Методы построения графа знаний и предметно-ориентированной модели LLM для анализа горных ударов на угольных шахтах

Дин, Линьлинь; Чжан, Чжийон; Ху, Юйхан; Чжу, Ченли; Хан, Имин

doi:10.15593/2712-8008/2026.1.5

Методы построения графа знаний и предметно-ориентированной модели LLM для анализа горных ударов на угольных шахтах

Линьлинь Дин, Чжийон Чжан, Юйхан Ху, Ченли Чжу, Имин Хан

Сведения об авторах

Линьлинь Дин
Ляонинский университет, Шэньян, Китайская Народная Республика
Чжийон Чжан
Ляонинский университет, Шэньян, Китайская Народная Республика
Юйхан Ху
Ляонинский университет, Шэньян, Китайская Народная Республика
Ченли Чжу
Ляонинский университет, Шэньян, Китайская Народная Республика
Имин Хан
Ляонинский университет, Шэньян, Китайская Народная Республика

https://doi.org/10.15593/2712-8008/2026.1.5

Горные удары на угольных шахтах представляют собой сложную динамическую катастрофу, вызванную накоплением и внезапным высвобождением энергии во время подземной добычи угля. С непрерывным увеличением глубины и интенсивности добычи угля частота и тяжесть инцидентов, связанных с горными ударами, демонстрируют значительную тенденцию к росту, представляя растущую угрозу безопасности шахт, целостности оборудования и непрерывности добычи. Несмотря на обширные исследования, предотвращение и контроль горных ударов по-прежнему сталкиваются с серьезными проблемами, включая фрагментированные разнородные данные из множества источников, разрозненность знаний в различных системах, ограниченную причинно-следственную связь и трудности в своевременном и точном принятии решений. Эти проблемы препятствуют всестороннему пониманию механизмов катастрофы и снижают эффективность стратегий предотвращения. Для решения этих проблем в данном исследовании предлагается систематическая структура для построения и совершенствования графа знаний о горных ударах на угольных шахтах, поддерживаемого предметно-ориентированной большой языковой моделью. Предлагаемая структура объединяет слияние данных из нескольких источников, семантическое моделирование на основе онтологий и причинно-следственные рассуждения для создания структурированного и машиночитаемого представления знаний, связанных с горными ударами. Одновременно используется предметно-ориентированная LLM для улучшения извлечения знаний, повышения семантики узлов, поддержки интеллектуального ответа на вопросы и обеспечения динамического обновления графа знаний. Сочетая преимущества графов знаний и больших языковых моделей, предлагаемый подход обеспечивает единую платформу для управления знаниями в области горных ударов. Он эффективно повышает доступность, интерпретируемость и аналитическую глубину знаний, связанных с горными ударами, обеспечивая мощную поддержку оценки рисков, прогнозирования катастроф и принятия интеллектуальных решений в управлении безопасностью угольных шахт.

Ключевые слова

горные удары на угольных шахтахграф знанийпредметно-ориентированная большая языковая модельпричинно-следственная связьслияние данных из нескольких источниковуправление знаниямиинтеллектуальная поддержка принятия решений

Construction Methods of Knowledge Graph and Domain-Specific LLM for Coal Mine Rockburst

Coal mine rockburst is a complex dynamic disaster induced by the accumulation and sudden release of energy during underground coal extraction. With the continuous increase in mining depth and intensity, both the frequency and severity of rockburst incidents have shown a significant upward trend, posing growing threats to mine safety, equipment integrity, and production continuity. Despite extensive research, the prevention and control of rockburst still face major challenges, including fragmented multi-source heterogeneous data, knowledge silos across systems, limited causal chain reasoning, and difficulties in timely and accurate decision-making. These issues hinder the comprehensive understanding of disaster mechanisms and reduce the effectiveness of prevention strategies. To address these limitations, this study proposes a systematic framework for constructing and enhancing a coal mine rockburst knowledge graph supported by a domain-specific large language model. The framework integrates multi-source data fusion, ontology-driven semantic modeling, and causal reasoning to establish a structured and machine-understandable representation of rockburst-related knowledge. Meanwhile, the domain-specific large language model is employed to improve knowledge extraction, enhance node semantics, support intelligent question answering, and enable dynamic updating of the knowledge graph. By combining the strengths of knowledge graphs and large language models, the proposed approach provides a unified platform for knowledge governance in the rockburst domain. It effectively improves the accessibility, interpretability, and analytical depth of rockburst-related knowledge, offering strong support for risk assessment, disaster prediction, and intelligent decision-making in coal mine safety management.

Keywords

coal mine rockburstknowledge graphdomain-specific large language modelcausal reasoningmulti-source data fusionknowledge governanceintelligent decision support

Литература

1.Surov on kve technolgies of new oneration knowledge eran / M. Wang, H.F. Wang, B.H. Li [et al.] // Journal of Computer Research and Development. - 2022. - No 50 (Q) - P 1947-1965. DOI: 10.7544/icn100-1230.20210820. Scholar
2.Prores of bire deodata / Y. Ge. T. Ma. T. Pei [et al. // Science Bulletin. - 2022. - No. 67 (17). - P. 1743-1744. DOI: 10.1016/j.scib.2022.07.022. Scholar
3.Huane. Z.W. Review and development trends of coalbed methane exploitation technology in China / Z.W. Huang, G.F. Li, R.Y. Yang // Journal of China Coal Society. - 2022. - No. 47 (9). - P. 3212-3238. Scholar
4.Review of nrdition and control for surface settlement caused by shield tmeline based on machine learning / R.P. Chen, N. Zou, H.N. Wu [et al.] // Journal of Huizhou University of Science and Technology (Natural Science Edition). - 2022. - No. 50 (R) - P 56-65. Scholar
5.Surov of entri relationship extraction based on deep learning / W.J. Zhang, S.Q. Xiao [et al.] // Journal of Software. - 2019. - No. 30 (6). - P. 1793-1818. DOI: 10.13328/icn1. no. 005817. Scholar
6.Yao. P. Summary of research and application of knowledge graphs in risk management field of commercial banks / P. Yao, K.W. Li, Y.F. Zhang // Information System Engineering. - 2020. - No. 5. - P. 121-123. Scholar
7.Summary of research and anlization of knowledge erans in risk management field of commercial banks / J. Yuan, G.Z. Liu, H.T. Liang [et al.] // Computer Engineering and Automation. - 2022. - No. 58 (10). - P. 37-52. Scholar
8.Ontolow-ware nrtinion for knowledge graph identification / J. Pujara, H. Miao, L. Getoor [et al.] // Automated Knowledge Base Construction. - 2013. - No. 4 (1). - P. 26-27. DOI: 10.1145/2509558.2509562. Scholar
9.Li. N. A review of rockburst prediction methods: From empirical to data- driven / N. Li, R. Jimenez, X.T. Feng // Journal of Rock Mechanics and Rock Engineering. - 2021. - No. 54 (9). - P. 4855-4877. Scholar
10.Summary of anlization and prospect analysis of knowledge graphs in marine field / Z.M. Xiong, H.Y. Ma, S. Li [et al.] // Computer Engineering and Applications. - 2022. - No. 58 (31). - P. 15-33. Scholar
11.Thane Y Construetion of a knowledge graph for coal mine safety hazards and its application in question answering / Y. Zhang, Y. Sun // Safety Science. - 2023. - No. 158 - P. 105053. Scholar
12.CN- DBodia2: an extraction and verification framework for enriching Chinese encyclopedia knowledge base / B. Xu, J. Liang, C. Xie [et al.] // Data Intelligence. - 2019. - No. 1 (3). - P. 12. DOI: 10.1162/dint a 00017 Scholar
13.Predictive rockbursts in underreund caverns based on the heuristic method and support vector machine / Y. Xue, C. Bai, D. Qiu [et al.] // Tunnelling and Underground Smaro Technology. - 2020. - No. 98 - P. 1102304. Scholar
14.Dnedia - a crvstallization point for the web of data / C. Bizer, J. Lehmann, G. Kobilarov [et al.] // Web Semantics: Science, Services and Agents on the World Wide Web. - 2009. - No. 7 (3). - P. 154-165. DOI: 10.1016/j.websem.2009.07.002. Scholar
15.Wikidata: a free collaborative knowledge base / D. Vrandec, M. Krotzsch // Communications of the ACM. - 2014. - No. 57 (10). - P. 78-85. DOI: 10.1145/2629489. Scholar
16.Wondrat: a lvial atashas for Fnch / G.A. Miller // Cmmnistions of the ACM. - 1995. - No. 38 (11). - P. 39-41. DOI: 10.1145/219717 2170478. Scholar
17.Wane I. Thane I. I. Mithi- surre data fusion for coal mine safety munitione based on imnrovd H- s- vdence thror // IFFE Arves. - 2022. - No. 10. - P. 12345-12356. Scholar
18.Vaeen a lrse ontology from Wikipedia and Wordnet / K.M. Surhane, G. Kasnevi, G. Weikum // Web Semantics: Science, Services and Agents on the World Wide Web. - 2008. - No. 6 (3). - P. 42-43. DOI: 10.1016/j.websem.2008.06.001. Scholar
19.Fast and transmissible domain knowledge eran construction method / K. Denr, P. Yane, Y.Z. Li [et al.] // Computer Science. - 2022. - No. 49 (S1). - P. 100-108. Scholar
20.Hvbrid attention- based neural networks for rockburst prediction in deen coal mines / H. Pu, Z. Li // Aodied Soft Commutiner. - 2023. - No. 134. - P. 110002. Scholar
21.Research review of knowledge graph and its application in medical domain / M.W. Hon, R.I. Wei [et al.] // Journal of Computer Research and Development. - 2018. - No. 55 (12). - P. 2587-2590. Scholar
22.BILSTM-CRF for ecolocal named entity recognition from the geoscience literature / Q. Qiu, Z. Xie, L. Wu [et al.] // Earth Science Informatics. - 2019. - No. 12 (4). - P. 565-579. DOI: 10.1007/s12145-019-00390-3. Scholar
23.Wane S. Automated extraction of mineral deposit information from text using deep learning / S. Wang, J. Zhang, X. Ma // Computers & Geosciences. - 2022. - No. 158 - P. 104058. Scholar
24.Sone S. Named entity recognition based on conditional random fields / S. Song, N. Zhang, H. Huang // Cluster Computing. - 2017. - No. 1. - P. 1-12. DOI: 10.1007/s10586-017-1146-3. Scholar
25.Fene. X.T. Prediction of rockburst using support vector machine / X.T. Feng, H.B. Zhao // Journal of Northeastern University. - 2002. - No. 1. - P. 57-59. DOI: 10.1088/1755-1315/861/6/062088. Scholar
26.3D metallometric prediction based on machine learning: a case study of the Lapa copper deposit in Sichuan Province / J. Xiang, J.P. Chen, K.Y. Xiao [et al.] // Geologica Bulletin of China. - 2019. - No. 38 (121). - P. 2010-2011. Scholar
27.Thane C. Geolocal entity recognition based on BERT and BILSTM-CRF from Chinese geological survey reports / C. Zhang, M. Wang, G. Liu // Earth Science Informatics. - 2024. - No. 17 (11). - P. 1023-1035. Scholar
28.Denz. C. GeoBERT: A pre-trained language model for the ecoscience domain / C. Denz, L. Jianz, X. Li // Anollied Sciences. - 2022. - No. 12 (9). - P. 4562. Scholar
29.Li. Z.J. Survey of natural language processing pre-training techniques / Z.J. Li, Y. Fan, Y.J. Wu // Computer Science. - 2020. - No. 47 (3). - P. 162-173. Scholar
30.Iin V A inet extraction model of ecolocal entities and relations based on dependency syntactic analysis / Y. Liu, J. Xu, M. Zhao // Journal of Intelligent & Fuzzy Systems. - 2023. - No. 44 (31). - P. 4567-4580. Scholar
31.A critical review of deep learning applications in mining environment / P. Thane H. W. Chen [et al.] // Journal of China Coal Service. - 2020. - No. 45 (10). - P. 3424-3440. Scholar
32.Geological named entity recognition based on BERT and BiGRU-attention CRF model / X.J. Xie, Z. Xie, K. Ma [et al.] // Geologica Bulletin of China. - 2021. - P. 1-13. Scholar
33.A unified MRC framework for named entity recognition / X. Li, J. Fene, Y. Menet [et al.]. - 2019. arXiv:1910.11476. DOI: 10.48550/arXiv.1910.11476. Scholar
34.Coarse-to-fine retraining for named entity recognition / M. Xue, B. Yu, Z. Zhang [et al.]. - 2020. arXiv:2010.08210. DOI: 10.48550/arXiv.2010.08210. Scholar
35.A survey on knowledge graph-based recommender systems / Q. Guo, F. Zhuang, C. Qin [et al.] // IEEE Transactions on Knowledge and Data Engineering. - 2022. - No. 34 (81). - P. 3540-3568. DOI: 10.48550/arXiv.2023.00011. Scholar
36.Li. I. A review of industrial knowledge graph construction and application / L. Li, R. Jiang, X. Wu // Journal of Industrial Information Integration. - 2022. - No. 29. - P. 100381. Scholar
37.Wu. N. Onomutilities and challenges of ChatGPT in the field of mining engineering / N. Wu, Y. Zhang // Metal Mine. - 2023. - No. 52 (5). - P. 1-8. Scholar
38.Annotation of machine learning in rock mechanics and engineering: A review / J. Zhang, X.T. Feng, C. Yang [et al.] // Rock Mechanics and Rock Engineering. - 2021. - No. 54. - P. 381-409. Scholar
39.Fene X T. Rekhurst mechanism and reinforcement method based on energy accumulation and release theory / X.T. Feng, J. Wang // International Journal of Rock Mechanics and Mining Sciences. - 2021. - No. 137. - P. 104503. Scholar
40.Early warning method of real-rock dynamic disaster based on multi-parameter fusion and deep belief network / Y. Zhou, S. Li, Q. Sun [et al.] // Journal of China University of Mine and Technology. - 2022. - No. 51 (31). - P. 555-564. Scholar
41.Adaptive anchor-based attention networks for large-scale sparse bipartite graph embedding / L. Ding, Y. Han, M. Li [et al.] // Knowledge-Based Systems. - 2025. - P. 114242. DOI: 10.1016/j.knosys.2025.114242. Scholar
42.HvIF: An internal-vertical induced embedding for knowledge hypergraph link prediction / L. Ding, Y. Gu, M. Li [et al.] // Information Fusion. - 2025. - P. 103744. DOI: 10.1016/j.inffus.2025.103744. Scholar
43.A comprehensive review of mrf fall prediction in underground coal mines using artificial intelligence techniques / X. Mao, Z. Zhao, J. Zhang [et al.] // Safety Science. - 2020. - No. 127. - P. 104712. Scholar
44.A review of knowledge graph embedding models and their applications / O. Xu, C. Chen, Z. Zhao [et al.] // Neurocomputing. - 2021. - No. 461. - P. 1-20. Scholar
45.Research on question-answer system combining large language models with knowledge graphs / H. Zhang, X. Wang, L. Han [et al.] // Journal of Computer Science and Information. - 2023. - No. 17 (11). - P. 2377-2388. Scholar
46.Knowledge graph completion for industrial fault diagnosis using graph convolutional networks / X. Zhou, J. Zhang, X. Liu [et al.] // Knowledge-Based Systems. - 2020. - No. 205. - P. 106300. Scholar

1.Wang M., Wang H.F., Li B.H. et al. Survey on key technologies of new generation knowledge graph. Journal of Computer Research and Development, 2022, no. 59 (9), pp. 1947-1965. DOI: 10.7544/issn1000-1239.20210829. Scholar
2.Ge Y., Ma T., Pei T. et al. Progress of big geodata. Science Bulletin, 2022, no. 67 (17), pp. 1743-1744. DOI: 10.1016/j.scib.2022.07.022. Scholar
3.Huang Z.W., Li G.F., Yang R.Y. Review and development trends of coalbed methane exploitation technology in China. Journal of China Coal Society, 2022, no. 47 (9), pp. 3212-3238. Scholar
4.Chen R.P., Zou N., Wu H.N. et al. Review of prediction and control for surface settlement caused by shield tunneling based on machine learning. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2022, no. 50 (8), pp. 56-65. Scholar
5.Zhang W.J., Xiao S.Q. et al. Survey of entity relationship extraction based on deep learning. Journal of Software, 2019, no. 30 (6), pp. 1793-1818. DOI: 10.13328/j.cnki.jos.005817. Scholar
6.Yao P., Li K.W., Zhang Y.F. Summary of research and application of knowledge graphs in risk management field of commercial banks. Information System Engineering, 2020, no. 5, pp. 121-123. Scholar
7.Yuan J., Liu G.Z., Liang H.T. et al. Summary of research and application of knowledge graphs in risk management field of commercial banks. Computer Engineering and Applications, 2022, no. 58 (19), pp. 37-52. Scholar
8.Pujara J., Miao H., Getoor L. et al. Ontology-aware partitioning for knowledge graph identification. Automated Knowledge Base Construction, 2013, no. 4 (1), pp. 26-27. DOI: 10.1145/2509558.2509562. Scholar
9.Li N., Jimenez R., Feng X.T. A review of rockburst prediction methods: From empirical to data-driven. Journal of Rock Mechanics and Rock Engineering, 2021, no. 54 (9), pp. 4855-4877. Scholar
10.Xiong Z.M., Ma H.Y., Li S. et al. Summary of application and prospect analysis of knowledge graphs in marine field. Computer Engineering and Applications, 2022, no. 58 (3), pp. 15-33. Scholar
11.Zhang Y., Sun Y. Construction of a knowledge graph for coal mine safety hazards and its application in question answering. Safety Science, 2023, no. 158, 105953. Scholar
12.Xu B., Liang J., Xie C. et al. CN-DBpedia2: an extraction and verification framework for enriching Chinese encyclopedia knowledge base. Data Intelligence, 2019, no. 1 (3), pp. 12. DOI: 10.1162/dint_a_00017. Scholar
13.Xue Y., Bai C., Qiu D. et al. Predicting rockbursts in underground caverns based on the heuristic method and support vector machine. Tunnelling and Underground Space Technology, 2020, no. 98, 102392. Scholar
14.Bizer C., Lehmann J., Kobilarov G. et al. DBpedia - a crystallization point for the web of data. Web Semantics: Science, Services and Agents on the World Wide Web, 2009, no. 7 (3), pp. 154-165. DOI: 10.1016/j.websem.2009.07.002. Scholar
15.Vrandečić D., Krötzsch M. Wikidata: a free collaborative knowledge base. Communications of the ACM, 2014, no. 57 (10), pp. 78-85. DOI: 10.1145/2629489. Scholar
16.Miller G.A. WordNet: a lexical database for English. Communications of the ACM, 1995, no. 38 (11), pp. 39-41. DOI: 10.1145/219717.2170478. Scholar
17.Wang L., Zhang L., Li M. et al. Multi-source data fusion for coal mine safety monitoring based on improved D-S evidence theory. IEEE Access, 2022, no. 10, pp. 12345-12356. Scholar
18.Suchanek F.M., Kasneci G., Weikum G. YAGO: a large ontology from Wikipedia and WordNet. Web Semantics: Science, Services and Agents on the World Wide Web, 2008, no. 6 (3), pp. 42-43. DOI: 10.1016/j.websem.2008.06.001. Scholar
19.Deng K., Yang P., Li Y.Z. et al. Fast and transferable domain knowledge graph construction method. Computer Science, 2022, no. 49 (S1), pp. 100-108. Scholar
20.Pu H., Li Z. Hybrid attention-based neural networks for rockburst prediction in deep coal mines. Applied Soft Computing, 2023, no. 134, 110002. Scholar
21.Hou M.W., Wei R.L. et al. Research review of knowledge graph and its application in medical domain. Journal of Computer Research and Development, 2018, no. 55 (12), pp. 2587-2590. Scholar
22.Qiu Q., Xie Z., Wu L. et al. BiLSTM-CRF for geological named entity recognition from the geoscience literature. Earth Science Informatics, 2019, no. 12 (4), pp. 565-579. DOI: 10.1007/s12145-019-00390-3. Scholar
23.Wang S., Zhang J., Ma X. Automated extraction of mineral deposit information from text using deep learning. Computers & Geosciences, 2022, no. 158, 104958. Scholar
24.Song S., Zhang N., Huang H. Named entity recognition based on conditional random fields. Cluster Computing, 2017, no. 1, pp. 1-12. DOI: 10.1007/s10586-017-1146-3. Scholar
25.Feng X.T., Zhao H.B. Prediction of rockburst using support vector machine. Journal of Northeastern University, 2002, no. 1, pp. 57-59. DOI: 10.1088/1755-1315/861/6/062088. Scholar
26.Xiang J., Chen J.P., Xiao K.Y. et al. 3D metallogenic prediction based on machine learning: a case study of the Lala copper deposit in Sichuan Province. Geological Bulletin of China, 2019, no. 38 (12), pp. 2010-2021. Scholar
27.Zhang C., Wang M., Liu G. Geological entity recognition based on BERT and BiLSTM-CRF from Chinese geological survey reports. Earth Science Informatics, 2024, no. 17 (1), pp. 1023-1035. Scholar
28.Deng C., Jiang L., Li X. GeoBERT: A pre-trained language model for the geoscience domain. Applied Sciences, 2022, no. 12 (9), 4562. Scholar
29.Li Z.J., Fan Y., Wu Y.J. Survey of natural language processing pre-training techniques. Computer Science, 2020, no. 47 (3), pp. 162-173. Scholar
30.Liu Y., Xu J., Zhao M. A joint extraction model of geological entities and relations based on dependency syntactic analysis. Journal of Intelligent & Fuzzy Systems, 2023, no. 44 (3), pp. 4567-4580. Scholar
31.Zhang P., Wu H., Chen R. et al. A critical review of deep learning applications in mining engineering. Journal of China Coal Society, 2020, no. 45 (10), pp. 3424-3440. Scholar
32.Xie X.J., Xie Z., Ma K. et al. Geological named entity recognition based on BERT and BiGRU-attention CRF model. Geological Bulletin of China, 2021, pp. 1-13. Scholar
33.Li X., Feng J., Meng Y. et al. A unified MRC framework for named entity recognition. 2019, arXiv:1910.11476. DOI: 10.48550/arXiv.1910.11476. Scholar
34.Xue M., Yu B., Zhang Z. et al. Coarse-to-fine pre-training for named entity recognition. 2020, arXiv:2010.08210. DOI: 10.48550/arXiv.2010.08210. Scholar
35.Guo Q., Zhuang F., Qin C. et al. A survey on knowledge graph-based recommender systems. IEEE Transactions on Knowledge and Data Engineering, 2022, no. 34 (8), pp. 3540-3568. DOI: 10.48550/arXiv.2003.10011. Scholar
36.Li L., Jiang R., Wu X. A review of industrial knowledge graph construction and application. Journal of Industrial Information Integration, 2022, no. 29, 100381. Scholar
37.Wu N., Zhang Y. Opportunities and challenges of ChatGPT in the field of mining engineering. Metal Mine, 2023, no. 52 (5), pp. 1-8. Scholar
38.Zhang J., Feng X.T., Yang C. et al. Application of machine learning in rock mechanics and engineering: A review. Rock Mechanics and Rock Engineering, 2021, no. 54, pp. 381-490. Scholar
39.Feng X.T., Wang J. Rockburst mechanism and prediction method based on energy accumulation and release theory. International Journal of Rock Mechanics and Mining Sciences, 2021, no. 137, 104593. Scholar
40.Zhou Y., Li S., Sun Q. et al. Early warning method of coal-rock dynamic disaster based on multi-parameter fusion and deep belief network. Journal of China University of Mining and Technology, 2022, no. 51 (3), pp. 555-564. Scholar
41.Ding L., Han Y., Li M. et al. Adaptive anchor-based attention networks for large-scale sparse bipartite graph embedding. Knowledge-Based Systems, 2025, 114242. DOI: 10.1016/j.knosys.2025.114242. Scholar
42.Ding L., Gu Y., Li M. et al. HyIE: An internal-external induced embedding for knowledge hypergraph link prediction. Information Fusion, 2025, 103744. DOI: 10.1016/j.inffus.2025.103744. Scholar
43.Mao X., Zhao Z., Zhang J. et al. A comprehensive review of roof fall prediction in underground coal mines using artificial intelligence techniques. Safety Science, 2020, no. 127, 104712. Scholar
44.Xu Q., Chen C., Zhao Z. et al. A review of knowledge graph embedding models and their applications. Neurocomputing, 2021, no. 461, pp. 1-20. Scholar
45.Zhang H., Wang X., Han L. et al. Research on question-answering system combining large language models with knowledge graphs. Journal of Computer Science and Information, 2023, no. 17 (10), pp. 2377-2388. Scholar
46.Zhang X., Zhang J., Liu X. et al. Knowledge graph completion for industrial fault diagnosis using graph convolutional networks. Knowledge-Based Systems, 2020, no. 205, 106300. Scholar

Другие статьи выпуска

Весь выпуск (Том 26, № 1, 2026)

Скачать PDF

Информация о статье

Опубликована: 12.01.2026
В выпуске: 12.01.2026
Выпуск: Том 26, № 1 (2026)

Методы построения графа знаний и предметно-ориентированной модели LLM для анализа горных ударов на угольных шахтах

Аннотация

Ключевые слова

Construction Methods of Knowledge Graph and Domain-Specific LLM for Coal Mine Rockburst

Keywords

Литература

Другие статьи выпуска

Информация о статье