| Autor: |
Lu Wang, Hui Liu, Jie Liang, Lijuan Zhang, Qingchang Ji, Jianqiang Wang |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
Frontiers in Energy Research, Vol 10 (2022) |
| Druh dokumentu: |
article |
| ISSN: |
2296-598X |
| DOI: |
10.3389/fenrg.2022.944961 |
| Popis: |
The rotor system is a core part of rotating machinery equipment. Its safe and reliable operation directly affects the economic benefit of using the equipment and the personal safety of users. To fully explore the complex feature mapping relationship between rotor vibration signals and fault types, rotor vibration signals were studied under different working conditions from the perspective of feature parameter construction and feature information mining. First, a variational mode decomposition algorithm was used to decompose the vibration signals, and quantum behavior particle swarm optimization was used to minimize the mean envelope entropy of intrinsic mode function components to determine the optimal combination of modal number and penalty coefficient. Second, the principal component analysis was used to reduce the dimensionality of IMF components of vibration signals. Finally, a support vector machine was used to mine the feature mapping relationship between vibration data after dimensionality reduction and rotor operation state to accurately identify rotor fault types. The proposed method was used to analyze the measured vibration signals of the rotor system. The experimental results showed that the proposed method effectively extracted characteristic information of the rotor running state from the vibration data, and the accuracies of four types of fault diagnoses were 100%, 88.89%, 100%, and 100%, respectively. In addition, the accuracies of the four fault diagnoses in this study were better than those of the previously reported models. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
