Assessing the Mass Transfer Coefficient in Jet Bioreactors with Classical Computer Vision Methods and Neural Networks Algorithms

GND
1283246023
ORCID
0000-0002-7766-7351
Affiliation
Otto-Schott-Institut für Materialforschung, Friedrich-Schiller University of Jena, 07743 Jena, Germany
Nizovtseva, Irina;
ORCID
0000-0003-1199-4314
Affiliation
Moscow Institute of Physics and Technology, 141701 Moscow, Russia
Palmin, Vladimir;
ORCID
0000-0003-1650-4177
Affiliation
Soft Matter and Physics of Fluids Centre, Bauman Moscow State Technical University, 105005 Moscow, Russia
Simkin, Ivan;
ORCID
0000-0001-6397-488X
Affiliation
Laboratory of Multiphase Physical and Biological Media Modeling, Ural Federal University, 620000 Ekaterinburg, Russia
Starodumov, Ilya;
ORCID
0000-0003-3455-5381
Affiliation
Laboratory of Multiphase Physical and Biological Media Modeling, Ural Federal University, 620000 Ekaterinburg, Russia
Mikushin, Pavel;
ORCID
0000-0001-9075-0080
Affiliation
Moscow Institute of Physics and Technology, 141701 Moscow, Russia
Nozik, Alexander;
ORCID
0000-0001-9099-4587
Affiliation
Moscow Institute of Physics and Technology, 141701 Moscow, Russia
Hamitov, Timur;
ORCID
0000-0002-1128-2942
Affiliation
Department of High Performance Computing, ITMO University, 197101 Saint Petersburg, Russia
Ivanov, Sergey;
ORCID
0000-0003-1217-9397
Affiliation
Laboratory of Multiphase Physical and Biological Media Modeling, Ural Federal University, 620000 Ekaterinburg, Russia
Vikharev, Sergey;
ORCID
0000-0002-0172-2625
Affiliation
Department of Educational Programmes, Institute of Education Faculty, HSE University, 101000 Moscow, Russia
Zinovev, Alexei;
ORCID
0000-0002-3699-3193
Affiliation
Laboratory of Multiphase Physical and Biological Media Modeling, Ural Federal University, 620000 Ekaterinburg, Russia
Svitich, Vladislav;
ORCID
0000-0003-0025-9031
Affiliation
Soft Matter and Physics of Fluids Centre, Bauman Moscow State Technical University, 105005 Moscow, Russia
Mogilev, Matvey;
ORCID
0000-0001-5408-4498
Affiliation
Laboratory of Multiphase Physical and Biological Media Modeling, Ural Federal University, 620000 Ekaterinburg, Russia
Nikishina, Margarita;
ORCID
0000-0002-9929-9502
Affiliation
Department of High Performance Computing, ITMO University, 197101 Saint Petersburg, Russia
Kraev, Simon;
ORCID
0000-0001-6821-904X
Affiliation
Soft Matter and Physics of Fluids Centre, Bauman Moscow State Technical University, 105005 Moscow, Russia
Yurchenko, Stanislav;
ORCID
0000-0002-0897-5932
Affiliation
Laboratory of Multiphase Physical and Biological Media Modeling, Ural Federal University, 620000 Ekaterinburg, Russia
Mityashin, Timofey;
ORCID
0000-0002-4822-6055
Affiliation
NPO Biosintez Ltd., 109390 Moscow, Russia
Chernushkin, Dmitrii;
ORCID
0000-0002-9612-8601
Affiliation
Department of High Performance Computing, ITMO University, 197101 Saint Petersburg, Russia
Kalyuzhnaya, Anna;
ORCID
0000-0003-4434-2873
Affiliation
Laboratory of Multiphase Physical and Biological Media Modeling, Ural Federal University, 620000 Ekaterinburg, Russia
Blyakhman, Felix

Development of energy-efficient and high-performance bioreactors requires progress in methods for assessing the key parameters of the biosynthesis process. With a wide variety of approaches and methods for determining the phase contact area in gas–liquid flows, the question of obtaining its accurate quantitative estimation remains open. Particularly challenging are the issues of getting information about the mass transfer coefficients instantly, as well as the development of predictive capabilities for the implementation of effective flow control in continuous fermentation both on the laboratory and industrial scales. Motivated by the opportunity to explore the possibility of applying classical and non-classical computer vision methods to the results of high-precision video records of bubble flows obtained during the experiment in the bioreactor vessel, we obtained a number of results presented in the paper. Characteristics of the bioreactor’s bubble flow were estimated first by classical computer vision (CCV) methods including an elliptic regression approach for single bubble boundaries selection and clustering, image transformation through a set of filters and developing an algorithm for separation of the overlapping bubbles. The application of the developed method for the entire video filming makes it possible to obtain parameter distributions and set dropout thresholds in order to obtain better estimates due to averaging. The developed CCV methodology was also tested and verified on a collected and labeled manual dataset. An onwards deep neural network (NN) approach was also applied, for instance the segmentation task, and has demonstrated certain advantages in terms of high segmentation resolution, while the classical one tends to be more speedy. Thus, in the current manuscript both advantages and disadvantages of the classical computer vision method (CCV) and neural network approach (NN) are discussed based on evaluation of bubbles’ number and their area defined. An approach to mass transfer coefficient estimation methodology in virtue of obtained results is also represented.

Cite

Citation style:
Could not load citation form.

Rights

License Holder: © 2023 by the authors.

Use and reproduction: