There is no clear standard for the number of mode decomposition and the selection of penalty factors for the method of variational mode decomposition (VMD). This paper proposes an artificial fish swarm algorithm for the parameter K and penalty factor $\alpha$ of the variational mode decomposition Perform global optimization. First, the artificial fish swarm algorithm is used to search for the optimal ($\alpha$, K) combination of VMD. In the iteration process, the fuzzy entropy of the IMF component decomposed by VMD is used as the objective function. The simulation results show that the AFSA-VMD method can be well completed adaptive acquisition of parameters K and $\alpha$, secondly, use the obtained K and $\alpha$ to decompose the rolling bearing fault signal to obtain K IMF components, select the best IMF component for filtering in the fractional domain, Finally, the 1.5-dimensional envelope spectrum is used for envelope demodulation to obtain its characteristic frequency.
Feature Extraction of Rolling Bearing Early Faults Based on AFSA-VMD
2020-10-14
447002 byte
Conference paper
Electronic Resource
English
Separation and Diagnosis of the Early Faults Vibration Signal of the Rolling Bearing
British Library Online Contents | 1998
|UAV Photogrammetry and AFSA-Elman Neural Network in Slopes Displacement Monitoring and Forecasting
Springer Verlag | 2020
|An Improved Feature Extraction Method for Rolling Bearing Fault Diagnosis Based on MEMD and PE
Online Contents | 2018
|