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

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Saman Marandi, Yu-Shu Hu, Mohammad Modarres
• Venue: arXiv: cs.AI
• Published: 2026-08-12
• Collected: 2026-08-13
• URL: http://arxiv.org/abs/2608.12304v1
• PDF: https://arxiv.org/pdf/2608.12304v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The study introduces a framework to automate the construction of Dynamic Master Logic (DML) models for complex systems using Retrieval-Augmented Generation and Large Language Models. These models, represented as Knowledge Graphs (KG-DML), help in diagnostic reasoning, safety assessment, upward failure propagation, and downward dependency tracing.

What the Document Says

• Dynamic Master Logic (DML) is a framework for representing system behavior.
• Construction of DML models relies on expert interpretation of technical documentation.
• The study presents a framework for automated construction of DML models from system descriptions and their representation as Knowledge Graphs (KG-DML).
• Retrieval-Augmented Generation and Large Language Models are used in the framework.
• The framework extends automated KG-DML construction to 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 is used to evaluate layer-specific precision and recall, logical gate consistency, and overall structural integrity.
• Application of the framework to a decommissioned Boiling Water Reactor's Low-Pressure Coolant Injection system shows consistent reconstruction across repeated runs.
• The results indicate that automated KG-DML construction can transform technical documentation into executable functional models for diagnostic and reliability analysis.

Key Concepts Mentioned

• Dynamic Master Logic (DML)
• Knowledge Graphs
• Retrieval-Augmented Generation
• Large Language Models
• system diagnostics
• complex systems
• technical documentation

Claims Made by the Document

• The framework can construct DML models automatically for larger and more complex systems.
• Automated KG-DML construction can transform technical documentation into executable functional models.

Evidence Used

• The study presents a framework for automated construction of DML models
• Results from the application to a decommissioned Boiling Water Reactor's Low-Pressure Coolant Injection system

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.