An Improved HHT Method and its Application in Fault Diagnosis of Roller Bearing

2013 ◽  
Vol 273 ◽  
pp. 264-268 ◽  
Author(s):  
Ling Li Jiang ◽  
Bo Bo Li ◽  
Xue Jun Li
Keyword(s):  
Fault Diagnosis ◽  
Wavelet Packet ◽  
Roller Bearing ◽  
Low Frequency ◽  
Analysis Method ◽  
Intrinsic Mode Functions ◽  
Hilbert Huang Transform ◽  
Time Frequency ◽  
Effective Time ◽  
Coefficient Method

Hilbert-Huang transform (HHT) is a very effective time-frequency analysis method, but it has some disadvantages. For example, the dense modal signal cannot be decomposed completely, and redundancy intrinsic mode functions (IMFs) are easy emerging at low frequency, which will cause the distortion of the processing results. In view of the above questions, this study applies the wavelet packet transform for denoising before HHT for improving the dense modal problem, and applies the correlation coefficient method to eliminate the redundancy IMF. The fault diagnostic case of roller bearing shows the effectiveness of the proposed method.

Time-Frequency Analysis for Power System Oscillations

2013 ◽  
Vol 336-338 ◽  
pp. 928-931
Author(s):  
Chia Liang Lu ◽  
Pei Hwa Huang
Keyword(s):  
Power Systems ◽  
Power System ◽  
Frequency Analysis ◽  
Low Frequency ◽  
Normal Operation ◽  
Intrinsic Mode Functions ◽  
Time Frequency Analysis ◽  
Hilbert Huang Transform ◽  
Time Frequency ◽  
Low Frequency Oscillations

Low frequency oscillations due to the lack of damping may occur in power systems under normal operation and will cause system instability. These oscillations are essentially nonlinear power responses which are difficult to extract the inherent characteristics by the time domain method. This paper aims to analyze nonlinear power responses by using the Hilbert-Huang transform (HHT) which is a time-frequency signal processing method which comprises steps of the empirical mode decomposition and the Hilbert transform. Dynamic power system responses, including generator output power and line power are to be processed by the HHT and a set of intrinsic mode functions and the associated Hilbert spectrum are obtained. The generator with most effects on the system will be accordingly found out through the time-frequency analysis and the power system stabilizer will be placed at the generator. Numerical results from a sample power system are demonstrated to show the validity of the time-frequency approach in the study of power system low frequency oscillations.

The Fault Diagnosis Method for Roller Bearing with Harmonic Wavelet Packet and DT-SVM

2015 ◽  
Vol 724 ◽  
pp. 238-241
Author(s):  
Rui Pan ◽  
Tao Xu ◽  
Yong Liu
Keyword(s):  
Fault Diagnosis ◽  
Wavelet Packet ◽  
Roller Bearing ◽  
Vibration Signal ◽  
Support Vector ◽  
Time Frequency ◽  
Vibration Data ◽  
Electric Engineering ◽  
Harmonic Wavelet ◽  
Diagnosis Method

This paper studies the roller bearing fault diagnosis method with harmonic wavelet packet and Decision Tree-Support Vector Machine (DT-SVM). The harmonic wavelet packet possesses better performances for its box-shaped spectrum and unlimited subdivision compared with the conventional time-frequency feature exaction method. Firstly, the proposed method decomposes the roller bearing vibration signal with harmonic wavelet packet and extracts the feature energy with coefficients of each spectrum. After the feature energy is normalized, feature vector are available. Based on multi-level binary tree, this paper designs the multi-classification SVM model due to its superior nonlinear mapping capability. Three two-classifications are incorporated to diagnosis the roller bearing faults. Finally, the proposed method is illustrated with the vibration data from the roller bearing stand of electric engineering lab in case western reserve university. Experimental results illustrate the higher accuracy of the proposed method compared with conventional method.

Fault Diagnosis of Rotating Machinery Due to Clearance Using Hilbert-Huang Transform

2009 ◽  
Author(s):  
Yeon-Sun Choi
Keyword(s):  
Fault Diagnosis ◽  
Rotating Machinery ◽  
Analysis Method ◽  
Hilbert Huang Transform ◽  
Time Frequency ◽  
Frequency Information ◽  
Stationary Signals ◽  
Signal Processing Methods ◽  
The Impact ◽  
Conventional Signal

The faults in rotating machinery, caused by the clearance between the rotor and the stator, commonly lie on partial rub and looseness. These problems cause malfunctions in rotating machinery since they create strange vibrations coming from impact and friction. However, non-linear and non-stationary signals due to impact and friction are difficult to identify. Therefore, exact time and frequency information are needed for identifying these signals. For this purpose, a newly developed time-frequency analysis method, HHT(Hilbert-Huang Transform), is applied to the signals of partial rub and looseness from the experiment RK-4 rotor kit. Conventional signal processing methods such as FFT, STFT and CWT were compared to verify the effectiveness of fault diagnosis using HHT. The results showed that the impact signals were generated regularly when partial rub occurred but that intermittent impact and friction occurred irregularly when looseness occurred. The time and frequency information was represented exactly by using HHT in both cases, which makes clear fault diagnosis between partial rub and looseness.

A New Spectral Representation of Earthquake Recordings Using an Improved Hilbert-Huang Transform

2011 ◽  
Vol 255-260 ◽  
pp. 1671-1675
Author(s):  
Tian Li Huang ◽  
Wei Xin Ren ◽  
Meng Lin Lou
Keyword(s):  
Empirical Mode Decomposition ◽  
Spectral Representation ◽  
Low Frequency ◽  
Accurate Information ◽  
Intrinsic Mode Functions ◽  
Hilbert Spectrum ◽  
Hilbert Huang Transform ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Marginal Spectrum

A new spectral representation method of earthquake recordings using an improved Hilbert-Huang transform (HHT) is proposed in the paper. Firstly, the problem that the intrinsic mode functions (IMFs) decomposed by the empirical mode decomposition (EMD) in HHT is not exactly orthogonal is pointed out and improved through the Gram-Schmidt orthogonalization method which is referred as the orthogonal empirical mode decomposition (OEMD). Combined the OEMD and the Hilbert transform (HT) which is referred as the improved Hilbert-Huang transform (IHHT), the orthogonal intrinsic mode functions (OIMFs) and the orthogonal Hilbert spectrum (OHS) and the orthogonal Hilbert marginal spectrum (OHMS) are obtained. Then, the IHHT has been applied for the analysis of the El Centro earthquake recording. The obtained spectral representation result shows that the OHS gives more detailed and accurate information in a time–frequency–energy presentation than the Hilbert spectrum (HS) and the OHMS gives more faithful low-frequency energy presentation than the Fourier spectrum (FS) and the Hilbert marginal spectrum (HMS).

METHOD FOR ENGINE WAVEFORM ANALYSIS AND FAULT DIAGNOSIS BASED ON SFB AND HHT

2013 ◽  
Vol 05 (04) ◽  
pp. 1350018
Author(s):  
SHUXIA JIANG ◽  
YIPING LUO ◽  
YUANYUAN LIU
Keyword(s):  
Fault Diagnosis ◽  
Time Domain ◽  
Pulse Width ◽  
Waveform Analysis ◽  
Analysis Method ◽  
Hilbert Huang Transform ◽  
Time Frequency ◽  
A New Technique ◽  
Injector Pulse ◽  
Mode Mixing

Traditional engine waveform analysis in time-domain fails to perform an accurate fault diagnosis when the fault waveform is very close to the normal waveform in time domain. A novel engine waveform analysis method is presented. In this paper, the aim is to perform fault diagnosis efficiently under such circumstances. This method is proposed by combining a new technique, called sensitive frequency band (SFB) selection, with the developed Hilbert–Huang transform (HHT). This can alleviate "mode mixing" by removing noise from the engine waveforms and reveal the time–frequency characteristics for a signal by deriving its time–frequency spectrum (TFS) distribution. The method is then applied to analyze the engine injector-pulse-width waveforms, and it works well for signal noise reduction and fault diagnosis.

Transform Operator Pair Assisted Hilbert–Huang Transform for Signals With Instantaneous Frequency Intersections

2015 ◽  
Vol 137 (6) ◽  
Author(s):  
Yuxin Sun ◽  
Chungang Zhuang ◽  
Zhenhua Xiong
Keyword(s):  
A Priori ◽  
Low Frequency ◽  
Ensemble Empirical Mode Decomposition ◽  
Frequency Resolution ◽  
Intrinsic Mode Functions ◽  
Hilbert Huang Transform ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Start Up ◽  
Instantaneous Frequencies

Due to low frequency resolution for closely spaced spectral components, i.e., the instantaneous frequencies (IFs) lie within an octave or even have intersections, the Hilbert–Huang transform (HHT) fails to separate such signals and consequently generates inaccurate time–frequency distribution (TFD). In this paper, a transform operator pair assisted HHT is proposed to improve the capability of the HHT to separate signals, especially those with IF intersections. The two operators of a pair are constructed to remove the chosen component that is clearly observed in the TFD of the signal, and then recover it from intrinsic mode functions (IMFs). With this approach, the components can be clearly separated and the intersections can also be identified in the TFD. Since a priori knowledge of the transform operator is usually not available in real applications, an iterative algorithm is presented to obtain a global transform operator. The effectiveness of the proposed algorithm is demonstrated by analysis of numerical signals and a real signal collected from a cracked rotor–bearing system during the start-up process. Moreover, the proposed approach is shown to be superior to the normalized Hilbert transform (NHT) as well as the ensemble empirical mode decomposition (EEMD).

scholarly journals Feature Extraction Strategy with Improved Permutation Entropy and Its Application in Fault Diagnosis of Bearings

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Fan Jiang ◽  
Zhencai Zhu ◽  
Wei Li ◽  
Bo Wu ◽  
Zhe Tong ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Optimal Number ◽  
Permutation Entropy ◽  
Support Vector ◽  
Intrinsic Mode Functions ◽  
Vibration Signals ◽  
Time Frequency ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis

Feature extraction is one of the most difficult aspects of mechanical fault diagnosis, and it is directly related to the accuracy of bearing fault diagnosis. In this study, improved permutation entropy (IPE) is defined as the feature for bearing fault diagnosis. In this method, ensemble empirical mode decomposition (EEMD), a self-adaptive time-frequency analysis method, is used to process the vibration signals, and a set of intrinsic mode functions (IMFs) can thus be obtained. A feature extraction strategy based on statistical analysis is then presented for IPE, where the so-called optimal number of permutation entropy (PE) values used for an IPE is adaptively selected. The obtained IPE-based samples are then input to a support vector machine (SVM) model. Subsequently, a trained SVM can be constructed as the classifier for bearing fault diagnosis. Finally, experimental vibration signals are applied to validate the effectiveness of the proposed method, and the results show that the proposed method can effectively and accurately diagnose bearing faults, such as inner race faults, outer race faults, and ball faults.

Enhanced deep residual network with multilevel correlation information for fault diagnosis of rotating machinery

2020 ◽  
pp. 107754632094971 ◽  
Author(s):  
Shoucong Xiong ◽  
Shuai He ◽  
Jianping Xuan ◽  
Qi Xia ◽  
Tielin Shi
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Wavelet Packet ◽  
Learning Algorithms ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Classification Performance ◽  
Residual Network ◽  
Time Frequency ◽  
Correlation Information

Modern machinery becomes more precious with the advance of science, and fault diagnosis is vital for avoiding economical losses or casualties. Among massive diagnosis methods, deep learning algorithms stand out to open an era of intelligent fault diagnosis. Deep residual networks are the state-of-the-art deep learning models which can continuously improve performance by deepening the network structures. However, in vibration-based fault diagnosis, the transient property instability of vibration signal usually calls for time–frequency analysis methods, and the characters of time–frequency matrices are distinct from standard images, which brings some natural limitations for the diagnosis performance of deep learning algorithms. To handle this issue, an enhanced deep residual network named the multilevel correlation stack-deep residual network is proposed in this article. Wavelet packet transform is used to preprocess the sensor signal, and then the proposed multilevel correlation stack-deep residual network uses kernels with different shapes to fully dig various kinds of useful information from any local regions of the processed input. Experiments on two rolling bearing datasets are carried out. Test results show that the multilevel correlation stack-deep residual network exhibits a more satisfactory classification performance than original deep residual networks and other similar methods, revealing significant potentials for realistic fault diagnosis applications.

Sign in / Sign up

Export Citation Format

Share Document