Dorin Şendrescu

Neural networks-based adaptive control for a class of nonlinear bioprocesses

The paper studies the design and analysis of a neural adaptive control strategy for a class of square nonlinear bioprocesses with incompletely known and time-varying dynamics. In fact, an adaptive controller based on a dynamical neural network used as a model of the unknown plant is developed. The neural controller design is achieved by using an input–output feedback linearization technique. The adaptation laws of neural network weights are derived from a Lyapunov stability property of the closed-loop system. The convergence of the system tracking error to zero is guaranteed without the need of network weights convergence. The resulted control method is applied in a depollution control problem in the case of a wastewater treatment bioprocess, belonging to the square nonlinear class, for which kinetic dynamics are strongly nonlinear, time varying and not exactly known.

Pseudo Bond Graph modelling and on-line estimation of unknown kinetics for a wastewater biodegradation process

Abstract This paper deals with the problem of modelling and on-line estimation of kinetics for a biomethanation process. This bioprocess is in fact a wastewater biodegradation process with production of methane gas, which takes place inside a Continuous Stirred Tank Bioreactor. The reaction scheme and the analysis of biochemical phenomena inside the bioreactor are used in order to obtain a nonlinear dynamic model of the bioprocess, by means of the pseudo Bond Graph method. Two nonlinear estimation strategies are developed for the identification of unknown kinetics of the bioprocess. First, an estimator is developed by using a state observer based technique. Second, an observer based on high-gain approach is designed and implemented. Several numerical simulations are performed in order to analyse and compare the behaviour and the performance of the proposed estimators.

Nonlinear and Neural Networks Based Adaptive Control for a Wastewater Treatment Bioprocess

The paper studies the design and analysis of some nonlinear and neural adaptive control strategies for a wastewater treatment process, which is an activated sludge process with nonlinear, time varying and not exactly known kinetics. In fact, an adaptive controller based on a dynamical neural network used as a model of the unknown plant is developed and then is compared with a classical linearizing controller. The neural controller design is achieved by using an input-output feedback linearization technique.

Neural Networks Based Adaptive Control of a Fermentation Bioprocess for Lactic Acid Production

This work deals with the design and analysis of some nonlinear and neural adaptive control strategy for a lactic acid production that is carried out in continuous stirred tank bioreactors. An indirect adaptive controller based on a dynamical neural network used as on-line approximator to learn the time-varying characteristics of process parameters is developed and then is compared with a classical linearizing controller. The controller design is achieved by using an input-output feedback linearization technique. The effectiveness and performance of both control algorithms are illustrated by numerical simulations applied in the case of a lactic fermentation bioprocess for which kinetic dynamics are strongly nonlinear, time varying and completely unknown.

Neural Network Model Predictive Control of a Wastewater Treatment Bioprocess

This paper deals with the design of a nonlinear model predictive control (NMPC) scheme for the regulation of the acetate concentration in a biomethanation process – wastewater biodegradation with production of methane gas that takes place inside a Continuous Stirred Tank Bioreactor. The NMPC control structure is based on a radial basis function neural network used as on-line approximator to learn the nonlinear characteristics of process. Minimization of the cost function is realised using the Levenberg–Marquardt numerical optimisation method. Some simulation results are given to illustrate the efficiency of the proposed control strategy.

Neural networks based model predictive control for a lactic acid production bioprocess

This work deals with the design and analysis of a nonlinear model predictive control (NMPC) strategy for a lactic acid production that is carried out in two continuous stirred bioreactors sequentially connected. The adaptive NMPC control structure is based on a dynamical neural network used as on-line approximator to learn the time-varying characteristics of process parameters. Minimization of a cost function depending on control inputs is realised using the Levenberg-Marquardt numerical optimisation method. The effectiveness and performance of the proposed control strategy is illustrated by numerical simulations applied in the case of a lactic fermentation bioprocess for which kinetic dynamics are strongly nonlinear, time varying and completely unknown.

Direct adaptive control of an anaerobic depollution bioprocess using radial basis neural networks

This work deals with the design and analysis of a nonlinear and neural adaptive control strategy for an anaerobic depollution bioprocess. A direct adaptive controller based on a radial basis function neural network used as on-line approximator to learn the time-varying characteristics of process parameters is developed and then is compared with a classical linearizing controller. The controller design is achieved by using an input-output feedback linearization technique. Numerical simulations, conducted in the case of a strongly nonlinear, time varying and not exactly known dynamical kinetics wastewater biodegradation process, are included to illustrate the behaviour and the performance of the presented controller.

Controller Design in Time Delay Systems Based on Shape Coefficients Method

Abstract This paper presents tuning relations for controllers in time delay systems based on shape coefficients method. The time scale factor is determined to fit the desired shape of the closed loop response to the time delay controlled plant by the so-called closing equation. The method can be applied to processes with both input-output delays and internal delays. Explicit tuning relations are obtained for PID controllers. Some comparative results are presented to point out the advantages and limits of the method.