TN-GTN: fault diagnosis of aircraft wiring network over edge computing
Abstract Fault diagnosis of the aircraft wiring network plays an important role in the intelligent manufacture of the aircraft. Many studies focus on the feature-based machine learning methods. However, these methods are improper in handling the data on heterogeneous graphs. Due to the scatter of th...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-07-01
|
| Series: | EURASIP Journal on Wireless Communications and Networking |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13638-022-02148-w |
| _version_ | 1818509914653327360 |
|---|---|
| author | Tian Wang Qiang Fang Gongping Liu Meng Chi Yuanqi Luo Jianming Shen |
| author_facet | Tian Wang Qiang Fang Gongping Liu Meng Chi Yuanqi Luo Jianming Shen |
| author_sort | Tian Wang |
| collection | DOAJ |
| description | Abstract Fault diagnosis of the aircraft wiring network plays an important role in the intelligent manufacture of the aircraft. Many studies focus on the feature-based machine learning methods. However, these methods are improper in handling the data on heterogeneous graphs. Due to the scatter of the valid feature information, the relevant information between the test nodes is ignored by these methods, which leads to the low accuracy fault diagnosis. Taking the advantage of the 5G technology that can remotely process large-scale graph data, this work proposes a fault diagnosis method named “topological network-graph transformer network (TN-GTN).” TN-GTN can improve the fault diagnosis accuracy through feature enhancement and classification, which is based on the topological information of heterogeneous graphs. The graph network is able to learn new graph structures by identifying useful meta-paths and multi-hop connections between unconnected nodes on original graphs. Feature-enhanced test nodes are used to classify the final labels by the artificial neural network. Results of the performed experiment showed that TN-GTN reduced the dependence on domain knowledge and achieved an accurate classification of the fault diagnosis on aircraft wiring network. |
| first_indexed | 2024-12-10T22:52:01Z |
| format | Article |
| id | doaj.art-c87ab7c3466a49c685dbede2c8b0dab3 |
| institution | Directory Open Access Journal |
| issn | 1687-1499 |
| language | English |
| last_indexed | 2024-12-10T22:52:01Z |
| publishDate | 2022-07-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Wireless Communications and Networking |
| spelling | doaj.art-c87ab7c3466a49c685dbede2c8b0dab32022-12-22T01:30:25ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992022-07-012022111910.1186/s13638-022-02148-wTN-GTN: fault diagnosis of aircraft wiring network over edge computingTian Wang0Qiang Fang1Gongping Liu2Meng Chi3Yuanqi Luo4Jianming Shen5School of Mechanical Engineering, Zhejiang UniversitySchool of Mechanical Engineering, Zhejiang UniversityAVIC Xi’an Aircraft Industry Group Company LtdCollege of Computer Science and Technology, Zhejiang UniversityAVIC Xi’an Aircraft Industry Group Company LtdCompany of AVIC Shenyang Aircraft CorporationAbstract Fault diagnosis of the aircraft wiring network plays an important role in the intelligent manufacture of the aircraft. Many studies focus on the feature-based machine learning methods. However, these methods are improper in handling the data on heterogeneous graphs. Due to the scatter of the valid feature information, the relevant information between the test nodes is ignored by these methods, which leads to the low accuracy fault diagnosis. Taking the advantage of the 5G technology that can remotely process large-scale graph data, this work proposes a fault diagnosis method named “topological network-graph transformer network (TN-GTN).” TN-GTN can improve the fault diagnosis accuracy through feature enhancement and classification, which is based on the topological information of heterogeneous graphs. The graph network is able to learn new graph structures by identifying useful meta-paths and multi-hop connections between unconnected nodes on original graphs. Feature-enhanced test nodes are used to classify the final labels by the artificial neural network. Results of the performed experiment showed that TN-GTN reduced the dependence on domain knowledge and achieved an accurate classification of the fault diagnosis on aircraft wiring network.https://doi.org/10.1186/s13638-022-02148-wEdge computingFault diagnosisAircraft wiring networkFeature enhancementGraph transformer network (GTN) |
| spellingShingle | Tian Wang Qiang Fang Gongping Liu Meng Chi Yuanqi Luo Jianming Shen TN-GTN: fault diagnosis of aircraft wiring network over edge computing EURASIP Journal on Wireless Communications and Networking Edge computing Fault diagnosis Aircraft wiring network Feature enhancement Graph transformer network (GTN) |
| title | TN-GTN: fault diagnosis of aircraft wiring network over edge computing |
| title_full | TN-GTN: fault diagnosis of aircraft wiring network over edge computing |
| title_fullStr | TN-GTN: fault diagnosis of aircraft wiring network over edge computing |
| title_full_unstemmed | TN-GTN: fault diagnosis of aircraft wiring network over edge computing |
| title_short | TN-GTN: fault diagnosis of aircraft wiring network over edge computing |
| title_sort | tn gtn fault diagnosis of aircraft wiring network over edge computing |
| topic | Edge computing Fault diagnosis Aircraft wiring network Feature enhancement Graph transformer network (GTN) |
| url | https://doi.org/10.1186/s13638-022-02148-w |
| work_keys_str_mv | AT tianwang tngtnfaultdiagnosisofaircraftwiringnetworkoveredgecomputing AT qiangfang tngtnfaultdiagnosisofaircraftwiringnetworkoveredgecomputing AT gongpingliu tngtnfaultdiagnosisofaircraftwiringnetworkoveredgecomputing AT mengchi tngtnfaultdiagnosisofaircraftwiringnetworkoveredgecomputing AT yuanqiluo tngtnfaultdiagnosisofaircraftwiringnetworkoveredgecomputing AT jianmingshen tngtnfaultdiagnosisofaircraftwiringnetworkoveredgecomputing |