Abstract
The performance of a gearbox is sensitive to failures, especially in the long-term high speed and heavy load field. However, the multi-fault diagnosis in gearboxes is a challenging problem because of the complex and non-stationary measured signal. To obtain fault information more fully and improve the accuracy of gearbox fault diagnosis, this paper proposes a feature extraction method, hierarchical refined composite multiscale fluctuation dispersion entropy (HRCMFDE) to extract the fault features of rolling bearing and the gear vibration signals at different layers and scales. On this basis, a novel fault diagnosis scheme for the gearbox based on HRCMFDE, ReliefF and grey wolf optimizer regularized extreme learning machine is proposed. Firstly, HRCMFDE is employed to extract the original features, the multi-frequency time information can be evaluated simultaneously, and the fault feature information can be extracted more fully. After that, ReliefF is used to screen the sensitive features from the high-dimensional fault features. Finally, the sensitive features are inputted into the optimized regularized extreme learning machine to identify the fault states of the gearbox. Through three different types of gearbox experiments, the experimental results confirm that the proposed method has better diagnostic performance and generalization, which can effectively and accurately identify the different fault categories of the gearbox and outperforms other contrastive methods.
Original language | English |
---|---|
Article number | 4585 |
Number of pages | 28 |
Journal | Mathematics |
Volume | 10 |
Issue number | 23 |
DOIs | |
Publication status | Published - 3 Dec 2022 |
Bibliographical note
Funding Information:This study was supported by the National Natural Science Foundation of China (52275505) and supported by the research (JZX7Y20220144100101).
Publisher Copyright:
© 2022 by the authors.
Keywords
- fault diagnosis
- gearbox
- grey wolf
- hierarchical refined composite multiscale fluctuation dispersion entropy (HRCMFDE)
- regularized extreme learning machine
- Relief
ASJC Scopus subject areas
- Computer Science (miscellaneous)
- General Mathematics
- Engineering (miscellaneous)