scale symbolic dynamic entropy (MMSDE) and minimum redundancy maximum relevance (mRMR) to identify the different health conditions of planetary gearbox. MMSDE is proposed to quantify the regularity of time series, which can assess the dynamical characteristics over a range of scales. MMSDE has obvious advantages in the detection of dynamical changes and computation efficiency. Then, the mRMR approach is introduced to refine the fault features. Lastly, the obtained new features are fed into the least square support vector machine (LSSVM) to complete the fault pattern identification. The proposed method is numerically and experimentally demonstrated to be able to recognize the different fault types of planetary gearboxes.

Original languageEnglish
Pages (from-to)295-312
Number of pages18
JournalMechanical Systems and Signal Processing
Volume91
DOIs
StatePublished - 1 Jul 2017
Externally publishedYes

Keywords

  • Fault diagnosis
  • Modified multi-scale symbolic dynamic entropy (MMSDE)
  • mRMR
  • Planetary gearboxes

Fingerprint

Dive into the research topics of 'A fault diagnosis scheme for planetary gearboxes using modified multi-scale symbolic dynamic entropy and mRMR feature selection'. Together they form a unique fingerprint.

Cite this