Multirate Variational Bayesian Decomposed State Space Model for Fault Detection in Multirate Processes
Journal of Chemometrics · 2026-07 · 40 (7)
DOI: 10.1002/cem.70161 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemometrics, online erschienen am 03.07.2026. Verfasst von Ilia Bychkov und 1 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Effective fault detection is essential for modern industry to mitigate equipment damage and safety risks. Due to heterogeneous sampling requirements and practical technical limitations, conventional single‐rate fault detection methods encounter significant performance bottlenecks in practical multirate processes. Furthermore, industrial processes are inherently dynamic, requiring the extraction of both auto‐correlations and cross‐correlations within the data. To tackle these issues, this paper proposes a novel multirate variational bayesian decomposed state space model (Mr‐VBDSSM). It decomposes the latent state into global and sampling‐rate‐specific local components. The former characterize broad system‐wide dynamics, while the latter capture individual fluctuations within specific subsystems. Additionally, local static factors are also designed for each sampling rate to capture steady‐state characteristics. Finally, the effectiveness of the proposed method is verified using the Tennessee Eastman benchmark and a real‐world wastewater treatment process.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Bychkov, I., & Lyu, Y. (2026). Multirate Variational Bayesian Decomposed State Space Model for Fault Detection in Multirate Processes. Journal of Chemometrics, 40(7). https://doi.org/10.1002/cem.70161
Vancouver
Bychkov I, Lyu Y. Multirate Variational Bayesian Decomposed State Space Model for Fault Detection in Multirate Processes. Journal of Chemometrics. 2026;40(7). doi:10.1002/cem.70161
BibTeX
@article{Bychkov2026,
author = {Bychkov, Ilia and Lyu, Yuting},
title = {Multirate Variational Bayesian Decomposed State Space Model for Fault Detection in Multirate Processes},
journal = {Journal of Chemometrics},
year = {2026},
volume = {40},
number = {7},
doi = {10.1002/cem.70161}
}
EUVIMED