Session: 15-13

Paper Number: 146582

146582 - A Text Intelligence-Based Approach for Automatic Generation of Fault Trees in Nuclear Power Plants 

Abstract: 

Fault Tree Analysis (FTA) is an indispensable tool in high-stakes industries like nuclear power for conducting thorough risk assessments. However, the development of fault trees for Nuclear Power Plants (NPPs) is often marred by the necessity of interdisciplinary and intricate knowledge, posing a significant hurdle for non-experts. This necessity for specialized knowledge limits the wider adoption of FTA across various sectors. In response to these challenges, this study introduces the Nuclear Large Language Model Fault Tree Generator (NuLLM-FTG), an innovative solution aims at streamlining and augmenting the FTA process. Central to our approach is the implementation of large language models (LLMs) supervised fine-tuning (SFT) techniques. Specifically, we have developed a uniquely textual data structure, meticulously crafted to encapsulate the distinct characteristics of fault trees. To enhance the precision of our methodology, a comprehensive dataset containing several thousand examples is constructed for SFT. NuLLM-FTG’s performance is subject to a thorough evaluation. This process involved unraveling the "black box" nature of the model, allowing for an in-depth examination of performance enhancements, particularly in terms of horizontal conversational pattern alignment and vertical fault tree knowledge evolution. The practicality and effectiveness of NuLLM-FTG are corroborated through online experiments involving real operators, coupled with evaluations conducted by domain experts. Additionally, the applicability of our method in real-world scenarios is demonstrated through its integration with the Risk Spectrum (Version 14.0), thereby confirming its effectiveness and robustness. Crucially, our findings indicate that the finely-tuned NuLLM-FTG attains a level of performance comparable to experienced fault tree professionals across various metrics, including professionalism, completeness, and satisfaction. Notably, under specific conditions, our model outperformed GPT-4, and the utilization of an English-language corpus within our model proved to be more effective. Ultimately, our proposed method facilitates novices’ involvement in FTA.

In conclusion, the seamless integration of Risk Spectrum with our text intelligence-based methodology provides a comprehensive and precise risk assessment framework. Our method is a significant leap forward in the field, empowering a broader range of professionals, including those with limited specialized knowledge, to efficiently create detailed fault trees. This comprehensive approach, combining the power of text intelligence with practical software tools, represents a paradigm shift in risk assessment methodologies. It paves the way for more accessible, accurate, and efficient safety evaluations. This capability is not confined to the nuclear power industry but is applicable across multiple sectors, broadening the scope of FTA. The application of our approach in nuclear power plants is especially promising, as it has the potential to significantly uplift safety protocols. This advancement could lead to substantial improvements in accident prevention and system reliability, underscoring the transformative impact of our research.

Presenting Author: Xingyu Xiao Tsinghua university

Presenting Author Biography: https://scholar.google.com/citations?user=VhZtXT8AAAAJ&hl=zh-CN

Authors:

Xingyu Xiao Tsinghua university
Songlin Liu Peking University
Zhiyong Zuo Univeristy of Science and Technology Beijing
Peng Chen University of Chinese Academy of Sciences
Ben Qi Tsinghua University
Jingang Liang Tsinghua University
Jiejuan Tong Tsinghua University