Processes including particles, like fermentation, flocculation, precipitation, crystallization etc. are some of the most frequently used operations in the bio-based industries. These processes are today typically monitored using sensors that measure on liquid and gas phase properties. The lack of knowledge of the particles itself has made it difficult to monitor and control these processes. Recent advances in continuous in-situ sensors, that can measure a range of particle properties using advanced image analysis, have now however opened up for implementing novel monitoring and modeling strategies, providing more process insights at a relatively low cost. In this work, an automated platform for particle microscopy imaging is proposed. Furthermore, a model based deep learning framework for predictive monitoring of particles in various bioprocesses using images is suggested, and demonstrated on a case study for crystallization of lactose.
|Conference||29th European Symposium on Computer Aided Process Engineering |
|Period||16/06/2019 → 19/06/2019|
|Series||Computer Aided Chemical Engineering|
- Bioprocess monitoring
- Advanced image analysis
- Modeling framework