Multisource Fault Signal Separation of Rotating Machinery Based on Wavelet Packet and Fast Independent Component Analysis

The vibration signal of rotating machinery compound faults acquired in actual fields has the characteristics of complex noise sources, the strong background noise, and the nonlinearity, causing the traditional blind source separation algorithm not be suitable for the blind separation of rotating machinery coupling fault. According to these problems, an extraction method of multisource fault signals based on wavelet packet analysis (WPA) and fast independent component analysis (FastICA) was proposed. Firstly, according to the characteristic of the vibration signal of rotating machinery, an effective denoising method of wavelet packet based on average threshold is presented and described to reduce the vibration signal noise. In the method, the thresholds of every node of the best wavelet packet basis are acquired and averaged, and then the average value is used as a global threshold to quantize the decomposition coefficient of every node. Secondly, the mixed signals were separated by using the improved FastICA algorithm. Finally, the results of simulations and real rotating machinery vibration signals analysis show that the method can extract the rotating machinery fault characteristics, verifying the effectiveness of the proposed algorithm.

[1]  Hamed Azami,et al.  Application of dispersion entropy to status characterization of rotary machines , 2019, Journal of Sound and Vibration.

[2]  Zhi Zhang,et al.  Sign normalised spline adaptive filtering algorithms against impulsive noise , 2018, Signal Process..

[3]  Seral Ozsen,et al.  A new denoising method for fMRI based on weighted three-dimensional wavelet transform , 2018 .

[4]  Yang Ge and Xiaomei Jiang.  Mathematical Morphology and Deep Learning-based Approach for Bearing Fault Recognition , 2018 .

[5]  Feng Miao,et al.  Research on the Fault Feature Extraction Method of Rotor Systems Based on GAW-PSO , 2020 .

[6]  D. Farina,et al.  Multi-channel intramuscular and surface EMG decomposition by convolutive blind source separation , 2016, Journal of neural engineering.

[7]  Christian Jutten,et al.  A second-order statistics method for blind source separation in post-nonlinear mixtures , 2019, Signal Process..

[8]  Min Xia,et al.  Fault Diagnosis for Rotating Machinery Using Multiple Sensors and Convolutional Neural Networks , 2018, IEEE/ASME Transactions on Mechatronics.

[9]  Peng Ding,et al.  Statistical Alignment-Based Metagated Recurrent Unit for Cross-Domain Machinery Degradation Trend Prognostics Using Limited Data , 2021, IEEE Transactions on Instrumentation and Measurement.

[10]  Hongchao Wang,et al.  The application of matching pursuit based on multi feature pattern set in the signal processing of rotating machinery , 2019, Journal of Vibration and Control.

[11]  Yao Cheng,et al.  Adaptive Multipoint Optimal Minimum Entropy Deconvolution Adjusted and Application to Fault Diagnosis of Rolling Element Bearings , 2019, IEEE Sensors Journal.

[12]  Wu Deng,et al.  Feature Extraction for Data-Driven Remaining Useful Life Prediction of Rolling Bearings , 2021, IEEE Transactions on Instrumentation and Measurement.

[13]  Li Xia,et al.  Image Denoising Based on the Dyadic Wavelet Transform and Improved Threshold , 2009, Int. J. Wavelets Multiresolution Inf. Process..

[14]  S. S. Shen,et al.  Applications of Hilbert–Huang transform to non‐stationary financial time series analysis , 2003 .

[15]  Feng Miao,et al.  A New Fault Feature Extraction Method for Rotating Machinery Based on Multiple Sensors , 2020, Sensors.

[16]  Feng Miao,et al.  A New Method of Denoising of Vibration Signal and Its Application , 2020, Shock and Vibration.

[17]  Wasfy B. Mikhael,et al.  Face Recognition Employing DMWT Followed by FastICA , 2017, Circuits, Systems, and Signal Processing.

[18]  Ahsan Kareem,et al.  System identification through nonstationary data using Time–Frequency Blind Source Separation , 2016 .

[19]  Konstantinos Gryllias,et al.  Vibration-Based Condition Monitoring of Wind Turbine Gearboxes Based on Cyclostationary Analysis , 2018, Journal of Engineering for Gas Turbines and Power.

[20]  Lingjiang Kong,et al.  Mainlobe jamming suppression for distributed radar via joint blind source separation , 2019, IET Radar, Sonar & Navigation.

[21]  Fengshou Gu,et al.  A Novel Method for the Dynamic Coefficients Identification of Journal Bearings Using Kalman Filter , 2020, Sensors.

[22]  Haidong Shao,et al.  An enhancement deep feature fusion method for rotating machinery fault diagnosis , 2017, Knowl. Based Syst..

[23]  Fang Ye,et al.  A complex mixing matrix estimation algorithm in under-determined blind source separation problems , 2017, Signal Image Video Process..

[24]  Haiyang Huang,et al.  Variable learning rate EASI-based adaptive blind source separation in situation of nonstationary source and linear time-varying systems , 2019, Journal of Vibroengineering.

[25]  Qiu-Hua Lin,et al.  Double Coupled Canonical Polyadic Decomposition for Joint Blind Source Separation , 2016, IEEE Transactions on Signal Processing.

[26]  Mingyang Lv,et al.  A New Performance Degradation Evaluation Method Integrating PCA, PSR and KELM , 2021, IEEE Access.

[27]  Hui Wang,et al.  An Adaptive Randomized Orthogonal Matching Pursuit Algorithm With Sliding Window for Rolling Bearing Fault Diagnosis , 2018, IEEE Access.

[28]  Haidong Shao,et al.  A novel deep autoencoder feature learning method for rotating machinery fault diagnosis , 2017 .

[29]  Tingkai Gong,et al.  Application of optimized multiscale mathematical morphology for bearing fault diagnosis , 2017 .

[30]  Feng Miao,et al.  Fault Diagnosis of Rotating Machinery Based on Multi-Sensor Signals and Median Filter Second-Order Blind Identification (MF-SOBI) , 2020, Applied Sciences.

[31]  Feng Miao,et al.  A New Fault Diagnosis Method for Rotating Machinery Based on SCA-FastICA , 2020 .

[32]  Joon-Ho Lee,et al.  Numerically Efficient Implementation of JADE ML Algorithm , 2008 .

[33]  Abdellah Kacha,et al.  Complex Blind Source Separation , 2017, Circuits Syst. Signal Process..

[34]  Charles E. Tinney,et al.  Modal parameter estimation of a reduced-scale rocket nozzle using blind source separation , 2019 .

[35]  M.-Ch. Pan,et al.  Adaptive angular-velocity Vold–Kalman filter order tracking – Theoretical basis, numerical implementation and parameter investigation , 2016 .

[36]  Rabah Abdelkader,et al.  Rolling Bearing Fault Diagnosis Based on an Improved Denoising Method Using the Complete Ensemble Empirical Mode Decomposition and the Optimized Thresholding Operation , 2018, IEEE Sensors Journal.

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

[38]  Bin Pang,et al.  Weak fault diagnosis of rolling bearings based on singular spectrum decomposition, optimal Lucy─Richardson deconvolution and speed transform , 2020 .

[39]  Tirza Routtenberg,et al.  Power Systems Topology and State Estimation by Graph Blind Source Separation , 2018, IEEE Transactions on Signal Processing.

[40]  Muhammad Saeed Aslam,et al.  A novel application of kernel adaptive filtering algorithms for attenuation of noise interferences , 2019, Neural Computing and Applications.

[41]  Marcus Eger,et al.  Convolutive blind source separation of surface EMG measurements of the respiratory muscles , 2017, Biomedizinische Technik. Biomedical engineering.

[42]  Yongquan Zhou,et al.  An improved quantum-inspired cooperative co-evolution algorithm with muli-strategy and its application , 2021, Expert Syst. Appl..

[43]  Jérôme Antoni,et al.  Reconstruction of cyclostationary sound source based on a back-propagating cyclic wiener filter , 2019, Journal of Sound and Vibration.

[44]  Andrew Kusiak,et al.  Cyclostationary Analysis of a Faulty Bearing in the Wind Turbine , 2017, Journal of Solar Energy Engineering.

[45]  Dongying Han,et al.  Fault Diagnosis of Rotating Machinery Based on Adaptive Stochastic Resonance and AMD-EEMD , 2016 .

[46]  Wady Naanaa,et al.  A new multi-scale framework for convolutive blind source separation , 2016, Signal, Image and Video Processing.