A Fault Diagnosis Method for Rolling Bearings Based on Feature Fusion of Multifractal Detrended Fluctuation Analysis and Alpha Stable Distribution

Xiong, Qing; Zhang, Weihua; Lü, Tao; Mei, Guiming; Liang, Shulin

doi:10.1155/2016/1232893

Cited by 12 publications

(11 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PDF non-Gaussianity thus complements portraits of intermittency when multifractaltype methods falter [28]. Multiscale PDF analysis resolves these issues and makes an elegant companion to MF-DFA.…”

Section: Introductionmentioning

confidence: 99%

Postural constraints recruit shorter-timescale processes into the non-Gaussian cascade processes

Furmanek

Mangalam

Kelty-Stephen

et al. 2020

Preprint

View full text Add to dashboard Cite

Healthy human postural sway exhibits strong intermittency, reflecting a richly interactive foundation of postural control. From a linear perspective, intermittent fluctuations might be interpreted as engagement and disengagement of complementary control processes at distinct timescales or from a nonlinear perspective, as cascade-like interactions across many timescales at once. The diverse control processes entailed by cascade-like multiplicative dynamics suggest specific non-Gaussian distributional properties at different timescales. Multiscale probability density function (PDF) analysis showed that when standing quietly, stable sand-filled loading of the upper extremities would elicit non-Gaussianity profiles showing a negative-quadratic crossover between short and long timescales. Unstable water-filled loading of the upper extremities would elicit simpler monotonic decreases in non-Gaussianity, that is, a positive-quadratic cancellation of the negative-quadratic crossover. Multiple known indices of postural sway governed the appearance or disappearance of the crossover. Finally, both loading conditions elicited Lévy-like distributions over progressively larger timescales. These results provide evidence that postural instability recruits shorter-timescale processes into the non-Gaussian cascade processes, that indices of postural sway moderate this recruitment, and that postural control under unstable loading shows stronger statistical hallmarks of cascade structure.

show abstract

Section: Introductionmentioning

confidence: 99%

Postural constraints recruit shorter-timescale processes into the non-Gaussian cascade processes

Furmanek

Mangalam

Kelty-Stephen

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The bearing fault data from the Case Western Reserve University (CWRU) Bearing Data Center [ 37 ] is selected to verify the validity of the method in a constant rotating speed environment. The bearing test stand used in the experiment is shown in Figure 7 .…”

Section: Methodsmentioning

confidence: 99%

“…All the conditions have an accuracy greater than 91.03%. Compared with diagnosis accuracies listed in [ 37 ], PSPP-CNN has equivalent accuracy, lower proportion of training samples and more conditions. This shows that the method we proposed has good performance in a constant rotating speed data diagnosis.…”

Section: Methodsmentioning

confidence: 99%

An Intelligent Fault Diagnosis Method for Bearings with Variable Rotating Speed Based on Pythagorean Spatial Pyramid Pooling CNN

Guo

Yang

Gao

et al. 2018

Sensors

View full text Add to dashboard Cite

Deep learning methods have been introduced for fault diagnosis of rotating machinery. Most methods have good performance when processing bearing data at a certain rotating speed. However, most rotating machinery in industrial practice has variable working speed. When processing the bearing data with variable rotating speed, the existing methods have low accuracies, or need complex parameter adjustments. To solve this problem, a fault diagnosis method based on continuous wavelet transform scalogram (CWTS) and Pythagorean spatial pyramid pooling convolutional neural network (PSPP-CNN) is proposed in this paper. In this method, continuous wavelet transform is used to decompose vibration signals into CWTSs with different scale ranges according to the rotating speed. By adding a PSPP layer, CNN can process CWTSs in different sizes. Then the fault diagnosis of variable rotating speed bearing can be carried out by a single CNN model without complex parameter adjustment. Compared with a spatial pyramid pooling (SPP) layer that has been used in CNN, a PSPP layer locates as front layer of CNN. Thus, the features obtained by PSPP layer can be delivered to convolutional layers for further feature extraction. According to experiment results, this method has higher diagnosis accuracy for variable rotating speed bearing than other methods. In addition, the PSPP-CNN model trained by data at some rotating speeds can be used to diagnose bearing fault at full working speed.

show abstract

“…5–10 Due to the simplicity in implementation, the multifractal detrended fluctuation analysis (MFDFA) is now becoming one of the most extensively adopted methods in mechanical fault diagnosis. 11–14…”

Section: Introductionmentioning

confidence: 99%

“…[5][6][7][8][9][10] Due to the simplicity in implementation, the multifractal detrended fluctuation analysis (MFDFA) is now becoming one of the most extensively adopted methods in mechanical fault diagnosis. [11][12][13][14] A necessary step of the MFDFA is to remove the local trends at different time-scales. In the classic MFDFA, the linear, quadratic, cubic or higher order polynomials are usually utilized to fit the local trends.…”

Section: Introductionmentioning

confidence: 99%

Multifractal characterization of mechanical vibration signals through improved empirical mode decomposition-based detrended fluctuation analysis

Guo

Gong

et al. 2016

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

A novel multifractal detrended fluctuation analysis based on improved empirical mode decomposition for the non-linear and non-stationary vibration signal of machinery is proposed. As the intrinsic mode functions selection and Kolmogorov–Smirnov test are utilized in the detrending procedure, the present approach is quite available for contaminated data sets. The intrinsic mode functions selection is employed to deal with the undesired intrinsic mode functions named pseudocomponents, and the two-sample Kolmogorov–Smirnov test works on each intrinsic mode function and Gaussian noise to detect the noise-like intrinsic mode functions. The proposed method is adaptive to the signal and weakens the effect of noise, which makes this approach work well for vibration signals collected from poor working conditions. We assess the performance of the proposed procedure through the classic multiplicative cascading process. For the pure simulation signal, our results agree with the theoretical results, and for the contaminated time series, the proposed method outperforms the traditional multifractal detrended fluctuation analysis methods. In addition, we analyze the vibration signals of rolling bearing with different fault types, and the presence of multifractality is confirmed.

show abstract

A Fault Diagnosis Method for Rolling Bearings Based on Feature Fusion of Multifractal Detrended Fluctuation Analysis and Alpha Stable Distribution

Cited by 12 publications

References 29 publications

Postural constraints recruit shorter-timescale processes into the non-Gaussian cascade processes

Postural constraints recruit shorter-timescale processes into the non-Gaussian cascade processes

An Intelligent Fault Diagnosis Method for Bearings with Variable Rotating Speed Based on Pythagorean Spatial Pyramid Pooling CNN

Multifractal characterization of mechanical vibration signals through improved empirical mode decomposition-based detrended fluctuation analysis

Contact Info

Product

Resources

About