Physically-informed Bayesian feature optimization for semi-supervised industrial anomaly detection
Measurement Science and Technology · 20.03.2026 · 37 (11) · 116103
DOI: 10.1088/1361-6501/ae4d69 ↗Kurz gefasst
Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 19.03.2026. Verfasst von Jianshe Feng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: Natural Science Foundation of Guangdong Province, China, Natural Science Foundation of Shenzhen Municipality, China.
Abstract (Originalsprache)
In tackling frequent batch anomalies in manufacturing processes, this study introduces a novel semi-supervised in-process monitoring method that enables real-time anomaly detection during production rather than post-process inspection. By integrating physically-informed Bayesian feature optimization with semi-supervised learning, the proposed method captures batch defects under conditions of scarce anomaly samples. First, a Bayesian feature optimization strategy is proposed to extract critical indicators from redundant industrial signals, effectively bridging the gap between domain expertise and data-driven representations. Second, to address the semi-supervised challenge of scarce anomaly samples, an out-of-distribution detection model trained on normal samples is established, combined with conformal calibration to determine robust decision thresholds. The superiority of the proposed method is validated with real-world stamping and injection molding datasets, with ablation studies confirming robustness to hyperparameter variations. The results demonstrate the potential of the proposed method for anomaly monitoring in data-scarce industrial contexts.
Förderung
- Natural Science Foundation of Guangdong Province, China
- Natural Science Foundation of Shenzhen Municipality, China
Zitieren
APA
Feng, J., Zhang, J., Yin, S., Qi, F., & Li, J. (2026). Physically-informed Bayesian feature optimization for semi-supervised industrial anomaly detection. Measurement Science and Technology, 37(11), 116103. https://doi.org/10.1088/1361-6501/ae4d69
Vancouver
Feng J, Zhang J, Yin S, Qi F, Li J. Physically-informed Bayesian feature optimization for semi-supervised industrial anomaly detection. Measurement Science and Technology. 2026;37(11):116103. doi:10.1088/1361-6501/ae4d69
BibTeX
@article{Feng2026,
author = {Feng, Jianshe and Zhang, Jianyu and Yin, Size and Qi, Fanyu and Li, Jiaqi},
title = {Physically-informed Bayesian feature optimization for semi-supervised industrial anomaly detection},
journal = {Measurement Science and Technology},
year = {2026},
volume = {37},
number = {11},
pages = {116103},
doi = {10.1088/1361-6501/ae4d69}
}
EUVIMED