Yu-Shu Hu

Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. Unlike event-based approaches such as Fault Tree Analysis, DML captures system objectives, functional dependencies, and unanticipated failure scenarios within a unified functional hierarchy. 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), leveraging Retrieval-Augmented Generation and Large Language Models as the enabling tools. Building upon prior work on small-scale systems, the present work introduces automated construction and evaluation of KG-DML models, extending the paradigm to substantially larger and more complex system. The proposed approach performs model construction across the hierarchy using targeted retrieval, preserving hierarchical dependencies and explicit logical relationships. The resulting KG-DML supports diagnostic reasoning, safety assessment, and graph-based analysis through upward failure propagation and downward dependency tracing. The framework is evaluated through a multi-level validation methodology that combines layer-specific precision and recall, logical gate consistency analysis, and an aggregate integrity metric capturing both element-level accuracy and system-level structural completeness. Application to the Low-Pressure Coolant Injection system of a decommissioned Boiling Water Reactor demonstrates consistent reconstruction across repeated runs and highlights factors influencing model stability. The results show that automated KG-DML construction can transform technical documentation into executable functional models for diagnostic and reliability analysis.

Fault Detection and Diagnosis (FDD) in complex industrial systems requires methods that can handle uncertain operating conditions, soft thresholds, evolving sensor behavior, and increasing volumes of heterogeneous data. Traditional model-based or rule-driven approaches offer interpretability but lack adaptability, while purely data-driven and Large Language Model (LLM)-based methods often struggle with consistency, traceability, and causal grounding. Dynamic Master Logic (DML) provides a causal and temporal reasoning structure with fuzzy rules that capture gradual drift, soft limits, and asynchronous sensor signals while preserving traceability and deterministic evidence propagation. Building on this foundation, this paper presents a DML–LLM hybrid architecture that integrates targeted LLM inference to interpret unstructured information such as logs, notes, or retrieved documents under controlled prompts that maintain domain constraints. The combined system integrates Bayesian updating, deterministic routing, and semantic interpretation into a unified FDD pipeline. In a semiconductor manufacturing case study, the proposed framework reduced time to detection (TTD) from 7.4 h to 1.2 h and improved the F1 score from 0.59 to 0.83 when compared with conventional Statistical Process Control (SPC) and Fault Detection and Classification (FDC) workflows. Provenance completeness increased from 18% to 96%, while engineer triage time was reduced from 72 min to 18 min per event. These results demonstrate that the hybrid framework provides a scalable and explainable approach to anomaly detection and fault diagnosis in sensor-rich industrial environments.

This paper presents a hybrid diagnostic framework that integrates Knowledge Graphs (KGs) with Large Language Models (LLMs) to support fault diagnosis in complex, high-reliability systems such as nuclear power plants. The framework is based on the Dynamic Master Logic (DML) model, which organizes system functions, components, and dependencies into a hierarchical KG for logic-based reasoning. LLMs act as high-level facilitators by automating the extraction of DML logic from unstructured technical documentation, linking functional models with language-based reasoning, and interpreting user queries in natural language. For diagnostic queries, the LLM agent selects and invokes predefined tools that perform upward or downward propagation in the KG using DML logic, while explanatory queries retrieve and contextualize relevant KG segments to generate user-friendly interpretations. This ensures that reasoning remains transparent and grounded in the system structure. This approach reduces the manual effort needed to construct functional models and enables natural language queries to deliver diagnostic insights. In a case study on an auxiliary feedwater system used in the nuclear pressurized water reactors, the framework achieved over 90 percent accuracy in model element extraction and consistently interpreted both diagnostic and explanatory queries. The results validate the effectiveness of LLMs in automating model construction and delivering explainable AI-assisted health monitoring.