Rolling Element Bearing Performance Degradation Assessment Using Variational Mode Decomposition and Gath-Geva Clustering Time Series Segmentation

Li, Yaolong; Li, Hongru; Wang, Bing; Gu, Hui‐Wen

doi:10.1155/2017/2598169

Cited by 6 publications

(2 citation statements)

References 26 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The time–frequency domain features are extracted based on the different signal processing methods. In recent years, the signal processing methods for degradation features have developed rapidly, e.g., Wavelet Transform (WT) [5], Empirical Mode Decomposition (EMD) [6], Ensemble Empirical Mode Decomposition (EEMD) [7], Local Mean Decomposition (LMD) [8], Variational Mode Decomposition (VMD) [9], Empirical Wavelet Transform (EWT) [10], etc.…”

Section: Introductionmentioning

confidence: 99%

A Novel Health Indicator Based on Cointegration for Rolling Bearings’ Run-To-Failure Process

2019

Sensors

Self Cite

View full text Add to dashboard Cite

The extraction of rolling bearings’ degradation features has been developed for decades. However, the degradation features always present different trends of different run-to-failure data. To find a consistent indicator of different data will be helpful to establish a general model and explore the nature of bearings’ degradation. In this study, we have found there is a trend of similarity between the energy and complexity features. By using the cointegration test, we found the two kinds of features exhibit a certain degree of cointegration relationship. Fused by the cointegration method, we have obtained a novel health indicator which can depict different run-to-failure data in a unified way. The difference between the energy features and complexity features can be explained by the novel health indicator. The indicator has “two-stage” characters. The first stage is the zero-line stage and the second stage is the quickly raise stage, which presents like an exponential function. It is easy to think about using an exponential degradation model to model this indicator. Next, we have compared the indicator to root mean square (RMS) by using the exponential degradation model. It shows that the indicator is more suitable for the exponential degradation model. In this paper, we used eleven run-to-failure data to verify the generality and “two-stage” characters of the proposed indicator. The result shows that the novel indicator is general and effective and that it will promote the development of bearings’ prognostics.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Health Indicator Based on Cointegration for Rolling Bearings’ Run-To-Failure Process

2019

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Fuzzy entropy and GG clustering are used in bearing diagnosis, 26 and the clustering effect is better than FCM and GK algorithms. A degradation condition evaluation method based on variational mode decomposition (VMD) and GG clustering is proposed, 27 and time series is segmented by GG clustering. A fault feature extraction method based on EEMD and singular value decomposition (SVD) is proposed, and GG fuzzy clustering method is employed in fault types clustering.…”

Section: Introductionmentioning

confidence: 99%

Bearing condition degradation assessment based on basic scale entropy and Gath-Geva fuzzy clustering

Wang

Xiong

Sun

et al. 2018

Advances in Mechanical Engineering

Self Cite

View full text Add to dashboard Cite

A method based on basic scale entropy and Gath-Geva fuzzy clustering is proposed in order to solve the issue of bearing degradation condition recognition. The evolution rule of basic scale entropy for bearing in performance degradation process is analyzed first, and the monotonicity and sensitivity of basic scale entropy are emphasized. Considering the continuity of the bearing degradation condition at the time scale, three-dimensional degradation eigenvectors are constructed including basic scale entropy, root mean square, and degradation time, and then, Gath-Geva fuzzy clustering method is used to divide different conditions in performance degradation process, thus realizing performance degradation recognition for bearing. Bearing whole lifetime data from IEEE PHM 2012 is adopted in application and discussion, and fuzzy c-means clustering and Gustafson-Kessel clustering algorithms are analyzed for comparison. The results show that the proposed basic scale entropy-Gath-Geva method has better clustering effect and higher time aggregation than the other two algorithms and is able to provide an effective way for mechanical equipment performance degradation recognition.

show abstract

A Wide Learning Approach for Interpretable Feature Recommendation for 1-D Sensor Data in IoT Analytics

Banerjee

Chattopadhyay

Garain

2019

Int. J. Autom. Comput.

View full text Add to dashboard Cite

Rolling Element Bearing Performance Degradation Assessment Using Variational Mode Decomposition and Gath-Geva Clustering Time Series Segmentation

Cited by 6 publications

References 26 publications

A Novel Health Indicator Based on Cointegration for Rolling Bearings’ Run-To-Failure Process

A Novel Health Indicator Based on Cointegration for Rolling Bearings’ Run-To-Failure Process

Bearing condition degradation assessment based on basic scale entropy and Gath-Geva fuzzy clustering

A Wide Learning Approach for Interpretable Feature Recommendation for 1-D Sensor Data in IoT Analytics

Contact Info

Product

Resources

About