Real‐time neural observer‐based controller for unknown nonlinear discrete delayed systems

Abstract

This work presents a neural observer-based controller for uncertain nonlinear discrete-time systems with unknown time-delays. The proposed neural observer does not need previous knowledge of the model about the system under consideration, neither the value of its parameters, delays, nor their explicit estimations. The proposed neural observer is based on a neural network composed of two recurrent high order neural networks (RHONNs) for nonmeasurable state variables, one in a parallel configuration, and for measurable state variables one in a series-parallel configuration. The neural network is trained on-line with an extended Kalman filter algorithm. The proposed RHONN observer provides a mathematical model for the system. Based on such a resulting mathematical model, a control law is designed using discrete-time sliding mode block control. Applicability is presented using real-time results that show the performance of the proposal using a linear induction motor prototype as the selected system; this prototype is under the presence of varying time-delays. A Lyapunov analysis is included to prove the semi-globally uniformly ultimately boundedness (SGUUB) of the proposed RHONN observer-controller scheme for uncertain nonlinear discrete-time systems with unknown delays. K E Y W O R D S discrete-time sliding modes, Lyapunov stability, neural block control, neural state estimation, real-time, time-delay systems 8402

Advances in bioreactor control for production of biotherapeutic products

“…The past decade has observed a significant advance in the various domains of fuzzy logics, NNs, and reinforcement learning (RL) to deal with nonlinearity and uncertainties of systems (Birle et al, 2016; Dewasme et al, 2015; Rios et al, 2019; Ahmed et al, 2019; Radu‐Emil & Radu‐Codrut 2019; Nikita et al, 2021). However, strategies dealing with both inherent stochasticity and model uncertainty are still lacking and need to be addressed (Yoo et al, 2021a).…”

“…Some of the recent developments in bioreactor modeling that are employed for control application are listed in Table 1. Advantages, disadvantages, and Understanding culture dynamics, metabolism, and glycosylation to optimize mAb quality Identified optimal galactose and uridine feeding regimes to maximize mAb galactosylation while eliminating negative impacts on product titer The past decade has observed a significant advance in the various domains of fuzzy logics, NNs, and reinforcement learning (RL) to deal with nonlinearity and uncertainties of systems (Birle et al, 2016;Dewasme et al, 2015;Rios et al, 2019;Ahmed et al, 2019;Radu-Emil & Radu-Codrut 2019;Nikita et al, 2021). However, strategies dealing with both inherent stochasticity and model uncertainty are still lacking and need to be addressed (Yoo et al, 2021a).…”

Residual Neural Network-Based Observer Design for Continuous Stirred Tank Reactor Systems

“…It is extremely beneficial for the controller design of the CSTR reaction. Inspired by [25][26][27], we design the observer as follows:…”

Redes neuronales aplicadas al control estadístico de procesos con cartas de control EWMA

“…Asanza y Mazón Olivo, 2018), máquinas adaptativas que están hechas de la interconexión de neuronas artificiales (Rios et al, 2020), conformadas por una gran cantidad de neuronas conectadas en capas (Theodorids, 2020); las cuales adquieren conocimiento a través de un aprendizaje tomado del entorno y lo almacenan en los pesos sinápticos de la red; donde el comportamiento de un neurona está definido por un modelo neuronal (Yang, 2019).…”