Fault diagnosis method for spherical roller bearing of wind turbine based on variational mode decomposition and singular value decomposition

Xueli An,Hongtao Zeng

doi:10.21595/jve.2016.16553

Abstract

For the non-stationary characteristics of the vibration signal of wind turbine’s roller bearing in fault condition, a bearing fault diagnosis method based on variational mode decomposition (VMD) and singular value decomposition (SVD) is proposed. The VMD method is used to decompose wind turbine’s roller bearing’s fault vibration signal into several components. These components are regard as initial feature vector matrix. The singular value decomposition of the matrix is done. The obtained singular value is used as the extracted bearing fault feature vectors. The probabilistic neural network is used as pattern recognition classifier to determine the working state and fault type of wind turbine roller bearings. The result of case study showed that the proposed method can effectively identify the working state and fault type of wind turbine roller bearings.

Highlights

Bearing is a key component of rotating machinery
Case study shows that this proposed method can effectively identify the operating states and fault types of wind turbine rolling bearings
Singular value decomposition of initial feature vector matrix is done to extract the characteristic of vibration signal

Summary

Introduction

Bearing is a key component of rotating machinery. It is core component of wind turbine’s mechanical drive system. The fault types are difficult to identify and difficult to determine the fault location [2] It has become the key for diagnosing the fault of rolling bearing, that how to extract fault feature information from the corresponding complex fault signals. The original non-stationary vibration signal is decomposed, and selecting the appropriate frequency bands or component to mine the information of signal This is a commonly used means of fault diagnosis. By means of reconstructing phase space attractor orbit matrix of fault signal, performing SVD, selecting appropriate singular value to reconstruct the fault signal, the fault features of fault signal can effectively extract It has a good noise reduction effect, has been widely applied to the fault diagnosis of rotating machinery. VMD method is used to decompose vibration signal of rolling bearing into several components These components are selected to form an initial feature vector matrix. Case study shows that this proposed method can effectively identify the operating states and fault types of wind turbine rolling bearings

Variational mode decomposition

Bearing fault diagnosis method of wind turbine based on VMD and SVD

Case study

Conclusions