Fault gear identification using vibration signal with discrete wavelet transform technique and fuzzy-logic inference

Jian Da Wu, Chuang Chin Hsu

Research output: Contribution to journalArticle

47 Citations (Scopus)

Abstract

This paper described a development of the fault gear identification system using the vibration signal with discrete wavelet transform and fuzzy-logic inference for a gear-set experimental platform. The proposed system consisted of a combination of signal feature extraction using discrete wavelet transform technique and fault identification using fuzzy-logic inference. Traditionally, the technique for fault diagnosis in rotating machinery depends on the experience of the technician. However, the rotating machinery may be operated in a complex and noisy environment. The conventional diagnosis technique has difficulty detecting the fault features, such as in a noisy environment. In the present study, a discrete wavelet transform technique using vibration signals in a gear-set experimental platform is studied. The extraction method of feature vector is based on discrete wavelet transform with energy spectrum. Further, the fuzzy-logic inference is proposed to develop the diagnostic rules of the data base in the present fault identification system. The experimental works are performed to evaluate the effect of fault diagnosis in a gear-set platform under various operation conditions. The experimental results indicated the proposed expert system is effective for increasing accuracy in fault gear identification of the gear-set platform.

Original languageEnglish
Pages (from-to)3785-3794
Number of pages10
JournalExpert Systems with Applications
Volume36
Issue number2 PART 2
DOIs
Publication statusPublished - 2009 Mar

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Fault gear identification using vibration signal with discrete wavelet transform technique and fuzzy-logic inference'. Together they form a unique fingerprint.

Cite this