EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DML–LLM Hybrid Architecture for Fault Detection and Diagnosis in Sensor-Rich Industrial Systems

Yu-Shu Hu iD, Saman Marandi iD, Mohammad Modarres iD

Sensors · 23.03.2026 · 26 (6) · 2008

DOI: 10.3390/s26062008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.03.2026. Verfasst von Yu-Shu Hu und 2 weiteren Autor:innen. Beteiligte Einrichtung: DML Inc., Chubei, Hsinchu 30274, Taiwan. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

causal inferencediagnosticsdynamic master logic (DML)fault detection and diagnosis (FDD)large language modelsneuro-symbolic hybridreasoningsoft thresholdsstate-aware orchestrationtemporal fuzzy logic

Autor:innen und Institutionen

  • DML Inc., Chubei, Hsinchu 30274, Taiwan.
  • Center for Risk and Reliability, A.J. Clark School of Engineering, University of Maryland, College Park, MD 20742, USA.

ORCID-Profile: Yu-Shu Hu, Saman Marandi, Mohammad Modarres

Zitieren

APA

Hu, Y. S., Marandi, S., & Modarres, M. (2026). DML–LLM Hybrid Architecture for Fault Detection and Diagnosis in Sensor-Rich Industrial Systems. Sensors, 26(6), 2008. https://doi.org/10.3390/s26062008

Vancouver

Hu YS, Marandi S, Modarres M. DML–LLM Hybrid Architecture for Fault Detection and Diagnosis in Sensor-Rich Industrial Systems. Sensors. 2026;26(6):2008. doi:10.3390/s26062008

BibTeX
@article{Hu2026,
  author = {Hu, Yu-Shu and Marandi, Saman and Modarres, Mohammad},
  title = {DML–LLM Hybrid Architecture for Fault Detection and Diagnosis in Sensor-Rich Industrial Systems},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {2008},
  doi = {10.3390/s26062008}
}
Kostenlos starten →