Loading...

Model Predictive Control of a Fed-Batch Bio-ethanol Fermenter Based on Hybrid Neural Networks

Yazdani, Saman | 2023

26 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56778 (06)
  4. University: Sharif University of Technology
  5. Department: Chemical and Petroleum Engineering
  6. Advisor(s): Pishvaie, Mahmoud Reza
  7. Abstract:
  8. Dynamic modeling and process control, especially the equipment of bioreactors and fermenters, have always faced many challenges due to the complexity and high uncertainty of the kinetics of environmental reactions. Among these, semi-continuous fermentation for bioethanol production is one of the important technologies in biochemical industries. The problem of modeling as well as controlling the use of the main discontinuous and semi-continuous methods of ethanol production is the lack of uniform state conditions and the possibility of aerobic and non-aerobic multiplication conditions in two ways. The main goal of this research is to obtain a new method in modeling bioethanol fermentation and use hybrid neural network as a new method for ease of use that can be used in different modeling and replace the classical modeling methods in this field. From a practical and industrial point of view, this type of modern networks can be used as an estimator of unmeasurable states (software sensor) and used in the structure of predictive controls with state feedback formulation. During the research, after checking and validating the project model, the values of project rates were obtained using laboratory data, and then neural networks based on laboratory data were designed to predict the behavior of growth rates. The neural networks with only one hidden layer with the lowest and most optimal number of neurons have been designed in order to be able to compete with the number of constants of growth rate formulas. After modeling using neural networks, the amount of bioethanol production has been maximized with model predictive control strategy.
  9. Keywords:
  10. Dynamic Modeling ; Hybrid Neural Network ; Bioethanol ; Bioreactor ; Predictive Controller ; Fermenters

 Digital Object List

 Bookmark