Summary
This paper presents a framework for automatically constructing Dynamic Master Logic (DML) models and representing them as knowledge graphs (KG-DML), using retrieval-augmented generation (RAG) and large language models (LLMs) as enabling tools. DML provides a hierarchical framework for representing system behavior by linking functional goals to underlying structural elements, but traditional DML construction relies on expert interpretation of technical documentation, limiting scalability for complex systems. The proposed framework performs construction across DML levels using goal-based retrieval that preserves functional dependencies and explicit logic relationships. The resulting KG-DML models support diagnostic reasoning, safety assessment, upward failure propagation, and downward dependency tracing. A multi-level validation approach evaluates level-specific precision and recall, logic gate consistency, and overall structural integrity. A case study on the low-pressure coolant injection system of a decommissioned boiling water reactor demonstrates consistent reconstruction across repeated runs, showing that automated KG-DML construction can convert technical documents into executable functional models for diagnostic and reliability analysis.
Paper Overview
Field: Machine Learning
Authors: Saman Marandi, Yu-Shu Hu, Mohammad Modarres
Published: 2026-08-13
arXiv: 2508.03416
Summary
Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional goals to underlying structural elements. However, DML construction typically depends on experts interpreting technical documentation, which limits scalability for complex systems.
This study proposes a framework for automatically constructing DML models from system descriptions and representing them as knowledge graphs (KG-DML), using retrieval-augmented generation (RAG) 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 larger and more complex systems.
Model construction is performed across DML levels, using goal-based retrieval while preserving functional dependencies and explicit logic relationships. The generated KG-DML supports:
- Diagnostic reasoning
- Safety assessment
- Upward failure propagation
- Downward dependency tracing
A multi-level validation approach evaluates level-specific precision and recall, logic gate consistency, and overall structural integrity.
Case Study
Application to the low-pressure coolant injection (LPCI) system of a decommissioned boiling water reactor demonstrates consistent reconstruction across repeated runs. The results indicate that automated KG-DML construction can transform technical documentation into executable functional models suitable for diagnostic and reliability analysis.
---
*Auto-collected on 2026-08-14*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178633456