Softsensing systems for the evaluation of key parameters in yeast management, beer maturation and cell cultivation

In nearly every biotechnological process, it is crucial whether the cells used are alive or dead (viability) and how functional (vitality) they are.  Fluctuations in these parameters can negatively impact both the process and the resulting product. Therefore, real-time measurement of these key parameters is essential for improving biotechnological processes. This can shorten process times, improve a process’s productivity and yield, enhance product quality, and conserve resources.

Despite the process industry’s efforts to measure critical process parameters inline—and thus in real time—this has not yet been sufficiently achieved for bioprocesses. The problem is that these parameters are often determined only by offline methods, and the resulting time lag and low data frequency make it difficult to respond optimally at an early stage. As part of the project, soft sensing (the combination of sensor data and models) will therefore be investigated for the indirect estimation of these physiological variables.

The CellSENSING project focuses on the following bioprocesses: i) yeast management for beer production, with the key parameters of yeast viability and vitality, ii) beer maturation, with metabolic byproducts such as diacetyl, iii) the cultivation of mammalian cells as a step in biopharmaceutical production, with live cell density and viability.

First, hardware sensors will be implemented into the processes to provide valid information on the concentration, viability, and vitality of yeast cells; on key metabolites of the beer brewing process, such as diacetyl; and on the live cell density and viability of CHO cells. Through sensor data fusion, data processing, mathematical modeling, and machine learning methods, this initially partially encoded information is to be converted into concrete quantitative information about the key parameters. A comparison of various methods is intended to enable the development of robust soft-sensing systems for the precise and accurate real-time determination of these key parameters.

The research question thus involves investigating and evaluating which data processing and mathematical modeling methods can be used to fuse data from various hardware sensors in order to enable robust soft sensing.

Funding Agency: Federal Ministry of Research, Technology, and Space (BMFTR)

Funding Program: Research at Universities of Applied Sciences (HAW) – “FH-Kooperativ”

Grant Number: 13FH045KX2

Cooperation partners:
Hamilton Bonaduz AG
, Schneider Electric GmbH
, WiFö der Deutschen Brauwirtschaft e.V.
, ZIEMANN HOLVRIEKA GmbH

Project Duration: April 1, 2024, through December 31, 2027

Project Leader:
Prof. Dr. rer. nat. Miriam Pein-Hackelbusch

Project Participants:
Prof. Dr.-Ing. Björn Frahm
,Prof. Dr.-Ing. Jan Schneider