Gearbox Fault Diagnosis Based on Refined Time-Shift Multiscale Reverse Dispersion Entropy and Optimised Support Vector Machine

Wang, Xiang; Han, Jiang

doi:10.3390/machines11060646

Cited by 3 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study of sensitive component signal selection is usually based on some typical signal evaluation indexes. 8,9 For example, Yu Mingyue, et al, introduced Katz fractal dimension to boost the features of component signals after wavelet transform and effectively extracted the feature information including in vibration signal in the state of compound failure of intermediate bearing. 10 Nonstationary signals were decomposed into multiple empirical wavelet functions (EWF) based on empirical wavelet transform and energy value was taken as the parameter index for EWF selection, and the failure of rolling bearing was diagnosed successfully by Li et al 11 Lempel-Ziv complexity applies to the algorithm in which measurement increases with sequence length and new mode also increases.…”

Section: Introductionmentioning

confidence: 99%

A novel method to identify the multiple faults of intermediate bearing based on multiscale Lempel–Ziv complexity enhancement

Guo

Cong

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

In order to solve the difficulty to correctly identify a compound failure in intermediate bearing of aircraft engine, the paper has brought forward the method of strengthening fault feature information of intermediate bearing with weighted multiscale Lempel–Ziv complexity parameter. The method works by combining multiscale Lempel–Ziv complexity parameter (M-LZC) with wavelet transform (WT) and singular value decomposition (SVD) and implements the feature extraction and identification of compound failure in intermediate bearing. Firstly, failure information from different frequency bands of casing vibration signals is separated and signals are denoised based on WT and SVD difference spectrum. Secondly, concerning that the larger Lempel–Ziv complexity (LZC) of signal is, the more abundant failure information in signal will be; meanwhile, so as to avoid “excessive coarse graining” caused by traditional binarization method, M-LZC values of component signals after denoising are used to describe the failure feature information included in component signals. Thirdly, to further strengthen the failure feature information of intermediate bearing, larger weight value will be endowed to the component signals containing more abundant failure feature information. Failure information is boosted by M-LZC weight coefficient of component signal. Finally, component signals of an enhanced feature are reconstructed and the spectrum of reconstructed signal is used to make precise identification of compound failure type of intermediate bearing in aircraft engine.

show abstract

Section: Introductionmentioning

confidence: 99%

A novel method to identify the multiple faults of intermediate bearing based on multiscale Lempel–Ziv complexity enhancement

Guo

Cong

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

show abstract

RTSMFFDE-HKRR: A fault diagnosis method for train bearing in noise environment

He,

Zhang,

Jin

et al. 2025

Measurement

View full text Add to dashboard Cite

Fault Diagnosis Method for Wind Turbine Gearbox Based on Ensemble-Refined Composite Multiscale Fluctuation-Based Reverse Dispersion Entropy

Wang,

2024

Entropy

View full text Add to dashboard Cite

The diagnosis of faults in wind turbine gearboxes based on signal processing represents a significant area of research within the field of wind power generation. This paper presents an intelligent fault diagnosis method based on ensemble-refined composite multiscale fluctuation-based reverse dispersion entropy (ERCMFRDE) for a wind turbine gearbox vibration signal that is nonstationary and nonlinear and for noise problems. Firstly, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and stationary wavelet transform (SWT) are adopted for signal decomposition, noise reduction, and restructuring of gearbox signals. Secondly, we extend the single coarse-graining processing method of refined composite multiscale fluctuation-based reverse dispersion entropy (RCMFRDE) to the multiorder moment coarse-grained processing method, extracting mixed fault feature sets for denoised signals. Finally, the diagnostic results are obtained based on the least squares support vector machine (LSSVM). The dataset collected during the gearbox fault simulation on the experimental platform is employed as the research object, and the experiments are conducted using the method proposed in this paper. The experimental results demonstrate that the proposed method is an effective and reliable approach for accurately diagnosing gearbox faults, exhibiting high diagnostic accuracy and a robust performance.

show abstract

Gearbox Fault Diagnosis Based on Refined Time-Shift Multiscale Reverse Dispersion Entropy and Optimised Support Vector Machine

Cited by 3 publications

References 41 publications

A novel method to identify the multiple faults of intermediate bearing based on multiscale Lempel–Ziv complexity enhancement

A novel method to identify the multiple faults of intermediate bearing based on multiscale Lempel–Ziv complexity enhancement

RTSMFFDE-HKRR: A fault diagnosis method for train bearing in noise environment

Fault Diagnosis Method for Wind Turbine Gearbox Based on Ensemble-Refined Composite Multiscale Fluctuation-Based Reverse Dispersion Entropy

Contact Info

Product

Resources

About