Abstract
Conventional modelling, state estimation, multi-step ahead prediction, and control of bioprocesses are often difficult owing to the uncertainties involved. Backpropagation multi-layer neural network models and fuzzy knowledge-based systems were constructed to overcome such problems. Neural networks were programmed in QuickC® and implemented in a personal computer with an 80486/33 MHz processor. Object oriented programming in a Smalltalk/V® environment was employed for the rule-based fuzzy expert systems. Results of multi-step ahead prediction both of the enzyme activity and biomass in a fed-batch glucoamylase fermentation, and of the adaptive estimation of substrate feed rate and biomass in a fed-batch baker’s yeast fermentation were presented as examples. The potential of neural networks in the context of process control and hybrid systems was discussed.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
