Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses
We demonstrate that our approach effectively detects and removes anomalies by compensating signal shift value, while remaining computationally efficient and practical for real-time use. It achieves an F1-score of 0.79 with a static threshold of 1.06 pF/cm and a double rolling aggregate transformer using window sizes <i>w1</i> = 1 and <i>w2</i> = 15. This flexible and scalable algorithm has the potential to bridge a crucial gap in process real-time analytics and control.
Authors
- Oskars Grīgs (ORCID: https://orcid.org/0000-0002-1848-4176)
- Vytautas Galvanauskas (ORCID: https://orcid.org/0000-0002-5472-2776)
- Miriam Pein‐Hackelbusch (ORCID: https://orcid.org/0000-0002-7920-0595)
- Emīls Bolmanis (ORCID: https://orcid.org/0000-0002-5087-2179)
- Selina Uhlendorff
Institutions
- Latvian Biomedical Research and Study Centre (LV)
- Kaunas University of Technology (LT)
- Riga Technical University (LV)
- Latvian State Institute of Wood Chemistry (LV)
- Ostwestfalen-Lippe University of Applied Sciences and Arts (DE)
Publication Details
- Journal
- Frontiers in Bioengineering and Biotechnology
- Published
- 2025-07-30
- DOI
- https://doi.org/10.3389/fbioe.2025.1609369
- Primary Topic
- Fault Detection and Control Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- European Commission
- Rīgas Tehniskā Universitāte
- European Regional Development Fund
- State Education Development Agency Republic of Latvia