@Article{1450-53392600020L,
  author                  = {Liu, Xiaojie and Geng, Yanping and Li, Hongwei and Zhang, Yujie and Duan, Yifan and Li, Xin},
  journal                 = {Journal of Mining and Metallurgy, Section B: Metallurgy},
  title                   = {Knowledge graph for blast furnace condition prediction and root cause tracing},
  year                    = {2026},
  volume                  = {62},
  number                  = {2},
  pages                   = {267-285},
  doi                     = {10.2298/JMMB260511020L},
  note                    = {Correspondence Address: Hongwei Li; Xin Li; North China University of Science and Technology, School of Metallurgy and Energy, Tangshan, China; North China University of Science and Technology, School of Science, Tangshan, China; North China University of Science and Technology, School of Civil Engineering, Tangshan, China; email: lhwcoarising@ncst.edu.cn; lxxx@ncst.edu.cn},
  url                     = {https://doi.org/10.2298/JMMB260511020L},
  affiliation             = {a North China University of Science and Technology, School of Metallurgy and Energy, Tangshan, China; b North China University of Science and Technology, School of Science, Tangshan, China; c North China University of Science and Technology, School of Civil Engineering, Tangshan, China;},
  abstract                = {Accurate prediction of blast furnace conditions and traceability of anomaly root causes are crucial for ensuring production stability and reducing energy consumption. However, existing methods struggle to simultaneously capture temporal dynamic evolution and causal structural relationships among parameters. To address this issue, this paper proposes a method for furnace condition prediction and root cause tracing that integrates a knowledge graph with dual-encoder deep learning. First, based on process mechanisms and expert rules, a knowledge graph containing anomaly types and their causal relationships is constructed, and historical cases are stored. Second, a temporal-graph dual encoder is designed: the temporal encoder employs a temporal convolutional network to extract dynamic evolution features from data, while the graph encoder uses a graph attention network to learn structural dependencies from the knowledge graph; a gated fusion mechanism then enables accurate prediction of six types of furnace conditions. Finally, a root cause tracing algorithm based on causal paths and case similarity is proposed, which leverages causal associations in the knowledge graph and historical cases to generate interpretable root cause chains. Experimental results show that the proposed method achieves an overall prediction accuracy of over 90% and an overall tracing accuracy of 91.7%, and that the generated paths are highly consistent with process mechanisms.},
  keywords                = {Blast furnace condition prediction; Knowledge graph; Root cause tracing; Fault diagnosis; Deep learning; Ironmaking},
  correspondence_address1 = {Hongwei Li; Xin Li; North China University of Science and Technology, School of Metallurgy and Energy, Tangshan, China; North China University of Science and Technology, School of Science, Tangshan, China; North China University of Science and Technology, School of Civil Engineering, Tangshan, China; email: lhwcoarising@ncst.edu.cn; lxxx@ncst.edu.cn},
  publisher               = {Technical Faculty in Bor},
  issn                    = {1450-5339},
  language                = {English},
  abbrev_source_title     = {J. Min. Metall. Sect. B Metall.},
  document_type           = {Article},
}