Sigmoid-based refined composite multiscale fuzzy entropy and t-SNE based fault diagnosis approach for rolling bearing

Zheng, Jianhua; Jiang, Zhanwei; Pan, Haiyang

doi:10.1016/j.measurement.2018.07.045

Cited by 97 publications

(30 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the bigger τ will increase computation time of two multiscale entropies (i.e., MPSE and MPGSE). Consequently, according to the recommendation of [51], the maximum scale factor τ max is usually chosen as 20, which can achieve an accurate evaluation of complexity of the signal and is sufficient to handle the actual data.…”

Section: Parameter Selection Of Mpse and Mpgsementioning

confidence: 99%

Fault Diagnosis of Rolling-Element Bearing Using Multiscale Pattern Gradient Spectrum Entropy Coupled with Laplacian Score

et al. 2020

View full text Add to dashboard Cite

Feature extraction is recognized as a critical stage in bearing fault diagnosis. Pattern spectrum (PS) and pattern spectrum entropy (PSE) in recent years have been smoothly applied in feature extraction, whereas they easily ignore the partial impulse signatures hidden in bearing vibration data. In this paper, the pattern gradient spectrum (PGS) and pattern gradient spectrum entropy (PGSE) are firstly presented to improve the performance of fault feature extraction of two approaches (PS and PSE). Nonetheless, PSE and PGSE are only able to evaluate dynamic behavior of the time series on a single scale, which implies there is no consideration of feature information at other scales. To address this problem, a novel approach entitled multiscale pattern gradient spectrum entropy (MPGSE) is further implemented to extract fault features across multiple scales, where its key parameters are determined adaptively by grey wolf optimization (GWO). Meanwhile, a Laplacian score-(LS-) based feature selection strategy is employed to choose the sensitive features and establish a new feature set. Finally, the selected new feature set is imported into extreme learning machine (ELM) to identify different health conditions of rolling bearing. Performance of our designed algorithm is tested on two experimental cases. Results confirm the availability of our proposed algorithm in feature extraction and show that our method can recognize effectively different bearing fault categories and severities. More importantly, the designed approach can achieve higher recognition accuracies and provide better stability by comparing with other entropy-based methods involved in this paper.

show abstract

Section: Parameter Selection Of Mpse and Mpgsementioning

confidence: 99%

Fault Diagnosis of Rolling-Element Bearing Using Multiscale Pattern Gradient Spectrum Entropy Coupled with Laplacian Score

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The cluster graphs achieved by the t-distributed stochastic neighbor embedding (t-SNE) method are shown in Figure 14. 40 With the increase in the noise level, the points in the clustering graph are more scattered, but they can still roughly distinguish the fault types and maintain high classification accuracy. It can be concluded that the proposed TL-CNN has clear cluster…”

Section: Fault Diagnosis Based On Deep Tlmentioning

confidence: 99%

Deep transfer learning for rolling bearing fault diagnosis under variable operating conditions

Che

Wang

et al. 2019

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Rolling bearings are the vital components of rotary machines. The collected data of rolling bearing have strong noise interference, massive unlabeled samples, and different fault features. Thus, a deep transfer learning method is proposed for rolling bearings fault diagnosis under variable operating conditions. To obtain robust feature representation, the denoising autoencoder is used to denoise and reduce dimension of unlabeled rolling bearing signals. For those unlabeled target domain signals, a feature matching method based on multi-kernel maximum mean discrepancies between source domain and target domain is adopted to get enough labeled target domain samples. Then, these rolling bearing signals are converted to multi-dimensional graph samples and fed into a convolutional neural network model for fault diagnosis. To improve the generalization of convolutional neural network under variable operating conditions, we combine modelbased transfer learning with feature-based transfer learning to initialize and optimize the convolutional neural network parameters. The effectiveness of the proposed method is validated through several comparative experiments of Case Western Reserve University data. The results demonstrate that the proposed method can learn features adaptively from noisy data and increase the accuracy rate by 2%-8% comparing with other models.

show abstract

“…Zhu et al [109] cross-fuzzy entropy 8 Zair et al [110] fuzzy entropy of empirical mode decomposition + principal component analysis + self-organizing map neural network 9 Deng et al [111] integrating empirical wavelet transform + fuzzy entropy 10 Zhu et al [112] adaptive local iterative filtering + modified fuzzy entropy + support vector machine 11 Liu et al [113] composite interpolation-based multiscale fuzzy entropy+ Laplacian support vector machine 12 Zheng et al [114] sigmoid-based refined composite multiscale fuzzy entropy 13 Zhu et al [115] multiscale fuzzy entropy + Laplacian support vector machine…”

Section: Application Of Fuzzy Entropy On Bearingmentioning

confidence: 99%

“…Liu et al [113] improve the multiscale fuzzy entropy and combine it with the Laplacian support vector machine, which can achieve higher recognition rates and better robustness than multiscale fuzzy entropy algorithm. To improve the performance of multiscale fuzzy entropy for complexity measure of short data series, Zheng et al [114] propose the Sigmoid-based refined composite multiscale fuzzy entropy. For the same problem, Zhu et al [115] apply the time shift multiscale fuzzy entropy to the complexity analysis of data series.…”

Section: Application Of Fuzzy Entropy On Bearingmentioning

confidence: 99%

Related Entropy Theories Application in Condition Monitoring of Rotating Machineries

Liu

Zhi

Zhang

et al. 2019

Entropy

View full text Add to dashboard Cite

Rotating machinery plays an important role in various kinds of industrial engineering. How to assess their conditions is a key problem for operating safety and condition-based maintenance. The potential anomaly, fault and failure information can be obtained by analyzing the collected condition monitoring data of the previously deployed sensors in rotating machinery. Among the available methods of analyzing sensors data, entropy and its variants can provide quantitative information contained in these sensing data. For implementing fault detection, diagnosis, and prognostics, this information can be utilized for feature extraction and selecting appropriate training data for machine learning methods. This article aims to review the related entropy theories which have been applied for condition monitoring of rotating machinery. This review consists of typical entropy theories presentation, application, summary, and discussion.

show abstract

Sigmoid-based refined composite multiscale fuzzy entropy and t-SNE based fault diagnosis approach for rolling bearing

Cited by 97 publications

References 16 publications

Fault Diagnosis of Rolling-Element Bearing Using Multiscale Pattern Gradient Spectrum Entropy Coupled with Laplacian Score

Fault Diagnosis of Rolling-Element Bearing Using Multiscale Pattern Gradient Spectrum Entropy Coupled with Laplacian Score

Deep transfer learning for rolling bearing fault diagnosis under variable operating conditions

Related Entropy Theories Application in Condition Monitoring of Rotating Machineries

Contact Info

Product

Resources

About