A sparse auto-encoder method based on compressed sensing and wavelet packet energy entropy for rolling bearing intelligent fault diagnosis

Improving diagnostic efficiency and shortening diagnostic time is important for improving the reliability and safety of rotating machinery, and has received more and more attention. When using intelligent diagnostic methods to diagnose bearing faults, the increasingly complex working conditions and...

Full description

Saved in:
Bibliographic Details
Published in:Journal of mechanical science and technology 2020, 34(4), , pp.1445-1458
Main Authors: Shi, Peiming, Guo, Xiaoci, Han, Dongying, Fu, Rongrong
Format: Article
Language:English
Subjects:
Coders
Control
Detection
Diagnostic systems
Dynamical Systems
Eigenvectors
Engineering
Entropy
Fault diagnosis
Feature extraction
Industrial and Production Engineering
Machine learning
Mechanical Engineering
Original Article
Roller bearings
Rotating machinery
Vibration
Wavelet analysis
기계공학
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Improving diagnostic efficiency and shortening diagnostic time is important for improving the reliability and safety of rotating machinery, and has received more and more attention. When using intelligent diagnostic methods to diagnose bearing faults, the increasingly complex working conditions and the huge amount of data make it a great challenge to diagnose fault quickly and effectively. In this paper, a novel fault diagnosis method based on sparse auto-encoder (SAE), combined with compression sensing (CS) and wavelet packet energy entropy (WPEE) for feature dimension reduction is proposed. Firstly, vibration signals of each fault type are projected linearly through compressed sensing to obtain compressed signals, which are merged into a low-dimensional compressed signal matrix of multiple fault types. Secondly, the WPEE of low-dimensional compressed signal matrix of multi-fault type is determined, and the eigenvector matrix of bearing fault diagnosis is formed, which greatly reduces the dimension of the eigenvector matrix. Finally, SAE are constructed by adding sparse penalty to auto-encoder (AE) for high-level feature learning and bearing fault classification, and it not only further learns the high-level features of data, but also reduces the feature dimension. Compared with traditional feature extraction methods and the standard deep learning method, the proposed method not only guarantees high accuracy, but also greatly reduces the diagnosis time.
ISSN:1738-494X
1976-3824
DOI:10.1007/s12206-020-0306-1