Rolling bearing combined fault diagnosis method based on multi-domain feature construction

US12366504B2 · kind B2 · utility

Assignee

• GUANDONG OCEAN UNIVERSITY · CN

Inventors

• Qiang Liu · Lo Wu, CN
• Guoyan YU · Zhanjiang, CN
• Jiawei Zhang · Sunnyvale, US
• Bo Wen · New York, US
• Xiaoming Xu · Zhanjiang, CN
• Zheng Liu · Shanghai, CN
• Donglin Hou · Zhanjiang, CN
• Jiale Liao · Zhanjiang, CN

Key dates

• Filing date: Jan 1, 2025
• Grant date: Jul 22, 2025
• Expiry date: Jan 1, 2045

Classification

• Technology area (CPC G): Physics
• CPC primary: G01M13/045
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

A rolling bearing combined fault diagnosis method based on a multi-domain feature construction is provided, including: collecting vibration signals of rolling bearings, extracting time-domain and frequency-domain features of fault-sensitive vibration signals of the rolling bearings, and obtaining an in-domain feature set; performing an improved empirical mode decomposition on the vibration signals of the rolling bearings to obtain time-frequency features; constructing a multi-domain fault sample set based on the in-domain feature set and the time-frequency features; performing a fault mechanism analysis on the multi-domain fault sample set to obtain modulation features under each single fault; carrying out a feature engineering on the time-domain and frequency-domain features, and screening out relevant features, redundant features and irrelevant features; performing an unsupervised hierarchical clustering on test set fault samples, and then inputting the test set fault samples into a KNN model for a classification, and obtaining rolling bearing combined fault diagnosis results.