scholarly journals Fault Feature Extraction for Reciprocating Compressors Based on Underdetermined Blind Source Separation

Entropy ◽  
2021 ◽  
Vol 23 (9) ◽  
pp. 1217
Author(s):  
Jindong Wang ◽  
Xin Chen ◽  
Haiyang Zhao ◽  
Yanyang Li ◽  
Zujian Liu
Keyword(s):  
Blind Source Separation ◽  
Hierarchical Clustering ◽  
Source Separation ◽  
Least Square Method ◽  
Least Square ◽  
Underdetermined Blind Source Separation ◽  
Matrix Estimation ◽  
Initial Cluster ◽  
Mixing Matrix ◽  
Source Signals

In practical engineering applications, the vibration signals collected by sensors often contain outliers, resulting in the separation accuracy of source signals from the observed signals being seriously affected. The mixing matrix estimation is crucial to the underdetermined blind source separation (UBSS), determining the accuracy level of the source signals recovery. Therefore, a two-stage clustering method is proposed by combining hierarchical clustering and K-means to improve the reliability of the estimated mixing matrix in this paper. The proposed method is used to solve the two major problems in the K-means algorithm: the random selection of initial cluster centers and the sensitivity of the algorithm to outliers. Firstly, the observed signals are clustered by hierarchical clustering to get the cluster centers. Secondly, the cosine distance is used to eliminate the outliers deviating from cluster centers. Then, the initial cluster centers are obtained by calculating the mean value of each remaining cluster. Finally, the mixing matrix is estimated with the improved K-means, and the sources are recovered using the least square method. Simulation and the reciprocating compressor fault experiments demonstrate the effectiveness of the proposed method.

scholarly journals Under-Determined Blind Source Separation

2021 ◽  
Author(s):  
Mehrdad Kafaiezadtehrani
Keyword(s):  
Blind Source Separation ◽  
Clustering Algorithm ◽  
Matching Pursuit ◽  
Source Separation ◽  
Least Square ◽  
Separation Problem ◽  
Second Stage ◽  
Mixing Matrix ◽  
Matching Pursuit Algorithm ◽  
Source Signals

The Under-determined Blind Source Separation problem aims at estimating N source signals, with only a given set of M known mixtures, where M < N. The problem is solved by a two-stage approach. The rst stage is the estimation of the unknown mixing matrix. The contributions made unravel a more precise and accurate tool which directly relates to the initialization of the clustering algorithm. Di erent schemes such as segmentation, correlation and least square curve tting are used to take advantage of the sparsity of the sources. A signi cant addition involves applying linear transforms to produce a higher sparse domain. Further, the second stage is the sparse source recovery using a Matching Pursuit algorithm. The contributions involve a Matching Pursuit algorithm with di

scholarly journals A Novel Underdetermined Blind Source Separation Method and Its Application to Source Contribution Quantitative Estimation

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1413 ◽  
Author(s):  
Jiantao Lu ◽  
Wei Cheng ◽  
Yanyang Zi
Keyword(s):  
Blind Source Separation ◽  
Quantitative Estimation ◽  
Source Separation ◽  
Estimation Method ◽  
Least Square ◽  
Underdetermined Blind Source Separation ◽  
Source Contribution ◽  
Time Frequency ◽  
Source Contributions ◽  
Source Signals

To identify the major vibration and radiation noise, a source contribution quantitative estimation method is proposed based on underdetermined blind source separation. First, the single source points (SSPs) are identified by directly searching the identical normalized time-frequency vectors of mixed signals, which can improve the efficiency and accuracy in identifying SSPs. Then, the mixing matrix is obtained by hierarchical clustering, and source signals can also be recovered by the least square method. Second, the optimal combination coefficients between source signals and mixed signals can be calculated based on minimum redundant error energy. Therefore, mixed signals can be optimally linearly combined by source signals via the coefficients. Third, the energy elimination method is used to quantitatively estimate source contributions. Finally, the effectiveness of the proposed method is verified via numerical case studies and experiments with a cylindrical structure, and the results show that source signals can be effectively recovered, and source contributions can be quantitatively estimated by the proposed method.

scholarly journals Mixing Matrix Estimation in Blind Source Separation Based on Generalized Gaussian Mixture Modal

2012 ◽  
Vol 4 ◽  
pp. 217-221
Author(s):  
Yong Qiang Chen ◽  
Jun Liu
Keyword(s):  
Objective Function ◽  
Blind Source Separation ◽  
Source Separation ◽  
Gaussian Mixture ◽  
Estimation Accuracy ◽  
Accurate Estimation ◽  
Traditional Methods ◽  
Underdetermined Blind Source Separation ◽  
Matrix Estimation ◽  
Mixing Matrix

The accurate estimation of mixing matrix is critical for blind separation, for solving the problems of traditional methods such as bad robustness and low accuracy, a method based on statistical modal is proposed. The generalized Gaussian mixture modal is used to fit the distribution of single-source-points, a new objective function for clustering is obtained from the view of maximum likelihood estimation. Constrained particle swarm optimization is used to optimize the objective function, by which the mixing matrix is estimated. This method is applicable to determined and underdetermined blind source separation. The simulation shows that the proposed method has higher estimation accuracy and is more robust than traditional methods.

Sign in / Sign up

Export Citation Format

Share Document