ORIGINAL RESEARCH article
Front. Bioeng. Biotechnol.
Sec. Bioprocess Engineering
Volume 13 - 2025 | doi: 10.3389/fbioe.2025.1609369
Anomaly Detection and Removal Strategies for In-line Permittivity Sensor Signal Used in Bioprocesses
Provisionally accepted
- 1Latvian State Institute of Wood Chemistry (LAS), Riga, Latvia
- 2Latvian Biomedical Research and Study Centre (BMC), Riga, Riga, Latvia
- 3Institute of Biomaterials and Bioengineering, Riga Technical University, Riga, Latvia
- 4Ostwestfalen-Lippe University of Applied Sciences, Lemgo, Germany
- 5Department of Automation, Kaunas University of Technology, Kaunas, Lithuania
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
In-line sensors, which are crucial for real-time (bio-)process monitoring, can suffer from anomalies. These signal spikes and shifts compromise process control. Due to the dynamic and non-stationary nature of bioprocess signals, addressing these issues requires specialized preprocessing. However, existing anomaly detection methods often fail for real-time applications. This study addresses a common yet critical issue in in-situ measurement: developing a robust and easy-to-implement algorithm for real-time anomaly detection and removal in permittivity sensor data, with recombinant Pichia pastoris fermentations serving as a case study. Trivial approaches, such as moving average filtering, do not adequately capture the complexity of the problem. However, our method provides a structured solution through three consecutive steps: 1) Signal preprocessing to reduce noise and eliminate context dependency; 2) Anomaly detection using threshold-based identification; 3) Validation and removal of identified anomalies. 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 w1 = 1 and w2 = 15. This flexible and scalable algorithm has the potential to bridge a crucial gap in process real-time analytics and control.
Keywords: In-situ, permittivity, Dielectric Spectroscopy, Signal preprocessing, Dynamic threshold, Static threshold, anomaly validation, Pichia pastoris
Received: 10 Apr 2025; Accepted: 21 Jul 2025.
Copyright: © 2025 Bolmanis, Uhlendorff, Pein-Hackelbusch, Galvanauskas and Grigs. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Oskars Grigs, Latvian State Institute of Wood Chemistry (LAS), Riga, Latvia
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.