A fault pulse extraction and feature enhancement method for bearing fault diagnosis

Chen, Zhiqiang; Guo, Liang; Gao, Hongli; Yu, Yaoxiang; Wenxin, Wu; You, Zhichao; Dong, Xun

doi:10.1016/j.measurement.2021.109718

Cited by 33 publications

(14 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional feature extraction methods are mainly applicable to the analysis of linear stationary signals, but it is difficult to analyze nonlinear and nonstationary signals. The feature extraction method based on nonlinear dynamics can better analyze the bearing signal and realize the bearing fault diagnosis [3]. Common nonlinear dynamic characteristics include Lempel-Ziv complexity (LZC), dispersion entropy (DE), fractal dimension (FD), and Lyapunov exponent (LE).…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Four Nonlinear Dynamic Characteristics in Feature Extraction of Bearing Fault Diagnosis

Zhang

Liang

2022

Journal of Sensors

View full text Add to dashboard Cite

To effectively extract the fault features of bearing signals in complex environments, four common nonlinear dynamic characteristics are used to analyze and compare the simulated signals and measured bearing fault signals in this paper, including Lempel-Ziv complexity (LZC), dispersion entropy (DE), Lyapunov exponent (LE), and fractal dimension (FD). Three groups of simulation experiments were carried out, and the simulation results show that all nonlinear dynamic characteristics can reflect the complexity change trend of MIX signal; compared with LZC and LE, DE and FD can better reflect the frequency change of amplitude modulated trend of chirped signal; only DE can reflect the amplitude change trend of amplitude modulated chirped signal. The experiments of feature extraction and classification are carried out for bearing fault signals. It concluded that compared with LZC, LE, and DE, FD has better stability and classification performance with the minimum standard deviation and the highest recognition rate.

show abstract

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Four Nonlinear Dynamic Characteristics in Feature Extraction of Bearing Fault Diagnosis

Zhang

Liang

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Chen et al [173] combined symplectic geometric mode decomposition and cepstrum pre-whitening, and finally extracted the fault features of rolling bearings using envelope analysis. Chen et al [174] combined cepstrum pre-whitening, spectral kurtosis and spectral correlation density methods, and finally used envelope analysis to extract bearing features.…”

Section: Cepstrum Pre-whiteningmentioning

confidence: 99%

Review of spectrum analysis in fault diagnosis for mechanical equipment

Wang,

Sun

2023

Eng. Res. Express

View full text Add to dashboard Cite

Various mechanical equipment play a crucial role, and their health or status may affect efficiency and safety seriously. Spectrum analysis of the corresponding signal has been widely used to diagnose the fault in the past decades. The diagnosis method based on spectrum analysis technology covers almost all aspects of mechanical fault diagnosis. However, there is a lack of review of diagnostic methods of spectrum analysis technologies in the field of mechanical equipment fault diagnosis. In order to fill this gap, this paper reviews the spectrum analysis technology in mechanical equipment diagnosis in detail. First of all, in order to let the researchers who are in contact with spectrum analysis technology for the first time quickly understand this field, the principles of spectrum are systematically sorted out, including spectrum, cepstrum, energy spectrum, power spectrum, higher-order spectrum, Hilbert spectrum, marginal spectrum, envelope spectrum, singular spectrum and so on. Furthermore, the characteristics of corresponding spectrum analysis technologies are summarized, and their advantages and disadvantages are analyzed and compared. High-quality references in recent ten years are cited for illustration to enhance persuasiveness. Finally, the prospect of spectrum analysis technology is summarized, and the future development trend of spectrum analysis technology is pointed out. It is believed that the joint diagnosis of fault severity, variable speed fault diagnosis, combined with deep learning and multiple spectrum analysis technologies should be given more attention in the future. This paper is expected to provide a comprehensive overview of mechanical fault diagnosis based on spectrum analysis theory, and help to develop corresponding spectrum analysis technologies in practical engineering.

show abstract

“…The one-dimensional signals is split with fixed patch length, and the determination of patch length can be ignored by the subsequent processing of transformer encoder in the study by Pei et al 31 However, this is just another way indirectly thinking about patch length. The fault pluse extraction can be realized by dictionary learning method in the study by Chen et al, 32 but the patch length in this work was only given by empirical setting.…”

Section: Introductionmentioning

confidence: 99%

Wind turbine pitch bearing fault detection with Bayesian augmented temporal convolutional networks

Zhang

2023

Structural Health Monitoring

View full text Add to dashboard Cite

There are few studies on the fault diagnosis of deep learning in real large-scale bearings, such as wind turbine pitch bearings. We present a novel fault diagnosis method, Bayesian augmented temporal convolutional network (BATCN), to filter the raw signal in wind turbine pitch bearing defect detection. This method, which employs temporal convolutional neural networks, is designed to capture the temporal dependencies of the signal, with such a focus on non-stationary relationships in the collected signals. By referring to the thoughts of Bayesian optimization, our approach can spontaneously find the best patch length that influences fault signal extraction during the filtering process, avoiding manual tuning of this hyper-parameter. This BATCN method is first performed on simulation signals and an open-source dataset of general bearings, and then validated on industrial wind turbine pitch bearings both in the lab and in the real wind farm, where the bearings have been operated for over 15 years. The results show that our method can work well for large-scale slow-speed wind turbine pitch bearings.

show abstract

A fault pulse extraction and feature enhancement method for bearing fault diagnosis

Cited by 33 publications

References 40 publications

A Comparative Study of Four Nonlinear Dynamic Characteristics in Feature Extraction of Bearing Fault Diagnosis

A Comparative Study of Four Nonlinear Dynamic Characteristics in Feature Extraction of Bearing Fault Diagnosis

Review of spectrum analysis in fault diagnosis for mechanical equipment

Wind turbine pitch bearing fault detection with Bayesian augmented temporal convolutional networks

Contact Info

Product

Resources

About