Weak Fault Feature Identification for Rolling Bearing Based on EMD and Spectral Kurtosis Method

Jing, Shuangxi; Yuan, Jinle; Li, Xinhua; Leng, Jinsong

doi:10.1109/iciscae.2018.8666841

Cited by 8 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sun et al [3] conducted the correlation analysis on the modal components of signals through EMD decomposition, selected the modal components with the larger correlation coefficient with the original signal, and reconstructed the signal to extract the fault features of rolling bearing. Jing et al [4] used mutual information, kurtosis, and cross-correlation to remove false IMF components in EMD and extracted the fault features of rolling bearings through an optimal bandpass filter with spectral kurtosis. However, EMD has some problems, such as mode mixing, the required large calculation load, and the incomplete theoretical basis [5].…”

Section: Introductionmentioning

confidence: 99%

Improved EEMD and overlapping group sparse second-order total variation

Zhang,

Gao,

Zhang

et al. 2024

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

Strong background noise increases the difficulty in extracting the early fault features of rolling bearing and leads to the signal waveform distortion problem of the total variation denoising method (TVD). Therefore, this paper presents an ensemble analysis method of fault features that combines improved ensemble empirical mode decomposition (MEEMD) with overlapping group sparse second-order total variation (OGSSTV). Based on typical vibration signals with background noise, the effects of mode mixing, reconstruction error, and noise reduction on MEEMD and OGSSTV methods were analyzed and the suitable parameters for fault feature extraction of vibration signals were determined. On this basis, the proposed method was used to extract motor bearing fault features. Simulation results and experimental data showed that the proposed method could suppress mode mixing, reduce the reconstruction error, and solve the waveform distortion problem caused by TVD in the process of signal noise reduction.

show abstract

Section: Introductionmentioning

confidence: 99%

Improved EEMD and overlapping group sparse second-order total variation

Zhang,

Gao,

Zhang

et al. 2024

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…There [9][10][11] exist several novel methods for signal processing, among which the most popular is the modal decomposition algorithm. Considering that the parameters of such algorithms affect the signal decomposition effect under manual intervention, this study employed the wavelet analysis algorithm with powerful functions and deep industry experience.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Deep Belief Network Based on Sparrow Search Algorithm for Rolling Bearing Fault Diagnosis

Xu,

2024

IEEE Access

View full text Add to dashboard Cite

This study addresses the randomness of training parameters in the Deep Belief Network (DBN) and proposes an optimization method for rolling bearing fault diagnosis based on the Sparrow Search Algorithm (SSA). SSA is employed to globally optimize the structural and training parameters of the DBN network, effectively resolving the challenge of parameter determination. Simultaneously, vibration signals are extracted from multiple dimensions to capture different types of fault features. These features are derived through Wavelet Transformation (WT) for noise reduction and Intrinsic Mode Functions (IMFs) extraction through Ensemble Empirical Mode Decomposition (EEMD). The fusion of time-domain and frequency-domain dimensional features forms a multidimensional feature set. This comprehensive feature set optimizes the parameters of the deep learning network and significantly improves the accuracy and effectiveness of rolling bearing fault diagnosis. With a remarkable recognition accuracy of 99.17%, this approach outperforms conventional feature sets and mainstream diagnostic methods such as PSO-DBN and SSA-SVM while maintaining high levels of generalization and stability. The introduction of this method represents a significant breakthrough in the field of rolling bearing fault diagnosis. INDEX TERMS Deep belief network, fault diagnosis, multi-domain features, sparrow search algorithm

show abstract

“…After MCKD processing, Fast spectral kurtosis (FSK) analysis was used to further identify the resonant frequency. Jing et al [16] used EMD data preprocessing to obtain the reconstructed signal, and then designed a suitable filter to filter the reconstructed signal through FSK to eliminate interferences, and finally analyzed the envelope demodulation result for feature extraction. Inspired by the aforementioned literatures, the SK algorithm is used to obtain the high-order statistics of each spectral line kurtosis in the vibration signal, and takes them as the input of CNN to enhance the feature representation.…”

Section: Introductionmentioning

confidence: 99%

Convolutional neural network intelligent diagnosis method using small samples based on SK-CAM

Chen,

Li,

et al. 2024

J. vibroeng.

View full text Add to dashboard Cite

In order to solve the dependence of convolutional neural networks (CNN) on large samples of training data, an intelligent fault diagnosis method based on spectral kurtosis (SK) and attention mechanism is proposed. Firstly, the SK algorithm is used to obtain two-dimensional fast kurtosis graphs from vibration signals, and the two-dimensional fast spectral kurtosis graphs are converted into one-dimensional kurtosis time-domain samples, which are used as the input of CNN. Then the channel attention module (CAM) is added to CNN, and the weight is increased in the channel domain to eliminate the interference of invalid features. The accuracy of fault identification can reach 99.8 % by applying the proposed method on the fault diagnosis experiment of rolling bearings. Compared with the traditional deep learning (DL) method, the proposed method not only has higher accuracy, but also has lower dependence on the number of samples.

show abstract

Weak Fault Feature Identification for Rolling Bearing Based on EMD and Spectral Kurtosis Method

Cited by 8 publications

References 6 publications

Improved EEMD and overlapping group sparse second-order total variation

Improved EEMD and overlapping group sparse second-order total variation

Optimization of Deep Belief Network Based on Sparrow Search Algorithm for Rolling Bearing Fault Diagnosis

Convolutional neural network intelligent diagnosis method using small samples based on SK-CAM

Contact Info

Product

Resources

About