Fault diagnosis of gas turbine based on matrix capsules with EM routing
The fault detection and diagnosis of a gas turbine is of great significance for guaranteeing the complicated dynamic systems working normally and safely. Most of the existing fault diagnosis methods, based on convolutional neural networks (CNN), have certain limitations in extracting correlations of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2021-04-01
|
| Series: | Systems Science & Control Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/21642583.2020.1833783 |
| _version_ | 1829142798393147392 |
|---|---|
| author | Yunji Zhao Menglin Zhou Nannan Zhang Xiaozhuo Xu Xinliang Zhang |
| author_facet | Yunji Zhao Menglin Zhou Nannan Zhang Xiaozhuo Xu Xinliang Zhang |
| author_sort | Yunji Zhao |
| collection | DOAJ |
| description | The fault detection and diagnosis of a gas turbine is of great significance for guaranteeing the complicated dynamic systems working normally and safely. Most of the existing fault diagnosis methods, based on convolutional neural networks (CNN), have certain limitations in extracting correlations of multi-channel data features. The accuracy of fault diagnosis still needs to be improved. In this paper, an approach of fault diagnosis, based on matrix capsules with EM routing, is presented. First of all, three channels data, which respectively represent acceleration, pressure and pulse, are integrated into one image to feed into the network. Secondly, network models based on the matrix capsules start to be trained by using input dataset which contains fault image and normal image. Finally, the pre-trained capsules model is used to diagnose the state of testing data. Besides, to verify the superiority of the algorithm used in this paper, a comparative experiment is implemented between matrix capsule networks and CNN. The results demonstrate that the testing accuracy is 99.995%. |
| first_indexed | 2024-12-14T20:37:53Z |
| format | Article |
| id | doaj.art-c479ff2579764f008caeb681ef6c1488 |
| institution | Directory Open Access Journal |
| issn | 2164-2583 |
| language | English |
| last_indexed | 2024-12-14T20:37:53Z |
| publishDate | 2021-04-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Systems Science & Control Engineering |
| spelling | doaj.art-c479ff2579764f008caeb681ef6c14882022-12-21T22:48:21ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832021-04-019S19610210.1080/21642583.2020.18337831833783Fault diagnosis of gas turbine based on matrix capsules with EM routingYunji Zhao0Menglin Zhou1Nannan Zhang2Xiaozhuo Xu3Xinliang Zhang4School of Electrical Engineering and Automation, Henan Polytechnic UniversitySchool of Electrical Engineering and Automation, Henan Polytechnic UniversitySchool of Electrical Engineering and Automation, Henan Polytechnic UniversitySchool of Electrical Engineering and Automation, Henan Polytechnic UniversitySchool of Electrical Engineering and Automation, Henan Polytechnic UniversityThe fault detection and diagnosis of a gas turbine is of great significance for guaranteeing the complicated dynamic systems working normally and safely. Most of the existing fault diagnosis methods, based on convolutional neural networks (CNN), have certain limitations in extracting correlations of multi-channel data features. The accuracy of fault diagnosis still needs to be improved. In this paper, an approach of fault diagnosis, based on matrix capsules with EM routing, is presented. First of all, three channels data, which respectively represent acceleration, pressure and pulse, are integrated into one image to feed into the network. Secondly, network models based on the matrix capsules start to be trained by using input dataset which contains fault image and normal image. Finally, the pre-trained capsules model is used to diagnose the state of testing data. Besides, to verify the superiority of the algorithm used in this paper, a comparative experiment is implemented between matrix capsule networks and CNN. The results demonstrate that the testing accuracy is 99.995%.http://dx.doi.org/10.1080/21642583.2020.1833783gas turbinefault diagnosiscapsulesem routingaccuracy |
| spellingShingle | Yunji Zhao Menglin Zhou Nannan Zhang Xiaozhuo Xu Xinliang Zhang Fault diagnosis of gas turbine based on matrix capsules with EM routing Systems Science & Control Engineering gas turbine fault diagnosis capsules em routing accuracy |
| title | Fault diagnosis of gas turbine based on matrix capsules with EM routing |
| title_full | Fault diagnosis of gas turbine based on matrix capsules with EM routing |
| title_fullStr | Fault diagnosis of gas turbine based on matrix capsules with EM routing |
| title_full_unstemmed | Fault diagnosis of gas turbine based on matrix capsules with EM routing |
| title_short | Fault diagnosis of gas turbine based on matrix capsules with EM routing |
| title_sort | fault diagnosis of gas turbine based on matrix capsules with em routing |
| topic | gas turbine fault diagnosis capsules em routing accuracy |
| url | http://dx.doi.org/10.1080/21642583.2020.1833783 |
| work_keys_str_mv | AT yunjizhao faultdiagnosisofgasturbinebasedonmatrixcapsuleswithemrouting AT menglinzhou faultdiagnosisofgasturbinebasedonmatrixcapsuleswithemrouting AT nannanzhang faultdiagnosisofgasturbinebasedonmatrixcapsuleswithemrouting AT xiaozhuoxu faultdiagnosisofgasturbinebasedonmatrixcapsuleswithemrouting AT xinliangzhang faultdiagnosisofgasturbinebasedonmatrixcapsuleswithemrouting |