scholarly journals A Sparse Modulation Signal Bispectrum Analysis Method for Rolling Element Bearing Diagnosis

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Guangbin Wang ◽  
Fengshou Gu ◽  
Ibraham Rehab ◽  
Andrew Ball ◽  
Long Li
Keyword(s):  
Carrier Frequency ◽  
Zero Point ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Rolling Element Bearing ◽  
Energy Concentration ◽  
Analysis Method ◽  
Damage Degree ◽  
Coordinate Origin ◽  
Modulation Signal

Modulation signal bispectrum (MSB) analysis is an effective method to obtain the fault frequency for rolling bearing, but harmonics make fault frequency dense and even frequency aliasing. Carrier frequency of bearing is generally determined by its structure and inherent characteristics and changes with the increase of the damage degree, so it is hard to be accurately found. To solve these problems, this paper proposes a sparse modulation signal bispectrum analysis method. Firstly the vibration signal is demodulated by MSB analysis and its bispectrum is obtained. After the frequency domain filtering, the carrier frequency is computed based on the characteristics of energy concentration at the carrier frequency on MSB. By shift-frequency MSB (SF-MSB), the carrier frequency is moved to the coordinate origin, the entire MSB is shifted for the same distance, and SF-MSB is obtained. At last, the bispectrum is shifted to the frequency zero point and diagonal slices are performed to obtain a sparse representation of MSB. Experimental results show that sparse MSB (S-MSB) method can not only eliminate the interference of harmonic frequency, but also make the extracted characteristic frequency of fault more obvious.

Rolling Bearing Localized Defect Evaluation by Multiscale Signature via Empirical Mode Decomposition

2012 ◽  
Vol 134 (6) ◽  
Author(s):  
Qingbo He ◽  
Peng Li ◽  
Fanrang Kong
Keyword(s):  
Health Information ◽  
Empirical Mode Decomposition ◽  
Multiple Scales ◽  
Regression Line ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Rolling Element Bearing ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
Rolling Element

Measured vibration signals from rolling element bearings with defects are generally nonstationary, and are multiscale in nature owing to contributions from events with different localization in time and frequency. This paper presents a novel approach to characterize the multiscale signature via empirical mode decomposition (EMD) for rolling bearing localized defect evaluation. Vibration signal measured from a rolling element bearing is first adaptively decomposed by the EMD to achieve a series of usable intrinsic mode functions (IMFs) carrying the bearing health information at multiple scales. Then the localized defect-induced IMF is selected from all the IMFs based on a variance regression approach. The multiscale signature, called multiscale slope feature, is finally estimated from the regression line fitted over logarithmic variances of the IMFs excluding the defect IMF. The presented feature reveals the pattern of energy transfer among multiple scales due to localized defects, representing an inherent self-similar signature of the bearing health information that is embedded on multiple analyzed scales. Experimental results verify the performance of the proposed multiscale feature, and further discussions are provided.

Fault Feature Extraction for Rolling Bearing Based on Dual Impulse Morlet Wavelet

2015 ◽  
Author(s):  
Yi Feng ◽  
Bao-chun Lu ◽  
Deng-feng Zhang ◽  
Wei Zhang
Keyword(s):  
Ant Colony Algorithm ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Morlet Wavelet ◽  
Feature Model ◽  
Energy Concentration ◽  
Similar Degree ◽  
Bearing Fault ◽  
Experiment Verification ◽  
Fault Feature Extraction

The common impulse feature model is oscillating and attenuated signal with a single maximum peak, while the formation principle of actual impulse feature is ignored. Considering the continuous dual impulse waveform feature of rolling bearing fault in the vibration signal and the matching effects of the single impulse waveform with Morlet wavelet, a “dual impulse Morlet wavelet” model is proposed. Through ant colony algorithm with the indicator of the maximum cross-correlation, 4 types of parameters are optimized adaptively which affect the similar degree between dual impulse Morlet wavelet and the dual impulse waveform intercepted from the bearing vibration signal. Then, the optimal model is obtained. The bearing fault experiment verification shows that the optimal dual impulse Morlet wavelet can effectively improve the analytical precision and energy concentration of impulse feature in both of time domain and frequency domain, which overcomes the disadvantages of Morlet wavelet effectively.

scholarly journals Multitask Convolutional Neural Network for Rolling Element Bearing Fault Identification

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Mingxing Jia ◽  
Yuemei Xu ◽  
Maoyi Hong ◽  
Xiyu Hu
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Rolling Bearing ◽  
Rolling Element Bearing ◽  
One Dimensional ◽  
Generalization Ability ◽  
Bearing Fault ◽  
Damage Degree

As one of the most vital parts of rotating equipment, it is an essential work to diagnose rolling bearing failure. The traditional signal processing-based rolling bearing fault diagnosis algorithms rely on artificial feature extraction and expert knowledge. The working condition of rolling bearings is complex and changeable, so the traditional algorithm is slightly lacking adaptability. The damage degree also plays a crucial role in fault monitoring. Different damage degrees may take different remedial measures, but traditional fault-diagnosis algorithms roughly divide the damage degree into several categories, which do not correspond to the continuous value of the damage degree. To solve the abovementioned two problems, this paper proposes a fault-diagnosis algorithm based on “end-to-end” one-dimensional convolutional neural network. The one-dimensional convolution kernel and the pooling layer are directly applied to the original time domain signal. Feature extraction and classifier are merged together, and the extracted features are used to judge the damage degree at the same time. Then, the generalization ability of the model is studied under a variety of conditions. Experiments show that the algorithm can achieve more than 99% accuracy and can accurately give the damage degree of the bearing. It has good performance under different speeds, different types of motors, and different sampling frequencies, and so it has good generalization ability.

Simulation Research on Rolling Element Bearing Feature Extraction Based on Recursive Least-Squares Lattice-Ladder Algorithms

2014 ◽  
Vol 548-549 ◽  
pp. 481-486
Author(s):  
Jie Ping Zhu ◽  
Yong Xiang Zhang ◽  
Shuai Zhang ◽  
Xiao Lin Wang
Keyword(s):  
Feature Extraction ◽  
Least Squares ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Rolling Element Bearing ◽  
Recursive Least Squares ◽  
Filter Method ◽  
Feature Extraction Method ◽  
Rolling Element ◽  
Element Bearing

In order to extract the weak fault information from complicated vibration signal of rolling element bearing, the Recursive Least-Squares (RLS) Lattice-Ladder Algorithms is introduced into the field of rolling bearing feature extraction. An adaptive feature extraction method is proposed. The RLS Lattice-Ladder algorithms and its adaptive filter property in the process of feature extraction were discussed. The rolling bearing vibration signal was refined by the RLS Lattice-Ladder filter method, and the refined vibration signal was demodulated by square envelope, then the rolling bearing’s characteristic fault frequency was identified by enveloped normalized amplitude-frequency spectrum. Simulation results show that compared with the LMS filter method, this method can identify fault frequency more quickly and more effectively.

scholarly journals Optimal SES Selection Based on SVD and Its Application to Incipient Bearing Fault Diagnosis

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Longlong Li ◽  
Yahui Cui ◽  
Runlin Chen ◽  
Xiaolin Liu
Keyword(s):  
Fault Diagnosis ◽  
Vibration Signal ◽  
Degradation Process ◽  
Rolling Bearing ◽  
Industrial Applications ◽  
Rotating Machinery ◽  
Accelerated Life Test ◽  
Rolling Element Bearing ◽  
Main Task ◽  
Detection Techniques

Rotating machinery has extensive industrial applications, and rolling element bearing (REB) is one of the core parts. To distinguish the incipient fault of bearing before it steps into serious failure is the main task of condition monitoring and fault diagnosis technology which could guarantee the reliability and security of rotating machinery. The early defect occurring in the REB is too weak and manifests itself in heavy surrounding noise, thus leading to the inefficiency of the fault detection techniques. Aiming at the vibration signal purification and promoting the potential of defects detection, a new method is proposed in this paper based on the combination of singular value decomposition (SVD) technique and squared envelope spectrum (SES). The kurtosis of SES (KSES) is employed to select the optimal singular component (SC) obtained by applying SVD to vibration signal, which provides the information of the REB for fault diagnosis. Moreover, the rolling bearing accelerated life test with the bearing running from normal state to failure is adopted to evaluate the performance of the SVD-KSES, and results demonstrate the proposed approach can detect the incipient faults from vibration signal in the natural degradation process.

Research on Rolling Element Bearing Fault Diagnosis Based on EEMD and Correlated Kurtosis

2014 ◽  
Vol 680 ◽  
pp. 198-205 ◽  
Author(s):  
Xiao Lin Wang ◽  
Wei Hua Han ◽  
Han Gu ◽  
Cun Hu ◽  
Xing Xing Han
Keyword(s):  
Fault Diagnosis ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Ensemble Empirical Mode Decomposition ◽  
Rolling Element Bearing ◽  
Intrinsic Mode Functions ◽  
Feature Extraction Method ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Mode Decomposition

In order to extract the faint fault information from complicated vibration signal of bearing, the correlated kurtosis is introduced into the field of rolling bearing fault diagnosis. Combined with ensemble empirical mode decomposition (EEMD) and correlated kurtosis, a feature extraction method is proposed. According to the method, by EEMD processing a group of intrinsic mode functions (IMFs) are obtained, then the IMF with maximal correlated kurtosis is selected, and the weak fault signal is clearly extracted. The effectiveness of the method is demonstrated on both simulated signal and actual data.

scholarly journals Research of Fault Diagnosis Based on Sensitive Intrinsic Mode Function Selection of EEMD and Adaptive Stochastic Resonance

2016 ◽  
Vol 2016 ◽  
pp. 1-12 ◽  
Author(s):  
Zhixing Li ◽  
Boqiang Shi
Keyword(s):  
Fault Diagnosis ◽  
Stochastic Resonance ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Difference Spectrum ◽  
Ensemble Empirical Mode Decomposition ◽  
Rolling Element Bearing ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
Selection Of

A novel methodology for the fault diagnosis of rolling bearing in strong background noise, based on sensitive intrinsic mode functions (IMFs) selection of ensemble empirical mode decomposition (EEMD) and adaptive stochastic resonance, is proposed. The original vibration signal is decomposed into a group of IMFs and a residual trend item by EEMD. Constructing weighted kurtosis index difference spectrum (WKIDS) to adaptively select sensitive IMFs, this method can overcome the shortcomings of the existing methods such as subjective choice or need to determine a threshold using the correlation coefficient. To further reduce noise and enhance weak characteristics, the adaptive stochastic resonance is employed to amplify each sensitive IMF. Then, the ensemble average is used to eliminate the stochastic noise. The simulation and rolling element bearing experiment with an inner fault are performed to validate the proposed method. The results show that the proposed method not only overcomes the difficulty of choosing sensitive IMFs, but also, combined with adaptive stochastic resonance, can better enhance the weak fault characteristics. Moreover, the proposed method is better than EEMD and adaptive stochastic resonance of each sensitive IMF, demonstrating the feasibility of the proposed method in highly noisy environments.

Rolling bearing degradation condition clustering using multidimensional degradation feature and Gath–Geva fuzzy clustering algorithm

2020 ◽  
pp. 107754632095495
Author(s):  
Bing Wang ◽  
Xiong Hu ◽  
Tao X Mei ◽  
Sun D Jian ◽  
Wang Wei
Keyword(s):  
Fuzzy Clustering ◽  
Clustering Algorithm ◽  
Chaotic Map ◽  
Vibration Signal ◽  
Degradation Process ◽  
Rolling Bearing ◽  
Performance Degradation ◽  
Time Parameter ◽  
Mechanical Equipment ◽  
Time Dimension

In allusion to the issue of rolling bearing degradation feature extraction and degradation condition clustering, a logistic chaotic map is introduced to analyze the advantages of C0 complexity and a technique based on a multidimensional degradation feature and Gath–Geva fuzzy clustering algorithmic is proposed. The multidimensional degradation feature includes C0 complexity, root mean square, and curved time parameter which is more in line with the performance degradation process. Gath–Geva fuzzy clustering is introduced to divide different conditions during the degradation process. A rolling bearing lifetime vibration signal from intelligent maintenance system bearing test center was introduced for instance analysis. The results show that C0 complexity is able to describe the degradation process and has advantages in sensitivity and calculation speed. The introduced degradation indicator curved time parameter can reflect the agglomeration character of the degradation condition at time dimension, which is more in line with the performance degradation pattern of mechanical equipment. The Gath–Geva fuzzy clustering algorithmic is able to cluster degradation condition of mechanical equipment such as bearings accurately.

Sign in / Sign up

Export Citation Format

Share Document