Multi-Layered Graph Convolutional Network-Based Industrial Fault Diagnosis with Multiple Relation Characterization Capability
Fault diagnosis of industrial equipments is extremely important for the safety requirements of modern production processes. Lately, deep learning (DL) has been the mainstream fault diagnosis tool due to its powerful representational ability in learning and flexibility. However, most of the existing...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/10/10/873 |
| _version_ | 1797471953420812288 |
|---|---|
| author | Yuanxin Wang Cunhua Pan Jian Zhang Ming Gao Haifeng Zhang Kai Zhong |
| author_facet | Yuanxin Wang Cunhua Pan Jian Zhang Ming Gao Haifeng Zhang Kai Zhong |
| author_sort | Yuanxin Wang |
| collection | DOAJ |
| description | Fault diagnosis of industrial equipments is extremely important for the safety requirements of modern production processes. Lately, deep learning (DL) has been the mainstream fault diagnosis tool due to its powerful representational ability in learning and flexibility. However, most of the existing DL-based methods may suffer from two drawbacks: Firstly, only one metric is used to construct networks, thus multiple kinds of potential relationships between nodes are not explored. Secondly, there are few studies on how to obtain better node embedding by aggregating the features of different neighbors. To compensate for these deficiencies, an advantageous intelligent diagnosis scheme termed AE-MSGCN is proposed, which employs graph convolutional networks (GCNs) on multi-layer networks in an innovative manner. In detail, AE is carried out to extract deep representation features in process measurement and then combined with different metrics (i.e., K-nearest neighbors, cosine similarity, path graph) to construct the multi-layer networks for better multiple interaction characterization among nodes. After that, intra-layer convolutional and inter-layer convolutional methods are adopted for aggregating extensive neighbouring information to enrich the representation of nodes and diagnosis performance. Finally, a benchmark platform and a real-world case both verify that the proposed AE-MSGCN is more effective and practical than the existing state-of-the-art methods. |
| first_indexed | 2024-03-09T19:55:24Z |
| format | Article |
| id | doaj.art-c16903e8bf2844caa70ba7ee251794d0 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-09T19:55:24Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-c16903e8bf2844caa70ba7ee251794d02023-11-24T00:59:13ZengMDPI AGMachines2075-17022022-09-01101087310.3390/machines10100873Multi-Layered Graph Convolutional Network-Based Industrial Fault Diagnosis with Multiple Relation Characterization CapabilityYuanxin Wang0Cunhua Pan1Jian Zhang2Ming Gao3Haifeng Zhang4Kai Zhong5Datang East China Electric Power Test and Research Institute, Hefei 230000, ChinaDatang East China Electric Power Test and Research Institute, Hefei 230000, ChinaDatang East China Electric Power Test and Research Institute, Hefei 230000, ChinaMaanshan Dangtu Power Generation Co., Ltd., Maanshan 243100, ChinaSchool of Mathematical Science, Anhui University, Hefei 230601, ChinaKey Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education, Institutes of Physical Science and Information Technology, Anhui University, Hefei 230601, ChinaFault diagnosis of industrial equipments is extremely important for the safety requirements of modern production processes. Lately, deep learning (DL) has been the mainstream fault diagnosis tool due to its powerful representational ability in learning and flexibility. However, most of the existing DL-based methods may suffer from two drawbacks: Firstly, only one metric is used to construct networks, thus multiple kinds of potential relationships between nodes are not explored. Secondly, there are few studies on how to obtain better node embedding by aggregating the features of different neighbors. To compensate for these deficiencies, an advantageous intelligent diagnosis scheme termed AE-MSGCN is proposed, which employs graph convolutional networks (GCNs) on multi-layer networks in an innovative manner. In detail, AE is carried out to extract deep representation features in process measurement and then combined with different metrics (i.e., K-nearest neighbors, cosine similarity, path graph) to construct the multi-layer networks for better multiple interaction characterization among nodes. After that, intra-layer convolutional and inter-layer convolutional methods are adopted for aggregating extensive neighbouring information to enrich the representation of nodes and diagnosis performance. Finally, a benchmark platform and a real-world case both verify that the proposed AE-MSGCN is more effective and practical than the existing state-of-the-art methods.https://www.mdpi.com/2075-1702/10/10/873intelligent fault diagnosismulti-layer GCNintra-layer and inter-layer convolutionmultiple relation characterization |
| spellingShingle | Yuanxin Wang Cunhua Pan Jian Zhang Ming Gao Haifeng Zhang Kai Zhong Multi-Layered Graph Convolutional Network-Based Industrial Fault Diagnosis with Multiple Relation Characterization Capability Machines intelligent fault diagnosis multi-layer GCN intra-layer and inter-layer convolution multiple relation characterization |
| title | Multi-Layered Graph Convolutional Network-Based Industrial Fault Diagnosis with Multiple Relation Characterization Capability |
| title_full | Multi-Layered Graph Convolutional Network-Based Industrial Fault Diagnosis with Multiple Relation Characterization Capability |
| title_fullStr | Multi-Layered Graph Convolutional Network-Based Industrial Fault Diagnosis with Multiple Relation Characterization Capability |
| title_full_unstemmed | Multi-Layered Graph Convolutional Network-Based Industrial Fault Diagnosis with Multiple Relation Characterization Capability |
| title_short | Multi-Layered Graph Convolutional Network-Based Industrial Fault Diagnosis with Multiple Relation Characterization Capability |
| title_sort | multi layered graph convolutional network based industrial fault diagnosis with multiple relation characterization capability |
| topic | intelligent fault diagnosis multi-layer GCN intra-layer and inter-layer convolution multiple relation characterization |
| url | https://www.mdpi.com/2075-1702/10/10/873 |
| work_keys_str_mv | AT yuanxinwang multilayeredgraphconvolutionalnetworkbasedindustrialfaultdiagnosiswithmultiplerelationcharacterizationcapability AT cunhuapan multilayeredgraphconvolutionalnetworkbasedindustrialfaultdiagnosiswithmultiplerelationcharacterizationcapability AT jianzhang multilayeredgraphconvolutionalnetworkbasedindustrialfaultdiagnosiswithmultiplerelationcharacterizationcapability AT minggao multilayeredgraphconvolutionalnetworkbasedindustrialfaultdiagnosiswithmultiplerelationcharacterizationcapability AT haifengzhang multilayeredgraphconvolutionalnetworkbasedindustrialfaultdiagnosiswithmultiplerelationcharacterizationcapability AT kaizhong multilayeredgraphconvolutionalnetworkbasedindustrialfaultdiagnosiswithmultiplerelationcharacterizationcapability |