Real-Time Multimodal Defect Detection and MES Feedback on Edge Devices via Bayesian Fusion and Causal Adaptation
IEEE Access · 2025 · 13 · 162226-162237
DOI: 10.1109/access.2025.3610341 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Yong Lin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Conventional single-modality or loosely coupled inspection systems often degrade under partial occlusion, transient sensor dropout, or illumination drift, and their feedback to Manufacturing Execution Systems (MES) can be delayed or non-deterministic. We present D3Lite-MES, a real-time multimodal defect detection framework that i) aligns heterogeneous sensors at both hardware and software levels, ii) fuses them via a Bayesian–Causal Weighted Fusion (BCWF) module, and iii) adapts model parameters on edge devices through a lightweight causal adaptation routine. Deployed on commodity edge hardware, the system sustains line-takt operation and writes verified defect events back to MES with bounded latency. On three production lines covering [product families anonymized], D3Lite-MES attains a mean F1 of 98.2% and mAP@0.5 of 97.6%, reducing false alarms by 98.2% compared with lightweight baselines, at an end-to-end latency of 34 ms and average power of 8.9 W. Ablations show that BCWF contributes + 1.7% F1 under partial observations, while causal adaptation yields + 1.7% under illumination drift. The MES feedback loop decreases manual triage time by 34% and shortens recovery from minor stops by 34%.
Zitieren
APA
Lin, Y., Lin, W., & Lin, Y. (2025). Real-Time Multimodal Defect Detection and MES Feedback on Edge Devices via Bayesian Fusion and Causal Adaptation. IEEE Access, 13, 162226-162237. https://doi.org/10.1109/access.2025.3610341
Vancouver
Lin Y, Lin W, Lin Y. Real-Time Multimodal Defect Detection and MES Feedback on Edge Devices via Bayesian Fusion and Causal Adaptation. IEEE Access. 2025;13:162226-162237. doi:10.1109/access.2025.3610341
BibTeX
@article{Lin2025,
author = {Lin, Yong and Lin, Wendi and Lin, Yadi},
title = {Real-Time Multimodal Defect Detection and MES Feedback on Edge Devices via Bayesian Fusion and Causal Adaptation},
journal = {IEEE Access},
year = {2025},
volume = {13},
pages = {162226--162237},
doi = {10.1109/access.2025.3610341}
}
EUVIMED