Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMAC
This paper proposed a new method of fault diagnosis based on Noise Assisted Multivariate Empirical Mode Decomposition (NA-MEMD) and Fuzzy Recurrent Cerebellar Model Articulation Controller (FRCMAC) Neural Networks. Aiming at the problem that during the use of the NA-MEMD method, the white noise ampl...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2018-10-01
|
Series: | The Journal of Engineering |
Subjects: | |
Online Access: | https://digital-library.theiet.org/content/journals/10.1049/joe.2018.8991 |
id |
doaj-b4bc21ecf50c46a6a826f5ef6d40944a |
---|---|
record_format |
Article |
spelling |
doaj-b4bc21ecf50c46a6a826f5ef6d40944a2021-04-02T12:44:09ZengWileyThe Journal of Engineering2051-33052018-10-0110.1049/joe.2018.8991JOE.2018.8991Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMACSheng Liu0Yue Sun1Lanyong Zhang2College of Automation, Harbin Engineering UniversityCollege of Automation, Harbin Engineering UniversityCollege of Automation, Harbin Engineering UniversityThis paper proposed a new method of fault diagnosis based on Noise Assisted Multivariate Empirical Mode Decomposition (NA-MEMD) and Fuzzy Recurrent Cerebellar Model Articulation Controller (FRCMAC) Neural Networks. Aiming at the problem that during the use of the NA-MEMD method, the white noise amplitude parameter needs to be selected by artificial experience, a method of using Genetic Algorithm (GA) to optimize its auxiliary white noise parameters is proposed, which facilitates the use of NA-MEMD. We proposed a novel FRCMAC structure which improved Learning efficiency and dynamic response speed than traditional CMAC structure. First, the GA-NA-MEMD method is applied to process the vibration signals of rolling bearings, and the signals are decomposed into a group of Intrinsic Mode Functions (IMFs). Then use energy moments of IMFs as fault feature vectors to train FRCMAC neural network, a neural network structure suitable for rolling bearing fault diagnosis is obtained. Finally, the data from bearing data center of Case Western Reserve University is used to prove that the fault diagnosis method proposed in this paper is superior to other methods in diagnosis time and precision, which can meet the training requirements more quickly with limited training samples and fault diagnosis results more accurate.https://digital-library.theiet.org/content/journals/10.1049/joe.2018.8991genetic algorithmsacoustic signal processingcerebellar model arithmetic computersrolling bearingsneurocontrollersmechanical engineering computingwhite noisevibrationsmachine bearingsfault diagnosisfault diagnosis approachnoise-assisted multivariate empirical mode decompositionfuzzy recurrent cerebellar model articulation controller neural networksartificial experiencegenetic algorithmauxiliary white noise parametersFRCMAC structurefuzzy processinginput spaceassociation degreeGaussian functionassociation unitautoregressive unitdynamic mappingtraditional CMAC structureGA-NA-MEMD methodrolling bearingsintrinsic mode functionsIMFsfault feature vectorsFRCMAC neural networkneural network structure suitablebearing fault diagnosisBearing Data Centerfault diagnosis methoddiagnosis timeprecisionfault diagnosis results |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sheng Liu Yue Sun Lanyong Zhang |
spellingShingle |
Sheng Liu Yue Sun Lanyong Zhang Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMAC The Journal of Engineering genetic algorithms acoustic signal processing cerebellar model arithmetic computers rolling bearings neurocontrollers mechanical engineering computing white noise vibrations machine bearings fault diagnosis fault diagnosis approach noise-assisted multivariate empirical mode decomposition fuzzy recurrent cerebellar model articulation controller neural networks artificial experience genetic algorithm auxiliary white noise parameters FRCMAC structure fuzzy processing input space association degree Gaussian function association unit autoregressive unit dynamic mapping traditional CMAC structure GA-NA-MEMD method rolling bearings intrinsic mode functions IMFs fault feature vectors FRCMAC neural network neural network structure suitable bearing fault diagnosis Bearing Data Center fault diagnosis method diagnosis time precision fault diagnosis results |
author_facet |
Sheng Liu Yue Sun Lanyong Zhang |
author_sort |
Sheng Liu |
title |
Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMAC |
title_short |
Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMAC |
title_full |
Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMAC |
title_fullStr |
Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMAC |
title_full_unstemmed |
Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMAC |
title_sort |
fault diagnosis approach of rolling bearing based on na-memd and frcmac |
publisher |
Wiley |
series |
The Journal of Engineering |
issn |
2051-3305 |
publishDate |
2018-10-01 |
description |
This paper proposed a new method of fault diagnosis based on Noise Assisted Multivariate Empirical Mode Decomposition (NA-MEMD) and Fuzzy Recurrent Cerebellar Model Articulation Controller (FRCMAC) Neural Networks. Aiming at the problem that during the use of the NA-MEMD method, the white noise amplitude parameter needs to be selected by artificial experience, a method of using Genetic Algorithm (GA) to optimize its auxiliary white noise parameters is proposed, which facilitates the use of NA-MEMD. We proposed a novel FRCMAC structure which improved Learning efficiency and dynamic response speed than traditional CMAC structure. First, the GA-NA-MEMD method is applied to process the vibration signals of rolling bearings, and the signals are decomposed into a group of Intrinsic Mode Functions (IMFs). Then use energy moments of IMFs as fault feature vectors to train FRCMAC neural network, a neural network structure suitable for rolling bearing fault diagnosis is obtained. Finally, the data from bearing data center of Case Western Reserve University is used to prove that the fault diagnosis method proposed in this paper is superior to other methods in diagnosis time and precision, which can meet the training requirements more quickly with limited training samples and fault diagnosis results more accurate. |
topic |
genetic algorithms acoustic signal processing cerebellar model arithmetic computers rolling bearings neurocontrollers mechanical engineering computing white noise vibrations machine bearings fault diagnosis fault diagnosis approach noise-assisted multivariate empirical mode decomposition fuzzy recurrent cerebellar model articulation controller neural networks artificial experience genetic algorithm auxiliary white noise parameters FRCMAC structure fuzzy processing input space association degree Gaussian function association unit autoregressive unit dynamic mapping traditional CMAC structure GA-NA-MEMD method rolling bearings intrinsic mode functions IMFs fault feature vectors FRCMAC neural network neural network structure suitable bearing fault diagnosis Bearing Data Center fault diagnosis method diagnosis time precision fault diagnosis results |
url |
https://digital-library.theiet.org/content/journals/10.1049/joe.2018.8991 |
work_keys_str_mv |
AT shengliu faultdiagnosisapproachofrollingbearingbasedonnamemdandfrcmac AT yuesun faultdiagnosisapproachofrollingbearingbasedonnamemdandfrcmac AT lanyongzhang faultdiagnosisapproachofrollingbearingbasedonnamemdandfrcmac |
_version_ |
1721567794062950400 |