EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A PI-Dual-STGCN Fault Diagnosis Model Based on the SHAP-LLM Joint Explanation Framework

Zheng Zhao iD, Shuxia Ye iD, Liang Qi iD, Hao Ni, Siyu Fei, Zhe Tong

Sensors · 21.01.2026 · 26 (2) · 723

DOI: 10.3390/s26020723 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.01.2026. Verfasst von Zheng Zhao und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhenjiang Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a PI-Dual-STGCN fault diagnosis model based on a SHAP-LLM joint explanation framework to address issues such as the lack of transparency in the diagnostic process of deep learning models and the weak interpretability of diagnostic results. PI-Dual-STGCN enhances the interpretability of graph data by introducing physical constraints and constructs a dual-graph architecture based on physical topology graphs and signal similarity graphs. The experimental results show that the dual-graph complementary architecture enhances diagnostic accuracy to 99.22%. Second, a general-purpose SHAP-LLM explanation framework is designed: Explainable AI (XAI) technology is used to analyze the decision logic of the diagnostic model and generate visual explanations, establishing a hierarchical knowledge base that includes performance metrics, explanation reliability, and fault experience. Retrieval-Augmented Generation (RAG) technology is innovatively combined to integrate model performance and Shapley Additive Explanations (SHAP) reliability assessment through the main report prompt, while the sub-report prompt enables detailed fault analysis and repair decision generation. Finally, experiments demonstrate that this approach avoids the uncertainty of directly using large models for fault diagnosis: we delegate all fault diagnosis tasks and core explainability tasks to more mature deep learning algorithms and XAI technology and only leverage the powerful textual reasoning capabilities of large models to process pre-quantified, fact-based textual information (e.g., model performance metrics, SHAP explanation results). This method enhances diagnostic transparency through XAI-generated visual and quantitative explanations of model decision logic while reducing the risk of large model hallucinations by restricting large models to reasoning over grounded, fact-based textual content rather than direct fault diagnosis, providing verifiable intelligent decision support for industrial fault diagnosis.

Schlagwörter

Stichwörter der Autor:innen

LLMSHAPexplainabilityexplainable AIfault diagnosis

Autor:innen und Institutionen

  • School of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, China.
  • Jiangsu Shipbuilding and Ocean Engineering Design and Research Institute, Zhenjiang 212100, China.

ORCID-Profile: Zheng Zhao, Shuxia Ye, Liang Qi

Förderung

  • Zhenjiang Science and Technology Program

Zitieren

APA

Zhao, Z., Ye, S., Qi, L., Ni, H., Fei, S., & Tong, Z. (2026). A PI-Dual-STGCN Fault Diagnosis Model Based on the SHAP-LLM Joint Explanation Framework. Sensors, 26(2), 723. https://doi.org/10.3390/s26020723

Vancouver

Zhao Z, Ye S, Qi L, Ni H, Fei S, Tong Z. A PI-Dual-STGCN Fault Diagnosis Model Based on the SHAP-LLM Joint Explanation Framework. Sensors. 2026;26(2):723. doi:10.3390/s26020723

BibTeX
@article{Zhao2026,
  author = {Zhao, Zheng and Ye, Shuxia and Qi, Liang and Ni, Hao and Fei, Siyu and Tong, Zhe},
  title = {A PI-Dual-STGCN Fault Diagnosis Model Based on the SHAP-LLM Joint Explanation Framework},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {723},
  doi = {10.3390/s26020723}
}
Kostenlos starten →