Rolling Bearing Fault Diagnosis Based on an Improved Denoising Method Using the Complete Ensemble Empirical Mode Decomposition and the Optimized Thresholding Operation

Abdelkader, Rabah; Kaddour, Abdelhafid; Bendiabdellah, Azeddine; Derouiche, Z.

doi:10.1109/jsen.2018.2853136

Cited by 78 publications

(28 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, EMD also exists some limitations, such as end effect and mode mixing. To address these limitations, based on the theory of EMD, an improved version called EEMD with the assistance of added gaussian white noise is proposed, but the results decomposed by EEMD may be influenced by the added noise: (1) the residual noise still exists in the reconstructed signal in application, which can easily inundate the fault-related information [13]; (2) different realizations of signal assisted with noise may produce different number of modes, making it difficult to calculate the means of these modes [13]. Different from the mentioned methods, VMD is a novel adaptive signal decomposition method by constructing and solving a constrained variational problem to achieve signal decomposition, thus avoiding the mode mixing in EMD, the noise effect in EEMD and the basis function selection in WT.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis for Rolling Bearings Based on Composite Multiscale Fine-Sorted Dispersion Entropy and SVM With Hybrid Mutation SCA-HHO Algorithm Optimization

Shao

Tan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The health condition of rolling bearing possesses a significant impact on the safety and efficiency of rotating machinery. Accordingly, to diagnose the faults in rolling bearings effectively and accurately, a novel hybrid approach coupling variational mode decomposition (VMD), composite multiscale fine-sorted dispersion entropy (CMFSDE) and support vector machine (SVM) optimized by mutation sine cosine algorithm and Harris hawks optimization (MSCAHHO) is proposed in the paper. Firstly, VMD is employed to decompose raw vibration signals with various fault types into different sets of intrinsic mode functions (IMFs) to weaken the non-stationarity of signals, before which the parameter K of VMD is decided through central frequency observation method. Subsequently, CMFSDE is put forward in this paper to analyze the complexity of fault signals by fully considering the relationship between neighboring elements based on composite multiscale technique, with which the representative features of different fault samples are extracted to construct feature vectors. Later, an enhanced hybrid optimization approach called MSCAHHO is proposed by integrating sine cosine algorithm (SCA) and a periodic mutation strategy to improve Harris hawks optimization (HHO). Then, MSCAHHO is employed to optimize the parameters of SVM, after which the optimal SVM model is utilized for fault classification. Finally, the performance of the proposed methodology is evaluated with four validity indices through comparative experiments. The experimental results reveal that the proposed VMD-CMFSDE-MSCAHHO-SVM method achieves favorable diagnosis results comparing with other relevant methods. INDEX TERMS Fault diagnosis, variational mode decomposition, composite multiscale fine-sorted dispersion entropy, support vector machine, hybrid mutation SCA-HHO.

show abstract

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis for Rolling Bearings Based on Composite Multiscale Fine-Sorted Dispersion Entropy and SVM With Hybrid Mutation SCA-HHO Algorithm Optimization

Shao

Tan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Rolling bearings are the core components of mechanical equipment and are susceptible to damage. According to statistics, 30% of mechanical equipment malfunction are caused by bearing failures [1]. Failure of rolling bearings can lead to mechanical system collapse, which can cause huge economic losses and endanger the safety of personnel in serious cases.…”

Section: Introductionmentioning

confidence: 99%

Deep Convolutional and LSTM Recurrent Neural Networks for Rolling Bearing Fault Diagnosis Under Strong Noises and Variable Loads

et al. 2020

View full text Add to dashboard Cite

To research the problems of the rolling bearing fault diagnosis under different noises and loads, a dual-input model based on a convolutional neural network (CNN) and long-short term memory (LSTM) neural network is proposed. The model uses both time domain and frequency domain features to achieve endto-end fault diagnosis. One-dimensional convolutional and pooling layers are utilized to extract the spatial features and retain the sequence features of the data. In addition, an LSTM layer is employed to extract the sequence features. Finally, a dense layer is applied for fault classification. To enhance recognition accuracy under different noises and loads, three techniques are applied to the proposed model, including taking timefrequency domain signals as input, using the CNN-LSTM model, and adopting the mini-batch and batch normalization methods. The Case Western Reserve University and Drivetrain Diagnostics Simulator data sets are used to construct experiments under different conditions, including varying loads and different noises. The proposed model can achieve a high fault recognition rate under variable load and noise conditions as well as satisfactory anti-noise and load adaptability.

show abstract

“…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

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

Rolling Bearing Fault Diagnosis Based on an Improved Denoising Method Using the Complete Ensemble Empirical Mode Decomposition and the Optimized Thresholding Operation

Cited by 78 publications

References 13 publications

Fault Diagnosis for Rolling Bearings Based on Composite Multiscale Fine-Sorted Dispersion Entropy and SVM With Hybrid Mutation SCA-HHO Algorithm Optimization

Fault Diagnosis for Rolling Bearings Based on Composite Multiscale Fine-Sorted Dispersion Entropy and SVM With Hybrid Mutation SCA-HHO Algorithm Optimization

Deep Convolutional and LSTM Recurrent Neural Networks for Rolling Bearing Fault Diagnosis Under Strong Noises and Variable Loads

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

Contact Info

Product

Resources

About