Local Mean Decomposition Based Bearing Fault Detection

2012 ◽  
Vol 490-495 ◽  
pp. 360-364 ◽  
Author(s):  
Hui Li
Keyword(s):  
Vibration Signal ◽  
Noise Condition ◽  
Local Mean Decomposition ◽  
Outer Race ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Product Function ◽  
Local Mean ◽  
Novel Method ◽  
Envelope Spectrum

A novel method of bearing fault diagnosis based on local mean decomposition (LMD) is proposed. LMD method is self-adaptive to non-stationary and non-linear signal. LMD can adaptively decompose the vibration signal into a series of product functions (PFs), which is the product of an envelope signal and a frequency modulated signal. Then the envelope spectrum is applied to the selected product function that stands for the bearing faults. Therefore, the character of the bearing fault can be recognized according to the envelope spectrum of product function. The experimental results show that local mean decomposition based envelope spectrum can effectively detect and diagnose bearing inner and outer race fault under strong background noise condition.

Bearing Fault Diagnosis Based on Dual-Tree Complex Wavelet Transform

2012 ◽  
Vol 490-495 ◽  
pp. 128-132
Author(s):  
Hui Li
Keyword(s):  
Wavelet Transform ◽  
Fault Diagnosis ◽  
Vibration Signal ◽  
Complex Wavelet Transform ◽  
Noise Condition ◽  
Outer Race ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Complex Wavelet ◽  
Envelope Spectrum

A novel method of bearing fault diagnosis based on demodulation technique of dual-tree complex wavelet transform (DTCWT) is proposed. It is demonstrated that the proposed dual-tree complex wavelet transform has better shift invariance, reduced frequency aliasing effect and de-noising ability. The bearing fault vibration signal is firstly decomposed and reconstructed using dual-tree complex wavelet transform. Then the real and imaginary parts are obtained and the vibration signal is amplitude demodulated. In the end, the amplitude envelope and wavelet envelope spectrum are computed. Therefore, the character of the bearing fault can be recognized according to the wavelet envelope spectrum. The experimental results show that dual-tree complex wavelet transform can effectively reduce spectral aliasing and fault diagnosis based on dual-tree complex wavelet transform can effectively diagnose bearing inner and outer race fault under strong background noise condition.

Bearing Fault Detection Based on Multi-Scale Laplace Wavelet Transform Spectrum

2013 ◽  
Vol 739 ◽  
pp. 413-417
Author(s):  
Ya Ning Wang
Keyword(s):  
Wavelet Transform ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Three Dimensions ◽  
Noise Condition ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Multi Scale ◽  
Integrated Technique ◽  
Envelope Spectrum

Laplace wavelet transform is self-adaptive to non-stationary and non-linear signal, which can detect the singularity characteristic of a signal precisely under strong background noise condition. A new method of bearing fault diagnosis based on multi-scale Laplace wavelet transform spectrum is proposed. The multi scale Laplace wavelet transform spectrum technique combines the advantages of Laplace wavelet transform, envelope spectrum and three dimensions color map into one integrated technique. The bearing fault vibration signal is firstly decomposed using Laplace wavelet transform. In the end, the multi scale Laplace wavelet transform spectrum is obtained and the characteristics of the bearing fault can be recognized according to the multi-scale Laplace wavelet transform spectrum. The proposed method has been verified by vibration signals obtained from rolling bearing with inner race fault.

Multi-Scale Hermitian Wavelet Envelope Spectrum Based Bearing Fault Detection

2012 ◽  
Vol 459 ◽  
pp. 132-136 ◽  
Author(s):  
Hui Li
Keyword(s):  
Wavelet Transform ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Three Dimensions ◽  
Noise Condition ◽  
Outer Race ◽  
Bearing Fault ◽  
Multi Scale ◽  
Integrated Technique ◽  
Envelope Spectrum

Hermitian wavelet is a low-oscillation, complex valued wavelet, which can detect the singularity characteristic of a signal precisely under strong background noise condition. A new method of bearing fault diagnosis based on multi-scale Hermitian wavelet envelope spectrum is proposed. The multi scale Hermitian wavelet envelope spectrum technique combines the advantages of Hermitian wavelet transform, envelope spectrum and three dimensions color map into one integrated technique. The bearing fault vibration signal is firstly decomposed using Hermitian continuous wavelet transform. Then the real and imaginary parts are obtained. In the end, the multi scale Hermitian wavelet envelope spectrum is obtained and the characteristics of the bearing fault can be recognized according to the multi-scale Hermitian wavelet envelope spectrum. The proposed method has been proved by vibration signals obtained from rolling bearing with inner or outer race fault. The experimental results verified the effectiveness of the proposed method.

Bearing Fault Diagnosis Based on Statistical Feature Extraction in Time and Frequency Domain and Neural Network

2017 ◽  
Vol 8 (4) ◽  
Author(s):  
L.S. Dhamande ◽  
M.B. Chaudhari
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Vibration Signal ◽  
Angular Speed ◽  
Machine Intelligence ◽  
Outer Race ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Rolling Element ◽  
Set Up

Bearing is an important component of almost every mechanical system used in industrial environment. Hence the defect in bearing must be detected in advance to avoid catastrophic failure. This paper aims to diagnose the defect in bearing automatically using machine intelligence. A condition monitoring setup is designed for analyzing the defects in outer race, inner race and rolling element of bearing. MATLAB is used for feature extraction and neural network is used for diagnosis. It is found that the amplitude at defect frequencies may not always clearly indicate the increment; hence statistical analysis of bearing signature is a better alternative. The work presents an experimental investigation carried out on an experimental set-up for the study of bearing fault at same angular speed and load. This paper proposes an approach of damage detection in which defects in bearing are accurately analysed using vibration signal and neural network.

Gas pipeline small leakage feature extraction based on LMD envelope spectrum entropy and PCA–RWSVM

2016 ◽  
Vol 38 (12) ◽  
pp. 1460-1470 ◽  
Author(s):  
Lina Wang ◽  
Xianwen Gao ◽  
Tan Liu
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Principal Component ◽  
Support Vector ◽  
Local Mean Decomposition ◽  
Natural Gas Pipelines ◽  
Product Function ◽  
Vector Machines ◽  
Local Mean ◽  
Envelope Spectrum

This paper presents a novel intelligent method based on local mean decomposition and multi-class reproducing wavelet support vector machines (RWSVMs), which are applied to detect leakage in natural gas pipelines. First, local mean decomposition is used to construct product function components to decompose the leakage signals. Then, we select the leakage signals which contain the most leakage information, according to the kurtosis features of these signals, through principal component analysis. Next, we reconstruct the principal product function components in order to acquire the envelope spectrum. Finally, we confirm the leak aperture by inputting envelope spectrum entropy features, as feature vectors, into the RWSVMs. Through analysing the pipeline leakage signals, the experiments show that this method can effectively identify different leak categories.

scholarly journals Improving the Accuracy of Fault Frequency by Means of Local Mean Decomposition and Ratio Correction Method for Rolling Bearing Failure

2019 ◽  
Vol 9 (9) ◽  
pp. 1888 ◽  
Author(s):  
Yongqiang Duan ◽  
Chengdong Wang ◽  
Yong Chen ◽  
Peisen Liu
Keyword(s):  
Fault Location ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Correction Method ◽  
Bearing Failure ◽  
Local Mean Decomposition ◽  
Local Mean ◽  
Hilbert Envelope ◽  
Ratio Correction ◽  
Envelope Spectrum

The fault frequencies are as they are and cannot be improved. One can only improve its estimation quality. This paper proposes a fault diagnosis method by combining local mean decomposition (LMD) and the ratio correction method to process the short-time signals. Firstly, the vibration signal of rolling bearing is decomposed into a series of product functions (PFs) by LMD. The PF, which contains the richest fault information, is selected to perform envelope spectrum analysis by the Hilbert transform (HT). Secondly, the Hilbert envelope spectrum of the selected PF is corrected with the ratio correction method. Finally, higher precision fault frequencies are extracted from the corrected Hilbert envelope spectrum, and then the fault location is accurately determined. The proposed method of this paper can be used in online real-time monitoring technology of rolling bearing failure.

Improved Local Mean Decomposition and its Application to Fault Diagnosis of Train Bearing

2013 ◽  
Vol 819 ◽  
pp. 155-159
Author(s):  
Peng Wang ◽  
Huai Xiang Ma
Keyword(s):  
Fault Diagnosis ◽  
Vibration Signal ◽  
Processing Method ◽  
Nonstationary Signal ◽  
Practical Application ◽  
Local Mean Decomposition ◽  
Signal Processing Method ◽  
Signal Demodulation ◽  
Improvement Method ◽  
Local Mean

Fault diagnosis of train bearing is an important method to ensure the security of railway. The key to the fault diagnosis is the method of vibration signal demodulation. The local mean decomposition (LMD) is a self-adapted signal processing method which has a good performance in nonlinear nonstationary signal demodulation. The improved LMD method based on kurtosis criterion can prevent errors in the process of calculating the product functions. With the verification of simulation and wheel set experiment, the improvement method has been certified usefully in practical application.

Sign in / Sign up

Export Citation Format

Share Document