Industrial-scale fermentation

Schematic of the 100,000 L fed-batch penicillin bioreactor and its main inputs/outputs, adapted from Goldrick et al., 2015, Journal of Biotechnology, 193, 70–82, and Metcalfe et al., 2025, “Towards a machine learning operations (MLOps) soft sensor for real-time predictions in industrial-scale fed-batch fermentation”, Computers & Chemical Engineering.

To showcase the capabilities of STAMM on realistic industrial processes, we use a fed-batch fermentation for the production of penicillin by Penicillium chrysogenum as a reference case study. The process is carried out in a 100,000 L production vessel (radius 2.1 m) equipped with multiple online sensors and three Rushton impellers operating at a fixed agitation speed of 100 rpm.

This type of large-scale fed-batch fermentation is representative of real industrial biotechnology operations, where process dynamics are nonlinear, measurements are noisy or delayed, and supervisory control must be combined with advanced monitoring and optimization strategies.

The data originate from the Industrial Penicillin Simulation dataset (IndPenSim), a first-principles benchmark model and open dataset that replicates an industrial penicillin campaign in silico.