Home // BIOTECHNO 2022, The Fourteenth International Conference on Bioinformatics, Biocomputational Systems and Biotechnologies // View article

Customized Adaptative Neuro-Fuzzy Approach to pH Control on a Stirred Tank Bioreactor

Authors:
Fernando Agustin Hernandez Gobertti
Carlos Heber Cigliutti Barilari
Andre Luiz Fonseca De Oliveira

Keywords: fuzzy logic, automatic control, pH controller, bioreactor design, optimization engineering

Abstract:
Bioreactors are complex sets of tubes, sensors and actuators embodied in recipients of different shapes and sizes, used thoroughly in biotechnical and chemical investigative and commercial environments for hours on end. Stirred tank bioreactors are widely used and available globally, whose design is intentioned for in-batch and continuous operations. They serve as closed controlled systems for specific organic compounds reaction examination when treated with agitation changes and temperature shifts, as well as oxygen saturation and viscosity variation for both aerobic and anaerobic processes. In particular, the rapidness and magnitude at which a substance changes its associated pH affect its solubility and molecular structure, possibly reaching its denaturalization. Hence, analyzing and acting upon these systems pH, where several parameters interact with each other, is crucial for avoiding compound stressing and arriving to the desired products in addition to coherent investigation conclusions. The pH level management, commonly done manually by scientists, serves the purpose for applying fuzzy logic principles where historical data, as well as human expertise and experience, can be best utilized in designing the controller sets of inference rules and membership functions. Thus, this paper focuses on experiments design and proven tuned applications with limited microorganisms capacities of adaptative neuro-fuzzy process trained with custom genetic algorithms for automatic pH control in 5 liters stirred tank bioreactors, joined with practical comparisons between other control engineering formulations. While earlier related research focused on simulated reactions and theoretical control, this empirical procedure gives promising results on 10 seconds cycles of sensing and actuating, achieving an average 0.1 pH error margin on stability when utilized on an agitation and temperature controlled environment. This study provides scientists with an extendable and configurable procedure so to successfully and efficiently control pH on closed systems using an affordable master-slave micro-controllers architecture.

Pages: 1 to 7

Copyright: Copyright (c) IARIA, 2022

Publication date: May 22, 2022

Published in: conference

ISSN: 2308-4383

ISBN: 978-1-61208-971-3

Location: Venice, Italy

Dates: from May 22, 2022 to May 26, 2022