Knowledge Acquisition and Reasoning Model for Welding Information Integration Based on CNN and Knowledge Graph
Knowledge acquisition and reasoning are essential in intelligent welding decisions. However, the challenges of unstructured knowledge acquisition and weak knowledge linkage across phases limit the development of welding intelligence, especially in the integration of domain information engineering. T...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/6/1275 |
| _version_ | 1797612287547146240 |
|---|---|
| author | Kainan Guan Yang Sun Guang Yang Xinhua Yang |
| author_facet | Kainan Guan Yang Sun Guang Yang Xinhua Yang |
| author_sort | Kainan Guan |
| collection | DOAJ |
| description | Knowledge acquisition and reasoning are essential in intelligent welding decisions. However, the challenges of unstructured knowledge acquisition and weak knowledge linkage across phases limit the development of welding intelligence, especially in the integration of domain information engineering. This paper proposes a cognitive model combining image recognition and a knowledge graph. A CNN is used as the perception layer to obtain direct information. Automated logic rules based on a knowledge graph are described to enable information integration in the knowledge reasoning domain. In addition, a welding knowledge graph of the bogie frame was constructed based on entity and relationship recognition. CNN models with different network structures were compared and trained under supervised conditions. In the results, the InceptionV1 network obtained a high score (0.758 for the thickness relation, 0.642 for the groove form, 0.704 for the joint type, and 0.835 for the base material form). The proposed model showed positive performance in terms of accuracy, interpretation, knowledge coverage, scalability, and portability compared with several other methods. The model can effectively address the abovementioned limitations and is important for welding manufacturing with engineering information integration. |
| first_indexed | 2024-03-11T06:39:11Z |
| format | Article |
| id | doaj.art-b9ec8bfad90147dca9b0fdb71739845a |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T06:39:11Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-b9ec8bfad90147dca9b0fdb71739845a2023-11-17T10:43:13ZengMDPI AGElectronics2079-92922023-03-01126127510.3390/electronics12061275Knowledge Acquisition and Reasoning Model for Welding Information Integration Based on CNN and Knowledge GraphKainan Guan0Yang Sun1Guang Yang2Xinhua Yang3School of Materials Science and Engineering, Dalian Jiaotong University, Dalian 116028, ChinaSchool of Materials Science and Engineering, Dalian Jiaotong University, Dalian 116028, ChinaSchool of Materials Science and Engineering, Dalian Jiaotong University, Dalian 116028, ChinaSchool of Materials Science and Engineering, Dalian Jiaotong University, Dalian 116028, ChinaKnowledge acquisition and reasoning are essential in intelligent welding decisions. However, the challenges of unstructured knowledge acquisition and weak knowledge linkage across phases limit the development of welding intelligence, especially in the integration of domain information engineering. This paper proposes a cognitive model combining image recognition and a knowledge graph. A CNN is used as the perception layer to obtain direct information. Automated logic rules based on a knowledge graph are described to enable information integration in the knowledge reasoning domain. In addition, a welding knowledge graph of the bogie frame was constructed based on entity and relationship recognition. CNN models with different network structures were compared and trained under supervised conditions. In the results, the InceptionV1 network obtained a high score (0.758 for the thickness relation, 0.642 for the groove form, 0.704 for the joint type, and 0.835 for the base material form). The proposed model showed positive performance in terms of accuracy, interpretation, knowledge coverage, scalability, and portability compared with several other methods. The model can effectively address the abovementioned limitations and is important for welding manufacturing with engineering information integration.https://www.mdpi.com/2079-9292/12/6/1275knowledge acquisitionknowledge reasoningwelding manufacturingCNNknowledge graph |
| spellingShingle | Kainan Guan Yang Sun Guang Yang Xinhua Yang Knowledge Acquisition and Reasoning Model for Welding Information Integration Based on CNN and Knowledge Graph Electronics knowledge acquisition knowledge reasoning welding manufacturing CNN knowledge graph |
| title | Knowledge Acquisition and Reasoning Model for Welding Information Integration Based on CNN and Knowledge Graph |
| title_full | Knowledge Acquisition and Reasoning Model for Welding Information Integration Based on CNN and Knowledge Graph |
| title_fullStr | Knowledge Acquisition and Reasoning Model for Welding Information Integration Based on CNN and Knowledge Graph |
| title_full_unstemmed | Knowledge Acquisition and Reasoning Model for Welding Information Integration Based on CNN and Knowledge Graph |
| title_short | Knowledge Acquisition and Reasoning Model for Welding Information Integration Based on CNN and Knowledge Graph |
| title_sort | knowledge acquisition and reasoning model for welding information integration based on cnn and knowledge graph |
| topic | knowledge acquisition knowledge reasoning welding manufacturing CNN knowledge graph |
| url | https://www.mdpi.com/2079-9292/12/6/1275 |
| work_keys_str_mv | AT kainanguan knowledgeacquisitionandreasoningmodelforweldinginformationintegrationbasedoncnnandknowledgegraph AT yangsun knowledgeacquisitionandreasoningmodelforweldinginformationintegrationbasedoncnnandknowledgegraph AT guangyang knowledgeacquisitionandreasoningmodelforweldinginformationintegrationbasedoncnnandknowledgegraph AT xinhuayang knowledgeacquisitionandreasoningmodelforweldinginformationintegrationbasedoncnnandknowledgegraph |