Planetary Gearbox Fault Diagnosis Based on ICEEMD-Time-Frequency Information Entropy and VPMCD

Autor: Hongmei Liu, Xin Gao, Yihan Wang, Zhonghui Fan
Jazyk: angličtina
Rok vydání: 2020
Předmět:
Zdroj: Applied Sciences
Volume 10
Issue 18
Applied Sciences, Vol 10, Iss 6376, p 6376 (2020)
ISSN: 2076-3417
DOI: 10.3390/app10186376
Popis: Planetary gearboxes are more and more widely used in large and complex construction machinery such as those used in aviation, aerospace fields, and so on. However, the movement of the gear is a typical complex motion and is often under variable conditions in real environments, which may make vibration signals of planetary gearboxes nonlinear and nonstationary. It is more difficult and complex to achieve fault diagnosis than to fix the axis gearboxes effectively. A fault diagnosis method for planetary gearboxes based on improved complementary ensemble empirical mode decomposition (ICEEMD)-time-frequency information entropy and variable predictive model-based class discriminate (VPMCD) is proposed in this paper. First, the vibration signal of planetary gearboxes is decomposed into several intrinsic mode functions (IMFs) by using the ICEEMD algorithm, which is used to determine the noise component by using the magnitude of the entropy and to remove the noise components. Then, the time-frequency information entropy of intrinsic modal function under the new decomposition is calculated and regarded as the characteristic matrix. Finally, the fault mode is classified by the VPMCD method. The experimental results demonstrate that the method proposed in this paper can not only solve the fault diagnosis of planetary gearboxes under different operation conditions, but can also be used for fault diagnosis under variable operation conditions. Simultaneously, the proposed method is superior to the wavelet entropy method and variational mode decomposition (VMD)-time-frequency information entropy.
Databáze: OpenAIRE