TY - JOUR
T1 - A Fault Diagnosis-Oriented Data-Driven Embedding Fine-Tuning and Domain-Aware Hybrid Retrieval Method for Intelligent Operation and Maintenance
AU - Li, Xueyi
AU - Li, Gang
AU - Dong, Jiannan
AU - Kong, Yun
AU - Hu, Wenyang
AU - Wang, Tianyang
N1 - Publisher Copyright:
© The Author(s) 2026.
PY - 2026
Y1 - 2026
N2 - To improve the support of engineering knowledge resources for fault diagnosis and intelligent maintenance, this paper proposes a fault diagnosis-oriented data-driven embedding fine-tuning and domain-aware hybrid retrieval method. The proposed framework is intended for industrial fault diagnosis and intelligent operation and maintenance and is instantiated and validated in wind turbine operation and maintenance. Domain-specific training data are constructed to fine-tune the embedding model, enhancing its representation of fault concepts, failure mechanisms, and maintenance knowledge. Query expansion, dense retrieval, sparse retrieval, and domain term matching are then integrated with weighted fusion and cross-encoder re-ranking to obtain relevant and low-redundancy diagnostic contexts. Compared with the general retrieval-augmented generation (RAG) baseline, the proposed method increases Recall@5 by 57.33 percentage points, achieves an MRR of 98%, increases the key-point coverage rate by 4.8 percentage points, reaches a factual support rate of 97.83%, and reduces the hallucination rate to 2.17%. These results demonstrate its effectiveness in improving retrieval accuracy and generation reliability for fault diagnosis and maintenance decision-making in the wind turbine operation and maintenance scenario.
AB - To improve the support of engineering knowledge resources for fault diagnosis and intelligent maintenance, this paper proposes a fault diagnosis-oriented data-driven embedding fine-tuning and domain-aware hybrid retrieval method. The proposed framework is intended for industrial fault diagnosis and intelligent operation and maintenance and is instantiated and validated in wind turbine operation and maintenance. Domain-specific training data are constructed to fine-tune the embedding model, enhancing its representation of fault concepts, failure mechanisms, and maintenance knowledge. Query expansion, dense retrieval, sparse retrieval, and domain term matching are then integrated with weighted fusion and cross-encoder re-ranking to obtain relevant and low-redundancy diagnostic contexts. Compared with the general retrieval-augmented generation (RAG) baseline, the proposed method increases Recall@5 by 57.33 percentage points, achieves an MRR of 98%, increases the key-point coverage rate by 4.8 percentage points, reaches a factual support rate of 97.83%, and reduces the hallucination rate to 2.17%. These results demonstrate its effectiveness in improving retrieval accuracy and generation reliability for fault diagnosis and maintenance decision-making in the wind turbine operation and maintenance scenario.
KW - domain knowledge
KW - fault diagnosis
KW - fine-tuning
KW - hybrid retrieval
KW - intelligent maintenance
UR - https://www.scopus.com/pages/publications/105052463355
U2 - 10.37965/jdmd.2026.1505
DO - 10.37965/jdmd.2026.1505
M3 - Article
AN - SCOPUS:105052463355
SN - 2833-650X
VL - 5
SP - 219
EP - 230
JO - Journal of Dynamics, Monitoring and Diagnostics
JF - Journal of Dynamics, Monitoring and Diagnostics
IS - 3
ER -