Automated construction of system logic models using LLMs and knowledge graphs

Researchers have developed a method to automatically construct Dynamic Master Logic (DML) models, representing system behavior as knowledge graphs (KG-DML). This approach utilizes retrieval-augmented generation and large language models to process technical documentation, overcoming the limitations of manual construction for complex systems. The resulting KG-DML models facilitate diagnostic reasoning, safety assessments, and dependency tracing. A validation methodology was employed, and the framework was successfully applied to reconstruct the Low-Pressure Coolant Injection system of a Boiling Water Reactor. AI

IMPACT Automates the creation of complex system diagnostic models, potentially improving safety and reliability analysis in critical infrastructure.

RANK_REASON Academic paper detailing a novel methodology for constructing system logic models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• boiling water reactor
• Dynamic Master Logic
• KG-DML
• knowledge graph
• large-language models
• Low-Pressure Coolant Injection
• retrieval-augmented generation

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →