Fault diagnosis method for wind turbine rolling bearings based on Hankel tensor decomposition
Authors:
Open Access
- 5 November 2018
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Renewable Power Generation
- Vol. 13 (2) , 220-226
Abstract
In order to diagnose the wind turbine rolling bearing faults with vibration signals effectively, a fault diagnosis method based on Hankel tensor decomposition is proposed. Firstly, IMF‐SVD (intrinsic mode function, IMF; singular value decomposition, SVD) is used to estimate the number of sources in sensor observation signals. Secondary, a third‐order Hankel tensor is formed by the observation matrix, and a set of low‐rank tensor subterms are obtained by tensor rank‐ decomposition. The fault features of each source are contained in the first and second modes of the corresponding subterm. Then, the source signals are reconstructed by the subterms. Finally, the envelope spectra of the reconstructed source signals are analysed, and the fault characteristic frequencies are extracted. The results of simulation and practical case analysis show that this method can realise the fault diagnosis of wind turbine rolling bearings correctly and effectively.Keywords
This publication has 16 references indexed in Scilit:
- Diagnosis of non‐linear mixed multiple faults based on underdetermined blind source separation for wind turbine gearbox: simulation, testbed and realistic scenariosIET Renewable Power Generation, 2017
- Sparse component analysis‐based under‐determined blind source separation for bearing fault feature extraction in wind turbine gearboxIET Renewable Power Generation, 2017
- Fault diagnosis of wind turbine bearing based on variational mode decomposition and Teager energy operatorIET Renewable Power Generation, 2016
- Artificial neural network and empirical mode decomposition based imbalance fault diagnosis of wind turbine using TurbSim, FAST and SimulinkIET Renewable Power Generation, 2016
- The structure healthy condition monitoring and fault diagnosis methods in wind turbines: A reviewRenewable and Sustainable Energy Reviews, 2015
- Tensor Decompositions for Signal Processing Applications: From two-way to multiway component analysisIEEE Signal Processing Magazine, 2015
- Rolling element bearing fault diagnosis based on non‐local means de‐noising and empirical mode decompositionIET Science, Measurement & Technology, 2014
- A brief status on condition monitoring and fault diagnosis in wind energy conversion systemsRenewable and Sustainable Energy Reviews, 2009
- Tensor Decompositions and ApplicationsSIAM Review, 2009
- Principal component analysis and blind source separation of modulated sources for electro-mechanical systems diagnosticMechanical Systems and Signal Processing, 2005