Laplace Prior-Based Bayesian Compressive Sensing Using K-SVD for Vibration Signal Transmission and Fault Detection

Ma, Yunfei; Jia, Xisheng; Hu, Qiwei; Xu, Dongmei; Guo, Chiming; Wang, Qiang; Wang, Shuangchuan

doi:10.3390/electronics8050517

Cited by 8 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CNN model is originally a two-dimensional (2D) neural network with a 2D matrix as input. With the deepening of the research, it has been found that CNN also has a strong feature extraction ability for onedimensional timing signals and has achieved good results in the vibration signal processing (Ma et al, 2020), fault diagnosis (Khan et al, 2018), natural language recognition (NLP; Zhao et al, 2018;Zhang et al, 2017) and other fields.…”

Section: Principles Of the Convolutional Neural Networkmentioning

confidence: 99%

Modelling and predictive investigation on the vibration response of a propeller shaft based on a convolutional neural network

2022

View full text Add to dashboard Cite

Abstract. It is crucial to detect the working state of a propeller shaft in real time, as its vibration affects the safety of the marine propulsion system directly. With the difficulty of obtaining an accurate signal due to the particularity of propeller shaft, a suitable method for estimating the vibration response of propeller shaft is proposed in this paper. The nonlinear relationship of vibration signals between the bearing and propeller shaft is obtained by fitting the existing data sets with various neural networks. The feasibility of the proposed method is demonstrated through a prediction of shaft vibration on the basis of a shaft experimental platform. Moreover, the optimal model of the neural network is obtained by comparing the influence of different hyper parameters and network models. The results indicate a prediction accuracy of over 95 % of the shaft vibration in the lower frequency band for a convolutional neural network. Therefore, the research provides an easier maintenance method for predicting the real-time monitoring for the vibration response of the propeller shaft.

show abstract

Section: Principles Of the Convolutional Neural Networkmentioning

confidence: 99%

Modelling and predictive investigation on the vibration response of a propeller shaft based on a convolutional neural network

2022

View full text Add to dashboard Cite

show abstract

“…Generally, an accurate reconstruction algorithm means more running time. Referring [29], the Lap-CBCS-KSVD algorithm can be seen as one of the most accurate algorithms. However, it costs much more time than traditional basic pursuit (BP), orthogonal matching pursuit (OMP) algorithms.…”

Section: Dbn For Cs Compressed Signalmentioning

confidence: 99%

A new fault diagnosis method using deep belief network and compressive sensing

Ma¹,

Jia²,

Bai³

et al. 2020

J. vibroeng.

Self Cite

View full text Add to dashboard Cite

Compressive sensing provides a new idea for machinery monitoring, which greatly reduces the burden on data transmission. After that, the compressed signal will be used for fault diagnosis by feature extraction and fault classification. However, traditional fault diagnosis heavily depends on the prior knowledge and requires a signal reconstruction which will cost great time consumption. For this problem, a deep belief network (DBN) is used here for fault detection directly on compressed signal. This is the first time DBN is combined with the compressive sensing. The PCA analysis shows that DBN has successfully separated different features. The DBN method which is tested on compressed gearbox signal, achieves 92.5 % accuracy for 25 % compressed signal. We compare the DBN on both compressed and reconstructed signal, and find that the DBN using compressed signal not only achieves better accuracies, but also costs less time when compression ratio is less than 0.35. Moreover, the results have been compared with other classification methods.

show abstract

“…Yuan and Chen proposed a fault diagnosis method for rolling bearings based on compression sensing, even under fluctuating working conditions [31]. Ma et al proposed a Bayesian compressed sensing method based on Laplacian priors and utilized K-singular value decomposition (K-SVD) for transmitting vibration signals and detecting faults [32]. Based on the compressed sensing method, efficient reconstruction of low-resolution fault signals of bearings is achieved.…”

Section: Introductionmentioning

confidence: 99%

Adaptive spectrum amplitude modulation method for rolling bearing fault frequency determination

Tu,

Luo,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Signal preprocessing and feature extraction are decisive factors in determining the frequency of bearing faults. The presence of noise interference in the status signal of rolling bearings often hampers accurate fault detection. Although there are various methods for preprocessing vibration signals in rolling bearings, they need further improvement in terms of enhancing fault feature expression and localizing fault frequency bands. This limitation significantly hinders the accuracy of fault frequency determination. In order to enhance the representation of fault information on the frequency spectrum, this study proposes a combined approach that incorporates sparse stacked autoencoder (SSAE), wavelet packet decomposition (WPD), and adaptive spectrum amplitude modulation (ASAM). The resulting method is referred to as SSAE-WPD-ASAM. Firstly, the bearing vibration signal is decomposed by wavelet packet according to the scale and frequency band of the signal. On this basis, the signal reconstruction is realized based on the wavelet packet coefficient and energy distribution in different frequency bands. Secondly, for the whole life cycle signal, the reconstructed signal is self-encoded by sparse stacked autoencoder to achieve dimensionality reduction of the reconstructed signal. Then, the spare reconstructed signal is subjected to adaptive spectrum amplitude modulation (ASAM). Finally, through envelope demodulation, peak detection of fault frequency and empirical fault frequency comparison, the specific fault types of rolling bearings are determined. The proposed method is verified by theoretical simulation and three groups of practical experiments. The results show that the proposed method has a significant improvement in diagnostic efficiency and accuracy compared with traditional diagnostic methods.

show abstract

Laplace Prior-Based Bayesian Compressive Sensing Using K-SVD for Vibration Signal Transmission and Fault Detection

Cited by 8 publications

References 23 publications

Modelling and predictive investigation on the vibration response of a propeller shaft based on a convolutional neural network

Modelling and predictive investigation on the vibration response of a propeller shaft based on a convolutional neural network

A new fault diagnosis method using deep belief network and compressive sensing

Adaptive spectrum amplitude modulation method for rolling bearing fault frequency determination

Contact Info

Product

Resources

About