A Fault Diagnosis Methodology Based on Non-Stationary Monitoring Signals by Extracting Features With Unknown Probability Distribution
This paper studies features with the characteristic of unknown probability distribution, and its application on fault diagnosis based on non-stationary monitoring signals, which mainly consider the uncertainty as the main factor in masking fault diagnosis of practical industrial system. Generally, t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9025196/ |
| _version_ | 1818557937665179648 |
|---|---|
| author | Huang Lei Wang Yiming Qu Jianfeng Ren Hao |
| author_facet | Huang Lei Wang Yiming Qu Jianfeng Ren Hao |
| author_sort | Huang Lei |
| collection | DOAJ |
| description | This paper studies features with the characteristic of unknown probability distribution, and its application on fault diagnosis based on non-stationary monitoring signals, which mainly consider the uncertainty as the main factor in masking fault diagnosis of practical industrial system. Generally, the probability distribution of the signal feature is unknown and prior information of the trend term is lacking. For this reason, different feature extraction methods, such as time-domain, frequency-domain and time-frequency-domain methods, have always been used to extract features, and they can be used to generate a high-dimensional and nonlinear initial feature set. However, the features' probability distribution is still unknown and prior information of the trend term is still lacking. In order to solve this top problem, Restricted Boltzmann Machine (RBM), with the advantage of feature learning and selection for initial feature set, has been stacked layer by layer to realize a high-dimensional nonlinear mapping between non-stationary signal features and fault modes. Two fault diagnosis experiments on self-confirmation sensor and rolling bearing shown the robustness and effectiveness of this proposed method. |
| first_indexed | 2024-12-14T00:06:15Z |
| format | Article |
| id | doaj.art-42986db8d1cd46fab1905ca133d37f55 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T00:06:15Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-42986db8d1cd46fab1905ca133d37f552022-12-21T23:26:01ZengIEEEIEEE Access2169-35362020-01-018598215983610.1109/ACCESS.2020.29781129025196A Fault Diagnosis Methodology Based on Non-Stationary Monitoring Signals by Extracting Features With Unknown Probability DistributionHuang Lei0Wang Yiming1Qu Jianfeng2Ren Hao3https://orcid.org/0000-0001-8471-9132School of Computer Science and Technology, Huaiyin Normal University, Huai’an, ChinaSchool of Automation, Chongqing University, Chongqing, ChinaSchool of Automation, Chongqing University, Chongqing, ChinaSchool of Automation, Chongqing University, Chongqing, ChinaThis paper studies features with the characteristic of unknown probability distribution, and its application on fault diagnosis based on non-stationary monitoring signals, which mainly consider the uncertainty as the main factor in masking fault diagnosis of practical industrial system. Generally, the probability distribution of the signal feature is unknown and prior information of the trend term is lacking. For this reason, different feature extraction methods, such as time-domain, frequency-domain and time-frequency-domain methods, have always been used to extract features, and they can be used to generate a high-dimensional and nonlinear initial feature set. However, the features' probability distribution is still unknown and prior information of the trend term is still lacking. In order to solve this top problem, Restricted Boltzmann Machine (RBM), with the advantage of feature learning and selection for initial feature set, has been stacked layer by layer to realize a high-dimensional nonlinear mapping between non-stationary signal features and fault modes. Two fault diagnosis experiments on self-confirmation sensor and rolling bearing shown the robustness and effectiveness of this proposed method.https://ieeexplore.ieee.org/document/9025196/Feature extractionrestricted Boltzmann machinedeep belief networknon-stationary signalsfault diagnosis |
| spellingShingle | Huang Lei Wang Yiming Qu Jianfeng Ren Hao A Fault Diagnosis Methodology Based on Non-Stationary Monitoring Signals by Extracting Features With Unknown Probability Distribution IEEE Access Feature extraction restricted Boltzmann machine deep belief network non-stationary signals fault diagnosis |
| title | A Fault Diagnosis Methodology Based on Non-Stationary Monitoring Signals by Extracting Features With Unknown Probability Distribution |
| title_full | A Fault Diagnosis Methodology Based on Non-Stationary Monitoring Signals by Extracting Features With Unknown Probability Distribution |
| title_fullStr | A Fault Diagnosis Methodology Based on Non-Stationary Monitoring Signals by Extracting Features With Unknown Probability Distribution |
| title_full_unstemmed | A Fault Diagnosis Methodology Based on Non-Stationary Monitoring Signals by Extracting Features With Unknown Probability Distribution |
| title_short | A Fault Diagnosis Methodology Based on Non-Stationary Monitoring Signals by Extracting Features With Unknown Probability Distribution |
| title_sort | fault diagnosis methodology based on non stationary monitoring signals by extracting features with unknown probability distribution |
| topic | Feature extraction restricted Boltzmann machine deep belief network non-stationary signals fault diagnosis |
| url | https://ieeexplore.ieee.org/document/9025196/ |
| work_keys_str_mv | AT huanglei afaultdiagnosismethodologybasedonnonstationarymonitoringsignalsbyextractingfeatureswithunknownprobabilitydistribution AT wangyiming afaultdiagnosismethodologybasedonnonstationarymonitoringsignalsbyextractingfeatureswithunknownprobabilitydistribution AT qujianfeng afaultdiagnosismethodologybasedonnonstationarymonitoringsignalsbyextractingfeatureswithunknownprobabilitydistribution AT renhao afaultdiagnosismethodologybasedonnonstationarymonitoringsignalsbyextractingfeatureswithunknownprobabilitydistribution AT huanglei faultdiagnosismethodologybasedonnonstationarymonitoringsignalsbyextractingfeatureswithunknownprobabilitydistribution AT wangyiming faultdiagnosismethodologybasedonnonstationarymonitoringsignalsbyextractingfeatureswithunknownprobabilitydistribution AT qujianfeng faultdiagnosismethodologybasedonnonstationarymonitoringsignalsbyextractingfeatureswithunknownprobabilitydistribution AT renhao faultdiagnosismethodologybasedonnonstationarymonitoringsignalsbyextractingfeatureswithunknownprobabilitydistribution |