Construction of Knowledge Graph for Marine Diesel Engine Faults Based on Deep Learning Methods
As the core equipment in ship power systems, the accurate and real-time diagnosis of ship diesel engine faults directly affects navigation safety and operation efficiency. Existing methods (e.g., expert systems, traditional machine learning) can hardly cope with the complex failure modes and dynamic...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/4/693 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850143994560905216 |
|---|---|
| author | Xiaohe Tian Huibing Gan Yanlin Liu |
| author_facet | Xiaohe Tian Huibing Gan Yanlin Liu |
| author_sort | Xiaohe Tian |
| collection | DOAJ |
| description | As the core equipment in ship power systems, the accurate and real-time diagnosis of ship diesel engine faults directly affects navigation safety and operation efficiency. Existing methods (e.g., expert systems, traditional machine learning) can hardly cope with the complex failure modes and dynamic operation environment due to the problems of relying on artificial features and insufficient generalization ability. In this paper, we propose a BiLSTM-CRF-based knowledge graph construction method for ship diesel engine faults, aiming at integrating multi-source heterogeneous data through deep learning and knowledge graph technology, and mining the deep semantic associations among fault phenomena, causes, and solutions. The research framework covers data acquisition, ontology modeling, and knowledge extraction and storage, and the BiLSTM-CRF model is used to fuse bi-directional contextual features with label transfer probability to achieve high-precision entity recognition and relationship extraction. Finally, a scalable knowledge graph is constructed by Neo4j. Experiments show that the model significantly outperforms baseline methods such as HMM, CRF, and BiLSTM, and the graph visualization clearly presents the fault causality network, which supports knowledge reasoning and decision optimization. For example, “high exhaust temperature” can be related to potential causes such as “turbine failure” and “poor cooling”, and recommended measures can be taken. This method not only improves fault diagnosis accuracy and efficiency but also provides a novel method for intelligent ship health management. |
| format | Article |
| id | doaj-art-51235f7f02e04d968e2bd84332d77a8a |
| institution | OA Journals |
| issn | 2077-1312 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-51235f7f02e04d968e2bd84332d77a8a2025-08-20T02:28:31ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-03-0113469310.3390/jmse13040693Construction of Knowledge Graph for Marine Diesel Engine Faults Based on Deep Learning MethodsXiaohe Tian0Huibing Gan1Yanlin Liu2Marine Engineering College, Dalian Maritime University, Dalian 116026, ChinaMarine Engineering College, Dalian Maritime University, Dalian 116026, ChinaMarine Engineering College, Dalian Maritime University, Dalian 116026, ChinaAs the core equipment in ship power systems, the accurate and real-time diagnosis of ship diesel engine faults directly affects navigation safety and operation efficiency. Existing methods (e.g., expert systems, traditional machine learning) can hardly cope with the complex failure modes and dynamic operation environment due to the problems of relying on artificial features and insufficient generalization ability. In this paper, we propose a BiLSTM-CRF-based knowledge graph construction method for ship diesel engine faults, aiming at integrating multi-source heterogeneous data through deep learning and knowledge graph technology, and mining the deep semantic associations among fault phenomena, causes, and solutions. The research framework covers data acquisition, ontology modeling, and knowledge extraction and storage, and the BiLSTM-CRF model is used to fuse bi-directional contextual features with label transfer probability to achieve high-precision entity recognition and relationship extraction. Finally, a scalable knowledge graph is constructed by Neo4j. Experiments show that the model significantly outperforms baseline methods such as HMM, CRF, and BiLSTM, and the graph visualization clearly presents the fault causality network, which supports knowledge reasoning and decision optimization. For example, “high exhaust temperature” can be related to potential causes such as “turbine failure” and “poor cooling”, and recommended measures can be taken. This method not only improves fault diagnosis accuracy and efficiency but also provides a novel method for intelligent ship health management.https://www.mdpi.com/2077-1312/13/4/693marine diesel enginefault diagnosisknowledge graphBiLSTM-CRF modeldeep learning |
| spellingShingle | Xiaohe Tian Huibing Gan Yanlin Liu Construction of Knowledge Graph for Marine Diesel Engine Faults Based on Deep Learning Methods Journal of Marine Science and Engineering marine diesel engine fault diagnosis knowledge graph BiLSTM-CRF model deep learning |
| title | Construction of Knowledge Graph for Marine Diesel Engine Faults Based on Deep Learning Methods |
| title_full | Construction of Knowledge Graph for Marine Diesel Engine Faults Based on Deep Learning Methods |
| title_fullStr | Construction of Knowledge Graph for Marine Diesel Engine Faults Based on Deep Learning Methods |
| title_full_unstemmed | Construction of Knowledge Graph for Marine Diesel Engine Faults Based on Deep Learning Methods |
| title_short | Construction of Knowledge Graph for Marine Diesel Engine Faults Based on Deep Learning Methods |
| title_sort | construction of knowledge graph for marine diesel engine faults based on deep learning methods |
| topic | marine diesel engine fault diagnosis knowledge graph BiLSTM-CRF model deep learning |
| url | https://www.mdpi.com/2077-1312/13/4/693 |
| work_keys_str_mv | AT xiaohetian constructionofknowledgegraphformarinedieselenginefaultsbasedondeeplearningmethods AT huibinggan constructionofknowledgegraphformarinedieselenginefaultsbasedondeeplearningmethods AT yanlinliu constructionofknowledgegraphformarinedieselenginefaultsbasedondeeplearningmethods |