Intelligent predictive maintenance RAG framework for power plants: Enhancing QA with StyleDFS and domain specific instruction tuning

Abstract

Process plants are complex large-scale industrial facilities that convert raw materials or intermediate products into final products, requiring continuous processes with high safety and efficiency standards. In particular, in nuclear process plants, Predictive Maintenance System (PMS) plays a critical role in predicting equipment anomalies and performing preventive maintenance. However, current PMS relies heavily on the experience of a few experts, leading to knowledge loss upon their retirement and difficulty in swift response. Existing off-premise Question-Answering (QA) systems based on Large Language Models (LLM) face issues such as data leakage and challenges in domain-specific tuning. To address these problems, this study proposes an on-premise intelligent PMS framework utilizing a new chunking method, StyleDFS, which effectively reflects the structural information of documents. Additionally, we demonstrate that Instruction tuning using relevant domain-specific data improves LLM performance even under limited data conditions.

BibTeX

@inproceedings{2024-intelligent-predictive-maintenance-rag-framework-power,
  title = {Intelligent predictive maintenance RAG framework for power plants: Enhancing QA with StyleDFS and domain specific instruction tuning},
  author = {Seongtae Hong and Joong Min Shin and Jaehyung Seo and Taemin Lee and Jeongbae Park and Cho Man Young and Byeongho Choi and Heuiseok Lim},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track},
  year = {2024},
  month = {11},
  pages = {805-820},
  abstract = {Process plants are complex large-scale industrial facilities that convert raw materials or intermediate products into final products, requiring continuous processes with high safety and efficiency standards. In particular, in nuclear process plants, Predictive Maintenance System (PMS) plays a critical role in predicting equipment anomalies and performing preventive maintenance. However, current PMS relies heavily on the experience of a few experts, leading to knowledge loss upon their retirement and difficulty in swift response. Existing off-premise Question-Answering (QA) systems based on Large Language Models (LLM) face issues such as data leakage and challenges in domain-specific tuning. To address these problems, this study proposes an on-premise intelligent PMS framework utilizing a new chunking method, StyleDFS, which effectively reflects the structural information of documents. Additionally, we demonstrate that Instruction tuning using relevant domain-specific data improves LLM performance even under limited data conditions.},
  url = {https://aclanthology.org/2024.emnlp-industry.61.pdf}
}