Research on feature extraction and intelligent diagnosis method of reciprocating compressor bearing clearance fault

Abstract This study presents an innovative approach to fault diagnosis in sliding bearings, targeting the challenges posed by weak fault signals and heavy noise interference. The proposed method employs a generalized multi-scale permutation entropy (GMPE) algorithm, which utilizes a multi-scale mean...

Full description

Saved in:
Bibliographic Details
Main Author: Feng Yan
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Journal of Engineering and Applied Science
Subjects:
Online Access:https://doi.org/10.1186/s44147-025-00667-z
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract This study presents an innovative approach to fault diagnosis in sliding bearings, targeting the challenges posed by weak fault signals and heavy noise interference. The proposed method employs a generalized multi-scale permutation entropy (GMPE) algorithm, which utilizes a multi-scale mean coarse-graining strategy to effectively capture dynamic transitions in signals. To overcome the shortcomings of traditional binary tree support vector machine (BTSVM) classifiers—such as slow convergence and error accumulation due to early misclassifications—an enhanced BTSVM model is introduced to reduce error propagation. The effectiveness of the method is validated on both reciprocating compressor sliding bearings and automotive rolling bearings, achieving a fault diagnosis accuracy of over 99%. These results highlight a significant advancement in mechanical fault detection and demonstrate the strong potential of combining GMPE with an improved BTSVM for accurate fault diagnosis in complex machinery.
ISSN:1110-1903
2536-9512