Wavelet leaders multifractal features based fault diagnosis of rotating mechanism

Du, Wenliao; Tao, Jianfeng; Liu, Yanming; Liu, Chengliang

doi:10.1016/j.ymssp.2013.09.003

Cited by 124 publications

(38 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In reference [25], Li et al presented a semisupervised diagnosis method based on a distance-preserving self-organizing map (SS-DPSOM) to identify 4 fault states under mixed working conditions by manually extracting 19 features. In reference [26], the author utilized eight wavelet packet energy with multifractal features (8WPE-MF) to train SVMs and to realize 10 fault states diagnosed under mixed working conditions.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Fine‐Grained Fault Diagnosis Method of Rolling Bearing Combining Multisynchrosqueezing Transform and Sparse Feature Coding Based on Dictionary Learning

Sun

Gao

Lin

et al. 2019

Shock and Vibration

View full text Add to dashboard Cite

To accurately diagnose fine-grained fault of rolling bearing, this paper proposed a new fault diagnosis method combining multisynchrosqueezing transform (MSST) and sparse feature coding based on dictionary learning (SFC-DL). Firstly, the highresolution time-frequency images of raw vibration signals, including different kinds of fine-grained faults of rolling bearing, were constructed by MSST. en, the basis dictionary was trained through nonnegative matrix factorization with sparseness constraints (NMFSC), and the trained basis dictionary was employed to extract features from time-frequency matrixes by using nonnegative linear equations. Finally, a linear support vector machine (LSVM) was trained with features of training samples, and the trained LSVM was employed to diagnosis the fault classification of test samples. Compared with state-of-the-art fault diagnosis methods, the proposed method, which was tested on the bearing dataset from Case Western Reserve University (CWRU), achieved the finegrained classification of 10 mixed fault states. Meanwhile, the proposed method was applied on the dataset from the Machinery Failure Prevention Technology (MFPT) Society and realized the classification of 3 fault states under different working conditions. ese results indicate that the proposed method has great robustness and could better meet the needs of practical engineering.

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Fine‐Grained Fault Diagnosis Method of Rolling Bearing Combining Multisynchrosqueezing Transform and Sparse Feature Coding Based on Dictionary Learning

Sun

Gao

Lin

et al. 2019

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…As a robust classification methodology, support vector machine (SVM) [2] has been successfully used in the applications of bearing fault diagnosis over recent years [3][4][5][6]. Given two sample sets, the classical SVM is aimed at constructing an optimal separating hyper-plane that maximizes the geometric margin between the hyper-plane and its closest samples from the two sample sets [2].…”

Section: Introductionmentioning

confidence: 99%

Maximum margin classification based on flexible convex hulls for fault diagnosis of roller bearings

Zeng

Zheng

et al. 2016

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

“…Fractal features have been widely used in texture analysis, signal analysis, object modeling and image classification, etc. [2][3][4][5]. The multifractal spectrum reveals deep structure features of images and improves the performance of traditional image processing methods.…”

Section: Introductionmentioning

confidence: 99%

Edge Detection of the Siberian Tiger Skull CT Image by Multifractal Spectrum Theory

Qi²,

Mu³

2016

Advanced Science and Technology Letters

View full text Add to dashboard Cite

Based on multifractal spectrum theory, the set of singular edge points plus the set of smoothing edge points is the set of image edge points. With   1   f corresponding to smoothing edge point andstanding for the set of image edge points. Experimental results showed that the method based on multifractal spectrum theory was effective and accurate to detect edges of Siberian tiger skull computed tomography images. A new method by applying multifractal spectrum theory in medical computed tomography images edge detection was provided in this paper. This method is a more local method compared with other conventional edge detection method.

show abstract

Wavelet leaders multifractal features based fault diagnosis of rotating mechanism

Cited by 124 publications

References 42 publications

Fine‐Grained Fault Diagnosis Method of Rolling Bearing Combining Multisynchrosqueezing Transform and Sparse Feature Coding Based on Dictionary Learning

Fine‐Grained Fault Diagnosis Method of Rolling Bearing Combining Multisynchrosqueezing Transform and Sparse Feature Coding Based on Dictionary Learning

Maximum margin classification based on flexible convex hulls for fault diagnosis of roller bearings

Edge Detection of the Siberian Tiger Skull CT Image by Multifractal Spectrum Theory

Contact Info

Product

Resources

About