EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Fermentation Process Monitoring through Data-Driven Modeling and Synthetic Time Series Generation

Hyun J Kwon iD, Joseph H Shiu, Celina K Yamakawa iD, Elmer C Rivera

Bioengineering · 08.08.2024 · 11 (8) · 803

DOI: 10.3390/bioengineering11080803 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 08.08.2024. Verfasst von Hyun J Kwon und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Engineering, Andrews University, Berrien Springs, MI 49104, USA. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Andrews University, Andrews University Faculty Research Grant, Undergraduate Research Scholarship.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Soft sensors based on deep learning regression models are promising approaches to predict real-time fermentation process quality measurements. However, experimental datasets are generally sparse and may contain outliers or corrupted data. This leads to insufficient model prediction performance. Therefore, datasets with a fully distributed solution space are required that enable effective exploration during model training. In this study, the robustness and predictive capability of the underlying model of a soft sensor was improved by generating synthetic datasets for training. The monitoring of intensified ethanol fermentation is used as a case study. Variational autoencoders were employed to create synthetic datasets, which were then combined with original datasets (experimental) to train neural network regression models. These models were tested on original versus augmented datasets to assess prediction improvements. Using the augmented datasets, the soft sensor predictive capability improved by 34%, and variability was reduced by 82%, based on R2 scores. The proposed method offers significant time and cost savings for dataset generation for the deep learning modeling of ethanol fermentation and can be easily adapted to other fermentation processes. This work contributes to the advancement of soft sensor technology, providing practical solutions for enhancing reliability and robustness in large-scale production.

Schlagwörter

Stichwörter der Autor:innen

deep learningfermentation processesmodelingsoft sensorvariational autoencoders

Autor:innen und Institutionen

  • School of Engineering, Andrews University, Berrien Springs, MI 49104, USA.
  • Department of Computer Science, Andrews University, Berrien Springs, MI 49104, USA.
  • River Stone Biotech ApS, Fruebjergvej 3, 2100 Copenhagen, Denmark.

ORCID-Profile: Hyun J Kwon, Celina K Yamakawa

Förderung

  • Andrews University
  • Andrews University Faculty Research Grant
  • Undergraduate Research Scholarship

Zitieren

APA

Kwon, H. J., Shiu, J. H., Yamakawa, C. K., & Rivera, E. C. (2024). Enhancing Fermentation Process Monitoring through Data-Driven Modeling and Synthetic Time Series Generation. Bioengineering, 11(8), 803. https://doi.org/10.3390/bioengineering11080803

Vancouver

Kwon HJ, Shiu JH, Yamakawa CK, Rivera EC. Enhancing Fermentation Process Monitoring through Data-Driven Modeling and Synthetic Time Series Generation. Bioengineering. 2024;11(8):803. doi:10.3390/bioengineering11080803

BibTeX
@article{Kwon2024,
  author = {Kwon, Hyun J and Shiu, Joseph H and Yamakawa, Celina K and Rivera, Elmer C},
  title = {Enhancing Fermentation Process Monitoring through Data-Driven Modeling and Synthetic Time Series Generation},
  journal = {Bioengineering},
  year = {2024},
  volume = {11},
  number = {8},
  pages = {803},
  doi = {10.3390/bioengineering11080803}
}
Kostenlos starten →