A Novel Signal Separation Method Based on Improved Sparse Non-Negative Matrix Factorization

In order to separate and extract compound fault features of a vibration signal from a single channel, a novel signal separation method is proposed based on improved sparse non-negative matrix factorization (SNMF). In view of the traditional SNMF failure to perform well in the underdetermined blind source separation, a constraint reference vector is introduced in the SNMF algorithm, which can be generated by the pulse method. The square wave sequences are constructed as the constraint reference vector. The output separated signal is constrained by the vector, and the vector will update according to the feedback of the separated signal. The redundancy of the mixture signal will be reduced during the constantly updating of the vector. The time–frequency distribution is firstly applied to capture the local fault features of the vibration signal. Then the high dimension feature matrix of time–frequency distribution is factorized to select local fault features with the improved SNMF method. Meanwhile, the compound fault features can be separated and extracted automatically by using the sparse property of the improved SNMF method. Finally, envelope analysis is used to identify the feature of the output separated signal and realize compound faults diagnosis. The simulation and test results show that the proposed method can effectively solve the separation of compound faults for rotating machinery, which can reduce the dimension and improve the efficiency of algorithm. It is also confirmed that the feature extraction and separation capability of proposed method is superior to the traditional SNMF algorithm.

[1]  Wenhua Du,et al.  A Novel Fault Diagnosis Method of Gearbox Based on Maximum Kurtosis Spectral Entropy Deconvolution , 2019, IEEE Access.

[2]  Hong Jiang,et al.  A novel Switching Unscented Kalman Filter method for remaining useful life prediction of rolling bearing , 2019, Measurement.

[3]  Nick C Fox,et al.  Gene-Wide Analysis Detects Two New Susceptibility Genes for Alzheimer's Disease , 2014, PLoS ONE.

[4]  Fuming Sun,et al.  Graph regularized and sparse nonnegative matrix factorization with hard constraints for data representation , 2016, Neurocomputing.

[5]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[6]  Lingli Cui,et al.  Fault Severity Classification and Size Estimation for Ball Bearings Based on Vibration Mechanism , 2019, IEEE Access.

[7]  Xuelong Li,et al.  Graph Regularized Non-Negative Low-Rank Matrix Factorization for Image Clustering , 2017, IEEE Transactions on Cybernetics.

[8]  Lingli Cui,et al.  A Novel Weighted Sparse Representation Classification Strategy Based on Dictionary Learning for Rotating Machinery , 2020, IEEE Transactions on Instrumentation and Measurement.

[9]  Jing Wang,et al.  Improved Complexity Based on Time-Frequency Analysis in Bearing Quantitative Diagnosis , 2013 .

[10]  Jianfeng Ma,et al.  Quantitative trend fault diagnosis of a rolling bearing based on Sparsogram and Lempel-Ziv , 2018, Measurement.

[11]  Wenju Liu,et al.  Deep Learning Based Speech Separation via NMF-Style Reconstructions , 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[12]  Lingli Cui,et al.  A three-dimensional geometric features-based SCA algorithm for compound faults diagnosis , 2019, Measurement.

[13]  Bin Zhang,et al.  Bearing performance degradation assessment using long short-term memory recurrent network , 2019, Comput. Ind..

[14]  Fulei Chu,et al.  HVSRMS localization formula and localization law: Localization diagnosis of a ball bearing outer ring fault , 2019, Mechanical Systems and Signal Processing.

[15]  Nicolás Ruiz-Reyes,et al.  A non-negative matrix factorization approach based on spectro-temporal clustering to extract heart sounds , 2017 .

[16]  Yu Zhang,et al.  Application of pattern recognition in gear faults based on the matching pursuit of a characteristic waveform , 2017 .

[17]  Guanghua Xu,et al.  Feature extraction and recognition for rolling element bearing fault utilizing short-time Fourier transform and non-negative matrix factorization , 2015 .

[18]  Christos G. Tsinos,et al.  Distributed Blind Hyperspectral Unmixing via Joint Sparsity and Low-Rank Constrained Non-Negative Matrix Factorization , 2017, IEEE Transactions on Computational Imaging.

[19]  Wenhua Du,et al.  Research and application of improved adaptive MOMEDA fault diagnosis method , 2019, Measurement.

[20]  Peng Chen,et al.  Step-by-Step Fuzzy Diagnosis Method for Equipment Based on Symptom Extraction and Trivalent Logic Fuzzy Diagnosis Theory , 2018, IEEE Transactions on Fuzzy Systems.

[21]  Huaqing Wang,et al.  A Novel Feature Enhancement Method Based on Improved Constraint Model of Online Dictionary Learning , 2019, IEEE Access.

[22]  Haiyang Pan,et al.  Symplectic geometry mode decomposition and its application to rotating machinery compound fault diagnosis , 2019, Mechanical Systems and Signal Processing.

[23]  Xuelong Li,et al.  Structurally Incoherent Low-Rank Nonnegative Matrix Factorization for Image Classification , 2018, IEEE Transactions on Image Processing.

[24]  Yong Chen,et al.  Soft orthogonal non-negative matrix factorization with sparse representation: Static and dynamic , 2018, Neurocomputing.

[25]  Gangbing Song,et al.  Multivariate empirical mode decomposition and its application to fault diagnosis of rolling bearing , 2016 .

[26]  Ruyi Huang,et al.  Deep Decoupling Convolutional Neural Network for Intelligent Compound Fault Diagnosis , 2019, IEEE Access.

[27]  Xin Wang,et al.  Improved Fault Size Estimation Method for Rolling Element Bearings Based on Concatenation Dictionary , 2019, IEEE Access.

[28]  Zhixiong Li,et al.  Multifault Detection, Diagnosis, and Prognosis for Rotating Machinery , 2018 .

[29]  Huaqing Wang,et al.  Underdetermined Source Separation of Bearing Faults Based on Optimized Intrinsic Characteristic-Scale Decomposition and Local Non-Negative Matrix Factorization , 2019, IEEE Access.

[30]  Tu Bao Ho,et al.  Fast Parallel Randomized Algorithm for Nonnegative Matrix Factorization with KL Divergence for Large Sparse Datasets , 2016, ArXiv.

[31]  Babak Nasersharif,et al.  Non-negative matrix factorization for speech/music separation using source dependent decomposition rank, temporal continuity term and filtering , 2017, Biomed. Signal Process. Control..

[32]  Ivica Kopriva,et al.  A Nonlinear Orthogonal Non-Negative Matrix Factorization Approach to Subspace Clustering , 2017, Pattern Recognit..

[33]  Ying Nian Wu,et al.  Decoding the encoding of functional brain networks: An fMRI classification comparison of non-negative matrix factorization (NMF), independent component analysis (ICA), and sparse coding algorithms , 2016, Journal of Neuroscience Methods.

[34]  Peng Chen,et al.  Vibration-Based Intelligent Fault Diagnosis for Roller Bearings in Low-Speed Rotating Machinery , 2018, IEEE Transactions on Instrumentation and Measurement.

[35]  Shi Li,et al.  A novel convolutional neural network based fault recognition method via image fusion of multi-vibration-signals , 2019, Comput. Ind..

[36]  Balbir S. Dhillon,et al.  Early fault diagnosis of rotating machinery based on wavelet packets—Empirical mode decomposition feature extraction and neural network , 2012 .

[37]  Xiping Jiang,et al.  Mixed pixel decomposition of mineral spectrum based on EMD-ICA method , 2015 .

[38]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[39]  Gang Tang,et al.  A Compound Fault Diagnosis for Rolling Bearings Method Based on Blind Source Separation and Ensemble Empirical Mode Decomposition , 2014, PloS one.

[40]  Haojie Li,et al.  Sparse dual graph-regularized NMF for image co-clustering , 2018, Neurocomputing.

[41]  Kun Zhang,et al.  Application of an enhanced fast kurtogram based on empirical wavelet transform for bearing fault diagnosis , 2019, Measurement Science and Technology.

[42]  Patrik O. Hoyer,et al.  Non-negative Matrix Factorization with Sparseness Constraints , 2004, J. Mach. Learn. Res..

[43]  Wei Liu,et al.  Discriminative separable nonnegative matrix factorization by structured sparse regularization , 2016, Signal Process..

[44]  Hugo Van hamme,et al.  Under-determined reverberant audio source separation using Bayesian Non-negative Matrix Factorization , 2016, Speech Commun..

[45]  Jing Wang,et al.  Basic pursuit of an adaptive impulse dictionary for bearing fault diagnosis , 2014, 2014 International Conference on Mechatronics and Control (ICMC).

[46]  Guolin He,et al.  Non-stationary vibration feature extraction method based on sparse decomposition and order tracking for gearbox fault diagnosis , 2018 .

[47]  An-bo Ming,et al.  Discriminative non-negative matrix factorization (DNMF) and its application to the fault diagnosis of diesel engine , 2017 .

[48]  Huaqing Wang,et al.  Underdetermined Blind Source Separation with Variational Mode Decomposition for Compound Roller Bearing Fault Signals , 2016, Sensors.

[49]  Xuelong Li,et al.  Manifold Regularized Sparse NMF for Hyperspectral Unmixing , 2013, IEEE Transactions on Geoscience and Remote Sensing.