State and parameter estimation based on a nonlinear filter applied to an industrial process control of ethanol production

Abstract

Most advanced computer-aided control applications rely on good dynamics process models. The performance of the control system depends on the accuracy of the model used. Typically, such models are developed by conducting off-line identification experiments on the process. These experiments for identification often result in input-output data with small output signal-to-noise ratio, and using these data results in inaccurate model parameter estimates [1]. In this work, a multivariable adaptive self-tuning controller (STC) was developed for a biotechnological process application. Due to the difficulties involving the measurements or the excessive amount of variables normally found in industrial process, it is proposed to develop "soft-sensors" which are based fundamentally on artificial neural networks (ANN). A second approach proposed was set in hybrid models, results of the association of deterministic models (which incorporates the available prior knowledge about the process being modeled) with artificial neural networks. In this case, kinetic parameters - which are very hard to be accurately determined in real time industrial plants operation - were obtained using ANN predictions. These methods are especially suitable for the identification of time-varying and nonlinear models. This advanced control strategy was applied to a fermentation process to produce ethyl alcohol (ethanol) in industrial scale. The reaction rate considered for substratum consumption, cells and ethanol productions are validated with industrial data for typical operating conditions. The results obtained show that the proposed procedure in this work has a great potential for application

Application of Hybrid Neural Models to Bioprocesses: A Systematic Literature Review

“…In the early years, hybrid models were mainly applied to traditional microbial processes such as Baker's yeast [22,23] , antibiotics production [24] and beer/bioethanol production [25][26][27][28][29] . Preusting et al (1996) addressed the historical penicillin process at the production scale [24] .…”

“…The model consisted of a 3-layers FFNN (describing the kinetic rates) connected in series with macroscopic mass-balance equations. Meleiro et al (2000) applied a hybrid model for dynamic modeling and control of an industrialscale S. cerevisiae fermentation process for bioethanol production. They combined a 3-layers FFNN with macroscopic material balances and simple Monod-type kinetics.…”

“…The hybrid model provided online estimations of key process state variables and kinetic parameters based on reliable and easily accessible measurements. It enabled the implementation of efficient automatic control strategies [25] . Recently, hybrid modeling of bioethanol production was revisited by Da Silva Pereira et al (2021) [31] .…”

Application of generalized predictive control to baker's yeast production

“…A simulation study was realized to test the efficiency and feasibility of the related control system. Meleiro and Maciel [7] have reported a multivariable adaptive self-tuning controller developed for a biotechnological process application. This control strategy was applied to a fermentation process to produce ethanol on an industrial scale.…”