Intelligent Early Fault Diagnosis of Space Flywheel Rotor System
Three frequently encountered problems—a variety of fault types, data with insufficient labels, and missing fault types—are the common challenges in the early fault diagnosis of space flywheel rotor systems. Focusing on the above issues, this paper proposes an intelligent early fault diagnosis method...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/19/8198 |
| _version_ | 1827722232515788800 |
|---|---|
| author | Hui Liao Pengfei Xie Sier Deng Hengdi Wang |
| author_facet | Hui Liao Pengfei Xie Sier Deng Hengdi Wang |
| author_sort | Hui Liao |
| collection | DOAJ |
| description | Three frequently encountered problems—a variety of fault types, data with insufficient labels, and missing fault types—are the common challenges in the early fault diagnosis of space flywheel rotor systems. Focusing on the above issues, this paper proposes an intelligent early fault diagnosis method based on the multi-channel convolutional neural network with hierarchical branch and similarity clustering (HB-SC-MCCNN). First, a similarity clustering (SC) method is integrated into the parameter-shared dual MCCNN architecture to set up as the basic structural block. The hierarchical branch model and additional loss are then added to SC-MCCNN to form a hierarchical branch network, which simplifies the problem of fault multi-classification into binary classification with multi-steps. Based on the self-learning characteristics of the proposed model, the unlabeled data and the missing fault types in the training set are re-labeled to realize the re-training of the network. The results of the experiments for comparing the abilities between the proposed method and several advanced deep learning models confirm that on the established early fault dataset of the space flywheel rotor system, the proposed method successfully achieves the hierarchical diagnosis and presents stronger competitiveness in the case of insufficient labeled data and missing fault types at the same time. |
| first_indexed | 2024-03-10T21:35:04Z |
| format | Article |
| id | doaj.art-d62c024f2c27426ba8170be1bd65091d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T21:35:04Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d62c024f2c27426ba8170be1bd65091d2023-11-19T15:04:09ZengMDPI AGSensors1424-82202023-09-012319819810.3390/s23198198Intelligent Early Fault Diagnosis of Space Flywheel Rotor SystemHui Liao0Pengfei Xie1Sier Deng2Hengdi Wang3School of Mechatronics Engineering, Northwestern Polytechnical University, Xi’an 710071, ChinaSchool of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Mechatronics Engineering, Northwestern Polytechnical University, Xi’an 710071, ChinaSchool of Mechatronics Engineering, Henan University of Science and Technology, Luoyang 471003, ChinaThree frequently encountered problems—a variety of fault types, data with insufficient labels, and missing fault types—are the common challenges in the early fault diagnosis of space flywheel rotor systems. Focusing on the above issues, this paper proposes an intelligent early fault diagnosis method based on the multi-channel convolutional neural network with hierarchical branch and similarity clustering (HB-SC-MCCNN). First, a similarity clustering (SC) method is integrated into the parameter-shared dual MCCNN architecture to set up as the basic structural block. The hierarchical branch model and additional loss are then added to SC-MCCNN to form a hierarchical branch network, which simplifies the problem of fault multi-classification into binary classification with multi-steps. Based on the self-learning characteristics of the proposed model, the unlabeled data and the missing fault types in the training set are re-labeled to realize the re-training of the network. The results of the experiments for comparing the abilities between the proposed method and several advanced deep learning models confirm that on the established early fault dataset of the space flywheel rotor system, the proposed method successfully achieves the hierarchical diagnosis and presents stronger competitiveness in the case of insufficient labeled data and missing fault types at the same time.https://www.mdpi.com/1424-8220/23/19/8198space flywheel rotor systemintelligent fault diagnosisdata with insufficient labelsmissing fault typeshierarchical branch structuresimilarity clustering |
| spellingShingle | Hui Liao Pengfei Xie Sier Deng Hengdi Wang Intelligent Early Fault Diagnosis of Space Flywheel Rotor System Sensors space flywheel rotor system intelligent fault diagnosis data with insufficient labels missing fault types hierarchical branch structure similarity clustering |
| title | Intelligent Early Fault Diagnosis of Space Flywheel Rotor System |
| title_full | Intelligent Early Fault Diagnosis of Space Flywheel Rotor System |
| title_fullStr | Intelligent Early Fault Diagnosis of Space Flywheel Rotor System |
| title_full_unstemmed | Intelligent Early Fault Diagnosis of Space Flywheel Rotor System |
| title_short | Intelligent Early Fault Diagnosis of Space Flywheel Rotor System |
| title_sort | intelligent early fault diagnosis of space flywheel rotor system |
| topic | space flywheel rotor system intelligent fault diagnosis data with insufficient labels missing fault types hierarchical branch structure similarity clustering |
| url | https://www.mdpi.com/1424-8220/23/19/8198 |
| work_keys_str_mv | AT huiliao intelligentearlyfaultdiagnosisofspaceflywheelrotorsystem AT pengfeixie intelligentearlyfaultdiagnosisofspaceflywheelrotorsystem AT sierdeng intelligentearlyfaultdiagnosisofspaceflywheelrotorsystem AT hengdiwang intelligentearlyfaultdiagnosisofspaceflywheelrotorsystem |