Research on Rolling Element Bearing Fault Diagnosis Based on Singular Value Decomposition and Kurtosis Criterion

2013 ◽  
Vol 432 ◽  
pp. 304-309 ◽  
Author(s):  
Xiao Lin Wang ◽  
Yong Xiang Zhang ◽  
Jie Ping Zhu ◽  
Zhong Qi Shi
Keyword(s):  
Singular Value Decomposition ◽  
Vibration Signal ◽  
Singular Value ◽  
Rolling Element Bearing ◽  
Feature Extraction Method ◽  
Bearing Fault Diagnosis ◽  
Rolling Element ◽  
New Feature ◽  
Value Decomposition ◽  
Fault Information

In order to extract the faint fault information from complicated vibration signal of bearing, a new feature extraction method based on singular value decomposition (SVD) and kurtosis criterion is proposed in my work. According to the method, a group of component signals are obtained firstly using SVD, then component signals with equal kurtosis are selected to be summed together, and the weak fault signal is clearly extracted. The effectiveness of the method is demonstrated on both simulated signal and actual data.

Rolling element bearing fault diagnostics: Development of health index

2016 ◽  
Vol 231 (21) ◽  
pp. 3923-3939 ◽  
Author(s):  
HS Kumar ◽  
Srinivasa P Pai ◽  
NS Sriram ◽  
GS Vijay
Keyword(s):  
Singular Value Decomposition ◽  
Singular Value ◽  
Rolling Element Bearing ◽  
Variable Load ◽  
Fisher Discriminant Analysis ◽  
Average Value ◽  
Health Indices ◽  
Rolling Element ◽  
Element Bearing ◽  
Value Decomposition

This article develops and compares health indices using different approaches namely singular value decomposition, average value of the cumulative feature and Mahalanobis distance for assessing the rolling element bearing condition. The vibration signals for four conditions of rolling element bearing are acquired from a customized bearing test rig under variable load conditions. Seventeen statistical features are extracted from wavelet coefficients of the denoised signals. Feature selection is performed using singular value decomposition and kernel Fisher discriminant analysis. These selected features are used in these three approaches to develop health indices. Finally, a comparison of the three proposed approaches is made to select the best approach which can be effectively used for fault diagnosis of rolling element bearings.

Roller Bearing Fault Diagnosis Based on ELMD and Fuzzy C-Means Clustering Algorithm

2014 ◽  
Vol 602-605 ◽  
pp. 1698-1700 ◽  
Author(s):  
Chang Liang Liu ◽  
Xiu Mei Huang ◽  
Xian Jin Luo
Keyword(s):  
Fault Diagnosis ◽  
Singular Value Decomposition ◽  
Feature Vector ◽  
Vibration Signal ◽  
Singular Value ◽  
Fuzzy C Means ◽  
Bearing Fault Diagnosis ◽  
Fuzzy C Means Clustering ◽  
Value Decomposition ◽  
Vector Matrix

For the non-stationary characteristics of rotating machinery fault vibration signal, proposed a fault diagnosis method that based on ensemble local mean decomposition (ELMD) to extract fault feature, and fuzzy C-means clustering (FCM) to perform the fault identification. ELMD method can effectively solve the problem of aliasing modes in LMD. Firstly, decomposing the fault vibration signal by ELMD, PF components were obtained in which the initial feature vector matrix, The PF components compose a initial feature vector matrix, and do singular value decomposition, using the singular value decomposition feature vector as the fault characteristic vectors. Finally, using FCM clustering as a fault classifier. Achieved the identification of different fault types. Experimental results show that this method can effectively achieve the bearing fault diagnosis.

scholarly journals Hybridization of time synchronous averaging, singular value decomposition, and adaptive neuro fuzzy inference system for multi-fault bearing diagnosis

2020 ◽  
Vol 12 (12) ◽  
pp. 168781402098056
Author(s):  
Walid Touzout ◽  
Djamel Benazzouz ◽  
Fawzi Gougam ◽  
Adel Afia ◽  
Chemseddine Rahmoune
Keyword(s):  
Singular Value Decomposition ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Vibration Signal ◽  
Relevant Information ◽  
Singular Value ◽  
Inference System ◽  
Operation Conditions ◽  
Neuro Fuzzy ◽  
Value Decomposition

Bearing diagnosis has attracted considerable research interest; thus, researchers have developed several signal processing techniques using vibration analysis to monitor the rotating machinery’s conditions. In practical engineering, features extraction with most relevant information from experimental vibration signals under variable operation conditions is still regarded as the most critical concern. Therefore, actual works focus on combining Time Domain Features (TDFs) with decomposition techniques to obtain accurate results for defect detection, identification, and classification. In this paper, a new hybrid method is proposed, which is based on Time Synchronous Averaging (TSA), TDFs, and Singular Value Decomposition (SVD) for the feature extraction, then the Adaptive Neuro-Fuzzy Inference System (ANFIS) which gathers the advantages of both neural networks and fuzzy logic is applied for the classification process. First, TSA is used to reduce noises in the vibration signal by extracting the periodic waveforms from the disturbed data; thereafter, TDFs are applied on each synchronous signal to construct a feature matrix; afterwards, SVD is performed on the obtained matrices to remove the instability of statistical values and select the most stable vectors. Finally, ANFIS is implemented to provide a powerful automatic tool for features classification.

scholarly journals Research on Rolling Bearing Fault Feature Extraction Based on Singular Value Decomposition considering the Singular Component Accumulative Effect and Teager Energy Operator

2019 ◽  
Vol 2019 ◽  
pp. 1-14
Author(s):  
Longlong Li ◽  
Yahui Cui ◽  
Runlin Chen ◽  
Lingping Chen ◽  
Lihua Wang
Keyword(s):  
Fault Diagnosis ◽  
Singular Value Decomposition ◽  
Energy Operator ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Singular Value ◽  
Teager Energy Operator ◽  
Singular Component ◽  
Value Decomposition ◽  
Teager Energy

The extraction of impulsive signatures from a vibration signal is vital for fault diagnosis of rolling element bearings, which are always whelmed by noise, especially in the early stage of defect development. Aiming at the weak defect diagnosis, kurtosis of Teager energy operator (KTEO) spectrum is employed to indicate the fault information capacity of a spectrum, and considering the accumulative effect of a singular component, accumulative kurtosis of TEO (AKTEO) is firstly proposed to determine the proper signal reconstructed order during vibration signal processing using singular value decomposition (SVD). Then, a vibration processing scheme named SVD-AKTEO is designed where an iteration is employed to reflect an accumulative singular effect by kurtosis of TEO spectrum. Finally, the fault diagnosis results can be extracted from the TEO spectrum output by SVD-AKTEO. Simulation data and real data from a run-to-failure experiment of a rolling bearing are adopted to validate the efficiency, and comparative analysis demonstrates the feasibility to detect the early defect of the rolling bearing.

scholarly journals Rolling Bearing Incipient Fault Detection Based on a Multi-Resolution Singular Value Decomposition

2019 ◽  
Vol 9 (20) ◽  
pp. 4465 ◽  
Author(s):  
Jiesi Luo ◽  
Shaohui Zhang
Keyword(s):  
Fault Detection ◽  
Singular Value Decomposition ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Singular Value ◽  
Incipient Fault ◽  
Periodic Impulse ◽  
Value Decomposition ◽  
Impulse Characteristics ◽  
Incipient Fault Detection

The periodic impulse characteristics caused by rolling bearing damage are weak in the incipient failure stage. Thus, these characteristics are always drowned out by background noise and other harmonic interference. A novel approach based on multi-resolution singular value decomposition (MRSVD) is proposed in order to extract the periodic impulse characteristics for incipient fault detection. With the MRSVD method, the vibration signal is first decomposed to obtain a group of approximate signals and detailed signals with different resolutions. The first detail signal is mainly composed of noise and the last approximate signal is mainly composed of harmonic interference. Combined with the kurtosis index, the hidden periodic impulse signal will be extracted from the detail signals (in addition to the first detail signal). Thus, the incipient fault detection of a rolling bearing can be fulfilled according to the envelope demodulation spectrum of the extracted periodic impulse signal. The effectiveness of the proposed method has been demonstrated with both simulation and experimental analyses.

Research on Fault Feature Extraction Method of the Wind Turbine Gearbox Based on SVD and Improved HHT

2012 ◽  
Vol 220-223 ◽  
pp. 785-788
Author(s):  
Chang Zheng Chen ◽  
Quan Gu ◽  
Bo Zhou
Keyword(s):  
Feature Extraction ◽  
Singular Value Decomposition ◽  
Wind Turbine ◽  
Extraction Method ◽  
Random Noise ◽  
Singular Value ◽  
Wind Turbine Gearbox ◽  
Feature Extraction Method ◽  
Value Decomposition ◽  
Fault Feature Extraction

This paper researches fault feature extraction method based on singular value decomposition and the improved HHT method for non-stationary characteristics of wind turbine gearbox vibration signal. Firstly, through the signal phase space reconstruction, the singular value decomposition as a pre-filter, to preprocessing the signal, effectively weaken the random noise. Then using EEMD to improve the HHT method, decompose the denoising signal into a series of different time scales component of intrinsic mode functions. The fault characteristics of the signal are extracted by the Hilbert transform. Finally, simulating gearbox fault experiment to verify the effectively of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document