Health Degradation Monitoring and Early Fault Diagnosis of a Rolling Bearing Based on CEEMDAN and Improved MMSE

Lv, Yong; Yuan, Rui; Wang, Tao; Li, Hewenxuan; Song, Gangbing

doi:10.3390/ma11061009

Cited by 73 publications

(51 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where T and stand for the range statistics and the semiquadratic statistic, respectively, and both statistics are based on the t-statistics as shown in (35)- (36). These two statistics (T and ) are mainly to remove the model whose p-value is less than the significance level .…”

Section: Evaluation Criteriamentioning

confidence: 99%

See 1 more Smart Citation

A CEEMDAN and XGBOOST‐Based Approach to Forecast Crude Oil Prices

Zhou

Shi

et al. 2019

Complexity

View full text Add to dashboard Cite

Crude oil is one of the most important types of energy for the global economy, and hence it is very attractive to understand the movement of crude oil prices. However, the sequences of crude oil prices usually show some characteristics of nonstationarity and nonlinearity, making it very challenging for accurate forecasting crude oil prices. To cope with this issue, in this paper, we propose a novel approach that integrates complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and extreme gradient boosting (XGBOOST), so-called CEEMDAN-XGBOOST, for forecasting crude oil prices. Firstly, we use CEEMDAN to decompose the nonstationary and nonlinear sequences of crude oil prices into several intrinsic mode functions (IMFs) and one residue. Secondly, XGBOOST is used to predict each IMF and the residue individually. Finally, the corresponding prediction results of each IMF and the residue are aggregated as the final forecasting results. To demonstrate the performance of the proposed approach, we conduct extensive experiments on the West Texas Intermediate (WTI) crude oil prices. The experimental results show that the proposed CEEMDAN-XGBOOST outperforms some state-of-the-art models in terms of several evaluation metrics.

show abstract

Section: Evaluation Criteriamentioning

confidence: 99%

“…Later, the authors put forward an improved version of CEEMDAN to obtain decomposed components with less noise and more physical meaning [33]. The CEEMDAN has succeeded in wind speed forecasting [34], electricity load forecasting [35], and fault diagnosis [36][37][38]. Therefore, CEEMDAN may have the potential to forecast crude oil prices.…”

Section: Introductionmentioning

confidence: 99%

A CEEMDAN and XGBOOST‐Based Approach to Forecast Crude Oil Prices

Zhou

Shi

et al. 2019

Complexity

View full text Add to dashboard Cite

show abstract

“…To alleviate these phenomena, CEEMDAN [14] was introduced to decompose non-liner and non-stationary signals. Currently, this method is also widely applied in the fault diagnosis domain to obtain feature information on vibration signals [47,48]. The following is the basic principle of CEEMDAN:…”

Section: Ceemdan Algorithmmentioning

confidence: 99%

Self-Adaptive Fault Feature Extraction of Rolling Bearings Based on Enhancing Mode Characteristic of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise

Zhan

et al. 2019

Symmetry

View full text Add to dashboard Cite

Originally, a rolling bearing, as a key part in rotating machinery, is a cyclic symmetric structure. When a fault occurs, it disrupts the symmetry and influences the normal operation of the rolling bearing. To accurately identify faults of rolling bearing, a novel method is proposed, which is based enhancing the mode characteristics of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). It includes two parts: the first is the enhancing decomposition of CEEMDAN algorithm, and the second is the identified method of intrinsic information mode (IIM) of vibration signal. For the first part, the new mode functions (CIMFs) are obtained by combing the adjacent intrinsic mode functions (IMFs) and performing the corresponding Fast Fourier Transform (FFT) to strengthen difference feature among IMFs. Then, probability density function (PDF) is used to estimate FFT of each CIMF to obtain overall information of frequency component. Finally, the final intrinsic mode functions (FIMFs) are obtained by proposing identified method of adjacent PDF based on geometrical similarity (modified Hausdorff distance (MHD)). FIMFs indicate the minimum amount of mode information with physical meanings and avoid interference of spurious mode in original CEEMDAN decomposing. Subsequently, comprehensive evaluate index (Kurtosis and de-trended fluctuation analysis (DFA)) is proposed to identify IIM in FIMFs. Experiment results indicate that the proposed method demonstrates superior performance and can accurately extract characteristic frequencies of rolling bearing.

show abstract

“…Energy variation of the 3× component (where X represents the frequency corresponding to the rotating speed) extracted based on Wavelet Packet Transform [43][44][45] was used to quantify the crack depth of a crack with known crack location in a rotor by Gómez et al [46], and the analytical Jeffcott rotor model and the corresponding experimental rotor with a saw-cut crack were studied to validate the method. EMD method [47][48][49] was applied to steady-state responses generated from a Jeffcott rotor to extract the 3× and 2× components in the neighborhood of 1/3 and 1/2 of the critical rotating speed by Guo et al [50], results showed that the variation of averaged amplitudes of super-harmonic components provided clear and robust signatures of early cracks in rotating rotors. However, from the literature, few researches have been carried out to identify both the location and depth of a crack in a rotor with these super-harmonic features.…”

Section: Introductionmentioning

confidence: 99%

A Super-Harmonic Feature Based Updating Method for Crack Identification in Rotors Using a Kriging Surrogate Model

Ouyang

2019

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Dynamic model updating based on finite element method (FEM) has been widely investigated for structural damage identification, especially for static structures. Despite the substantial advances in this method, the key issue still needs to be addressed to boost its efficiency in practical applications. This paper introduces the updating idea into crack identification for rotating rotors, which has been rarely addressed in the literature. To address the problem, a novel Kriging surrogate model-based FEM updating method is proposed for the breathing crack identification of rotors by using the super-harmonic nonlinear characteristics. In this method, the breathing crack induced nonlinear characteristics from two locations of the rotors are harnessed instead of the traditional linear damage features for more sensitive and accurate breathing crack identification. Moreover, a FEM of a two-disc rotor-bearing system with a response-dependent breathing crack is established, which is partly validated by experiments. In addition, the associated breathing crack induced nonlinear characteristics are investigated and used to construct the objective function of Kriging surrogate model. Finally, the feasibility and the effectiveness of the proposed method are verified by numerical experiments with Gaussian white noise contamination. Results demonstrate that the proposed method is effective, accurate, and robust for breathing crack identification in rotors and is promising for practical engineering applications.

show abstract

Health Degradation Monitoring and Early Fault Diagnosis of a Rolling Bearing Based on CEEMDAN and Improved MMSE

Cited by 73 publications

References 51 publications

A CEEMDAN and XGBOOST‐Based Approach to Forecast Crude Oil Prices

A CEEMDAN and XGBOOST‐Based Approach to Forecast Crude Oil Prices

Self-Adaptive Fault Feature Extraction of Rolling Bearings Based on Enhancing Mode Characteristic of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise

A Super-Harmonic Feature Based Updating Method for Crack Identification in Rotors Using a Kriging Surrogate Model

Contact Info

Product

Resources

About