|
| Fault Feature Extraction Method of Rolling Bearing Based on CYCBD and Sparrow Search Algorithm |
| |
| View Full Text View/Add Comment Download reader |
| DOI：10.7643/issn.1672-9242.2022.08.006 |
| KeyWord:rolling bearing fault feature extraction sparrow search algorithm CYCBD rolling tail missile strong noise |
| Author | Institution |
| CONG Xiao |
Intelligent Manufacturing College, Shandong Business Institute, Shandong Yantai , China |
| LI Gen |
Naval Aeronautical University, Shandong Yantai , China |
|
| Hits: |
| Download times: |
| Abstract: |
| The paper aims to solve the problem that the effect of maximum second-order cyclostationary blind deconvolution (CYCBD) algorithm in rolling bearing fault feature extraction is not good in strong noise environment, and provide a method reference for rolling bearing fault diagnosis of rolling tail missile. A method using sparrow search algorithm (SSA) to optimize CYCBD algorithm is proposed. The envelope spectral entropy of deconvolution of CYCBD algorithm is taken as the fitness function of SSA optimization. The appropriate cycle frequency and filter length are efficiently found by SSA. After adaptive parameter selection, CYCBD algorithm is used to effectively deconvolute to obtain periodic pulse characteristics. At the same time, the envelope spectrum of fault feature extraction before and after SSA optimization CYCBD is compared. The noise amplitude of CYCBD is not more than 0.13 m/s2, and the peak value is not more than 0.29 m/s2. The noise amplitude of CYCBD optimized by SSA is not more than 0.08 m/s2, and the peak value is not more than 0.32 m/s2. The fault frequency component is more prominent, and the noise amplitude and peak amplitude characteristics are greatly improved compared with CYCBD. The simulation results verify that the SSA optimized CYCBD method can more clearly identify the fault characteristic frequency and its frequency doubling components, and it has a good engineering application prospect. |
| Close |
|
|
|