Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline

Article Types

Countries / Regions

Search Results (1)

Search Parameters:
Keywords = symbolic dynamics entropy (SDE)

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
19 pages, 5291 KB  
Article
Fault Diagnosis Method of Motor Bearing Under Variable Load Condition Based on Parameter Optimization VMD-NLMS
by Youbing Li, Zhenning Zhu, Zhixian Zhong and Guangbin Wang
Appl. Sci. 2025, 15(5), 2607; https://doi.org/10.3390/app15052607 - 28 Feb 2025
Cited by 1 | Viewed by 509
Abstract
Given that the fault information of motor bearing is submerged due to strong noise under variable load conditions, a fault diagnosis method of motor bearing based on parameter optimization variational mode decomposition (VMD) and normalized least mean square (NLMS) is proposed. Firstly, VMD’s [...] Read more.
Given that the fault information of motor bearing is submerged due to strong noise under variable load conditions, a fault diagnosis method of motor bearing based on parameter optimization variational mode decomposition (VMD) and normalized least mean square (NLMS) is proposed. Firstly, VMD’s modal number K and α penalty factor are optimized by symbolic dynamic entropy (SDE). Then, the VMD algorithm with optimized parameters is used to extract the fault signals of bearing inner and outer rings under different load conditions. Then, the appropriate intrinsic mode decomposition (IMF) is selected, according to the weighted kurtosis index to reconstruct the fault feature signals. Finally, the NLMS algorithm reduces noise in the reconstructed signal and highlights the fault characteristics. The fault characteristics are analyzed by envelope demodulation. The RMSE and SNR of the simulated signal are calculated by filtering the improved method. It is found that the RMSE of the filtered signal is reduced 60%, and the signal-to-noise ratio is increased by about 119.87%. Compared to the sparrow search algorithm (SSA)-optimized VMD method, the proposed approach shows significant improvements in fault feature extraction. This study provides an effective solution for motor bearing fault diagnosis in noisy and variable load environments. Full article
Show Figures

Figure 1

Back to TopTop