Bearing fault diagnosis of a wind turbine based on variational mode decomposition and permutation entropy

Abstract

Variational mode decomposition is a new signal decomposition method, which can process non-linear and nonstationary signals. It can overcome the problems of mode mixing and compensate for the shortcomings in empirical mode decomposition. Permutation entropy is a method which can detect the randomness and kinetic mutation behavior of a time series. It can be considered for use in fault diagnosis. The complexity of wind power generation systems means that the randomness and kinetic mutation behavior of their vibration signals are displayed at different scales. Multi-scale permutation entropy analysis is therefore needed for such vibration signals. This research investigated a method based on variational mode decomposition and permutation entropy for the fault diagnosis of a wind turbine roller bearing. Variational mode decomposition was adopted to decompose the bearing vibration signal into its constituent components. The components containing key fault information were selected for the extraction of their permutation entropy. This entropy was used as a bearing fault characteristic value. The nearest neighbor algorithm was employed as a classifier to identify faults in a roller bearing. The experimental data showed that the proposed method can be applied to wind turbine roller bearing fault diagnosis.

Related Entropy Theories Application in Condition Monitoring of Rotating Machineries

“…As a metric of non-linear behavior measurement, permutation entropy has been utilized to realize condition monitoring data analysis. The most widely used strategy is the combination of permutation entropy and decomposition methods, as given in [64][65][66][67][68][69][70]. Similar to those works in the category of energy entropy, these achieved features are mainly the metrics in time domain, frequency domain, and their combination.…”

Optimized Dynamic Mode Decomposition via Non-Convex Regularization and Multiscale Permutation Entropy

“…Bandt [33] and Zunino [34] suggested that d should be in the range 3-7. Time delay τ has little effect on the MPE of time series [35,36], and in most literatures [36][37][38], authors employ τ = 1.…”

“…In [36,38,39], the length N of time series are suggested as N > 5d!, thus the sample points of the simulation signal should be larger than 3600.…”

“…Time delay τ has little effect on the MPE of time series [35,36], and in most literatures [36][37][38], authors employ 1 τ = . In this paper, we employ…”

Compound Fault Diagnosis of Bearings Using an Improved Spectral Kurtosis by MCDK

“…Rolling bearing is one of the most widely used parts in mechanical equipment. Its operation condition affects the working state of the whole system [2][3][4][5]. The fault identification and diagnosis of rolling bearing are of great significance to ensure the safe and reliable operation of mechanical equipment.…”