Spectral Kurtosis of Choi–Williams Distribution and Hidden Markov Model for Gearbox Fault Diagnosis
A combination of spectral kurtosis (SK), based on Choi−Williams distribution (CWD) and hidden Markov models (HMM), accurately identifies initial gearbox failures and diagnoses fault types of gearboxes. First, using the LMD algorithm, five types of gearbox vibration signals are collected an...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/12/2/285 |
| id |
doaj-bdeead427bb742e68250d5da0756fe97 |
|---|---|
| record_format |
Article |
| spelling |
doaj-bdeead427bb742e68250d5da0756fe972020-11-25T01:45:51ZengMDPI AGSymmetry2073-89942020-02-0112228510.3390/sym12020285sym12020285Spectral Kurtosis of Choi–Williams Distribution and Hidden Markov Model for Gearbox Fault DiagnosisYufei Li0Wanqing Song1Fei Wu2Enrico Zio3Yujin Zhang4School of Electronic & Electrical Engineering, Shanghai University of Science Engineering, Shanghai 201620, ChinaSchool of Electronic & Electrical Engineering, Shanghai University of Science Engineering, Shanghai 201620, ChinaSchool of Electronic & Electrical Engineering, Shanghai University of Science Engineering, Shanghai 201620, ChinaEnergy Department, Politecnico di Milano, Via La Masa 34/3, 20156 Milan, ItalySchool of Electronic & Electrical Engineering, Shanghai University of Science Engineering, Shanghai 201620, ChinaA combination of spectral kurtosis (SK), based on Choi−Williams distribution (CWD) and hidden Markov models (HMM), accurately identifies initial gearbox failures and diagnoses fault types of gearboxes. First, using the LMD algorithm, five types of gearbox vibration signals are collected and decomposed into several product function (PF) components and the multicomponent signals are decomposed into single-component signals. Then, the kurtosis value of each component is calculated, and the component with the largest kurtosis value is selected for the CWD-SK analysis. According to the calculated CWD-SK value, the characteristics of the initial failure of the gearbox are extracted. This method not only avoids the difficulty of selecting the window function, but also provides original eigenvalues for fault feature classification. In the end, from the CWD-SK characteristic parameters at each characteristic frequency, the characteristic sequence based on CWD-SK is obtained with HMM training and diagnosis. The experimental results show that this method can effectively identify the initial fault characteristics of the gearbox, and also accurately classify the fault characteristics of different degrees.https://www.mdpi.com/2073-8994/12/2/285choi–williams distributionspectral kurtosishmmgearbox fault classification |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Yufei Li Wanqing Song Fei Wu Enrico Zio Yujin Zhang |
| spellingShingle |
Yufei Li Wanqing Song Fei Wu Enrico Zio Yujin Zhang Spectral Kurtosis of Choi–Williams Distribution and Hidden Markov Model for Gearbox Fault Diagnosis Symmetry choi–williams distribution spectral kurtosis hmm gearbox fault classification |
| author_facet |
Yufei Li Wanqing Song Fei Wu Enrico Zio Yujin Zhang |
| author_sort |
Yufei Li |
| title |
Spectral Kurtosis of Choi–Williams Distribution and Hidden Markov Model for Gearbox Fault Diagnosis |
| title_short |
Spectral Kurtosis of Choi–Williams Distribution and Hidden Markov Model for Gearbox Fault Diagnosis |
| title_full |
Spectral Kurtosis of Choi–Williams Distribution and Hidden Markov Model for Gearbox Fault Diagnosis |
| title_fullStr |
Spectral Kurtosis of Choi–Williams Distribution and Hidden Markov Model for Gearbox Fault Diagnosis |
| title_full_unstemmed |
Spectral Kurtosis of Choi–Williams Distribution and Hidden Markov Model for Gearbox Fault Diagnosis |
| title_sort |
spectral kurtosis of choi–williams distribution and hidden markov model for gearbox fault diagnosis |
| publisher |
MDPI AG |
| series |
Symmetry |
| issn |
2073-8994 |
| publishDate |
2020-02-01 |
| description |
A combination of spectral kurtosis (SK), based on Choi−Williams distribution (CWD) and hidden Markov models (HMM), accurately identifies initial gearbox failures and diagnoses fault types of gearboxes. First, using the LMD algorithm, five types of gearbox vibration signals are collected and decomposed into several product function (PF) components and the multicomponent signals are decomposed into single-component signals. Then, the kurtosis value of each component is calculated, and the component with the largest kurtosis value is selected for the CWD-SK analysis. According to the calculated CWD-SK value, the characteristics of the initial failure of the gearbox are extracted. This method not only avoids the difficulty of selecting the window function, but also provides original eigenvalues for fault feature classification. In the end, from the CWD-SK characteristic parameters at each characteristic frequency, the characteristic sequence based on CWD-SK is obtained with HMM training and diagnosis. The experimental results show that this method can effectively identify the initial fault characteristics of the gearbox, and also accurately classify the fault characteristics of different degrees. |
| topic |
choi–williams distribution spectral kurtosis hmm gearbox fault classification |
| url |
https://www.mdpi.com/2073-8994/12/2/285 |
| work_keys_str_mv |
AT yufeili spectralkurtosisofchoiwilliamsdistributionandhiddenmarkovmodelforgearboxfaultdiagnosis AT wanqingsong spectralkurtosisofchoiwilliamsdistributionandhiddenmarkovmodelforgearboxfaultdiagnosis AT feiwu spectralkurtosisofchoiwilliamsdistributionandhiddenmarkovmodelforgearboxfaultdiagnosis AT enricozio spectralkurtosisofchoiwilliamsdistributionandhiddenmarkovmodelforgearboxfaultdiagnosis AT yujinzhang spectralkurtosisofchoiwilliamsdistributionandhiddenmarkovmodelforgearboxfaultdiagnosis |
| _version_ |
1725022271762857984 |