Bearing fault diagnosis method based on fast nonlinear sparse spectrum

The invention discloses a bearing fault diagnosis method based on a fast nonlinear sparse spectrum, and relates to the technical field of vibration signal intelligent fault diagnosis. The method comprises the following steps: a preprocessing stage, which comprises carrying out signal acquisition: ta...

Full description

Saved in:
Bibliographic Details
Main Authors HAN BAOKUN, ZHANG ZONGZHEN, YANG ZUJIE, WANG JINRUI, BAO HUAIQIAN
Format Patent
LanguageChinese
English
Published 23.11.2021
Subjects
CALCULATING
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
MEASURING
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
TESTING
TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES
TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR
Online AccessGet full text

Cover

More Information
Summary:The invention discloses a bearing fault diagnosis method based on a fast nonlinear sparse spectrum, and relates to the technical field of vibration signal intelligent fault diagnosis. The method comprises the following steps: a preprocessing stage, which comprises carrying out signal acquisition: taking an acquired bearing fault vibration signal as an input sample; performing normalization processing: performing Z-score normalization processing on the collected bearing fault signal y (n), normalizing the processed sample data into distribution with a mean value of 0 and a standard deviation of 1, and performing nonlinear activation by adopting a Sigmoid function; determining the maximum decomposition layer number K: determining the maximum decomposition layer number K according to the spectrum characteristics of the signal; and carrying out spectrum boundary division, signal reconstruction, sparse spectrogram construction and fault diagnosis. According to the method, pq-mean sparse expression is introduced to
Bibliography:Application Number: CN202110940650