scholarly journals Improved Tensor-Based Singular Spectrum Analysis Based on Single Channel Blind Source Separation Algorithm and Its Application to Fault Diagnosis

2017 ◽  
Vol 7 (4) ◽  
pp. 418 ◽  
Author(s):  
Dan Yang ◽  
Cancan Yi ◽  
Zengbin Xu ◽  
Yi Zhang ◽  
Mao Ge ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Blind Source Separation ◽  
Spectrum Analysis ◽  
Single Channel ◽  
Source Separation ◽  
Singular Spectrum Analysis ◽  
Separation Algorithm ◽  
Singular Spectrum

Hyperbolic median filtering and singular spectrum analysis for simultaneous source separation

2019 ◽  
Author(s):  
Aleksei Tarasov ◽  
Andrei Shuvalov ◽  
Andrey Konkov ◽  
Vladimir Ignatev ◽  
Ivan Polikarpov ◽  
...  
Keyword(s):  
Spectrum Analysis ◽  
Source Separation ◽  
Singular Spectrum Analysis ◽  
Median Filtering ◽  
Singular Spectrum ◽  
Simultaneous Source

Roller element bearing fault diagnosis using singular spectrum analysis

2013 ◽  
Vol 35 (1-2) ◽  
pp. 150-166 ◽  
Author(s):  
Bubathi Muruganatham ◽  
M.A. Sanjith ◽  
B. Krishnakumar ◽  
S.A.V. Satya Murty
Keyword(s):  
Fault Diagnosis ◽  
Spectrum Analysis ◽  
Singular Spectrum Analysis ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Singular Spectrum ◽  
Element Bearing

scholarly journals Fault diagnosis of rolling bearings using singular spectrum analysis and artificial neural networks

2021 ◽  
Vol 43 (2) ◽  
pp. 183-196
Author(s):  
Quang Thinh Tran ◽  
Kieu Nhi Ngo ◽  
Sy Dzung Nguyen
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Fault Diagnosis ◽  
Spectrum Analysis ◽  
Singular Spectrum Analysis ◽  
Frequency Noise ◽  
Singular Spectrum ◽  
Experimental Apparatus ◽  
Artificial Neural ◽  
Set Up

Singular spectrum analysis (SSA) has been employed effectively for analyzing in the time-frequency domain of time series. It can collaborate with data-driven models (DDMs) such as Artificial Neural Networks (ANN) to set up a powerful tool for mechanical fault diagnosis (MFD). However, to take advantage of SSA more effectively for MFD, quantifying the optimal component threshold in SSA should be addressed. Also, to exploit the managed mechanical system adaptively, the variation tendency of its physical parameters needs to be caught online. Here, we present a bearing fault diagnosis method (BFDM) based on ANN and SSA that targets these aspects. First, a multi-feature is built from pure mechanical properties distilled from the vibration signal of the system. Relied on SSA, the measured acceleration signal is analyzed to cancel the high-frequency noise. The remaining components take part in building a multi-feature to establish a database for training the ANN. Optimizing the number of the kept components is then carried out to obtain a dataset called Tr_Da. Based on Tr_Da, we receive the optimal ANN (OANN). In the next period, at each checking time, another database called Test_Da is set up online following the same way of building the Tr_Da. The compared result between the encoded output and the output of the OANN corresponding to the input to be Test_Da provides the bearing(s) health information. An experimental apparatus is built to evaluate the BFDM. The obtained results reflect the positive effects of the method.

A New Method for Adaptive Blind Source Separation Based on the Estimated Number of Dynamic Fault Sources

2012 ◽  
Vol 233 ◽  
pp. 211-217 ◽  
Author(s):  
Xiao Yan Yang ◽  
Xiong Zhou ◽  
Yi Ke Tang
Keyword(s):  
Fault Diagnosis ◽  
Blind Source Separation ◽  
Source Separation ◽  
Estimation Algorithm ◽  
Accurate Estimation ◽  
Separation Algorithm ◽  
Underdetermined Blind Source Separation ◽  
Source Signal ◽  
Fault Source ◽  
Source Number

In fault diagnosis of large rotating machinery, the number of fault sources may be subject to dynamic changes, which often lead to the failure in accurate estimation of the number of sources and the effective isolation of the fault source. This paper introduced the expansion of the fourth-order cumulant matrices in estimating the dynamic fault source number, plus the relationship between the source signal number and the number of sensors being utilized in the selection of the blind source separation algorithm to achieve adaptive blind source separation. Experiments showed that the source number estimation algorithm could be quite effective in estimating the dynamic number of fault sources, even in the underdetermined condition. This adaptive blind source separation algorithm could then effectively achieve fault diagnosis in respect to the positive-determined, overdetermined and underdetermined blind source separation.

Sign in / Sign up

Export Citation Format

Share Document