Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models

2026-08-12

AI Summary

This work addresses the limited scalability of traditional Dynamic Master Logic (DML) models, which rely on manual expert construction and struggle to handle complex systems. The authors propose a novel automated approach that leverages Retrieval-Augmented Generation (RAG) and large language models to construct hierarchical DML knowledge graphs (KG-DML) end-to-end directly from system technical documentation. This method explicitly establishes traceable logical relationships between functional objectives and structural components. Through multi-level validation and logic gate consistency checks, the approach successfully reconstructs a KG-DML for the low-pressure coolant injection system of a decommissioned boiling water reactor. Repeated experiments yield consistent results, demonstrating the method’s effectiveness in terms of precision, recall, and structural completeness.

Abstract

Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. However, DML construction typically relies on expert interpretation of technical documentation, limiting scalability for complex systems. This study presents a framework for automated construction of DML models from system descriptions and their representation as Knowledge Graphs (KG-DML), using Retrieval-Augmented Generation and Large Language Models as enabling tools. Building on prior work with small-scale systems, the framework extends automated KG-DML construction and evaluation to substantially larger and more complex systems. Model construction proceeds across the DML hierarchy using targeted retrieval while preserving functional dependencies and explicit logical relationships. The resulting KG-DML supports diagnostic reasoning, safety assessment, upward failure propagation, and downward dependency tracing. A multi-level validation methodology evaluates layer-specific precision and recall, logical gate consistency, and overall structural integrity. Application to the Low-Pressure Coolant Injection system of a decommissioned Boiling Water Reactor demonstrates consistent reconstruction across repeated runs. The results show that automated KG-DML construction can transform technical documentation into executable functional models for diagnostic and reliability analysis.

Problem

• Dynamic Master Logic
• Knowledge Graph
• Complex System Diagnostics
• Automated Model Construction
• Technical Documentation

Innovation

• Retrieval-Augmented Generation
• Large Language Models
• Dynamic Master Logic
• Knowledge Graphs
• Automated Model Construction