Water Treatment by Ozonation: Contaminants Concentration Estimation by Dynamical Neural Network

Authors:	Chairez Isaac, CINVESTAV, Mexico Poznyak Alexander, CINVESTAV, Mexico Poznyak Tatyana, ESIQIE-IPN, Mexico
Topic:	8.3 Modelling & Control of Environmental Systems
Session:	Modeling and Control of Environmental Systems
Keywords:	Environmental systems, Dynamic neural network, Sliding mode observer

Abstract

A real data set from model mixtures water treatment is considered to be analyzed trough this observer based on dynamical neural networks and sliding mode-like design. The residual sign term is suggested to be used to reduce the output external noise effect in the estimation process, and the dynamic neural network is employed to reconstruct the state dynamics of the system under this study.