Cinética da biossorção da mistura Ni+² - Cr+³ via redes neurais artificiais
Nenhuma Miniatura disponível
Data
2021-03
Título da Revista
ISSN da Revista
Título de Volume
Editor
Resumo
The concern with the treatment of wastewater produced by the industry is real. Adsorption is one of the most used processes, especially in the refining steps, in which the concentrations of the components are low and conventional processes are not efficient. However, finding the best condition for this task is not simple, as itinvolves the definition of a complex kinetic model and several independent variables. This field is still little explored due to the difficulty to develop such models. Therefore, Artificial Neural Networks can be a viable alternative. In this work, to overcome the difficulties found in the formulation of phenomenological models, the mains objective was to obtain a neural model to describe the adsorption kinetics of the Ni2+-Cr3+mixture by the seaweed Sargassumfilipendula. A systematic study was carried out to determine the number of hidden layers and neurons, such that they would be sufficient to describe the phenomenon in question. The ion concentrations at times tand t-1were the input variables. The RNA output was the concentration at timet+1. The Levenberg-Marquardt, Levenberg-Marquardt methods with Bayesian Regularization, Resilient Back-Propagation and Powell were used. The RNA that presented the most satisfactory result has the structure 4-10-10-2. It was obtained by using the Levenberg-Marquardt method with Bayesian Regularization and hyperbolic tangent activation functions for the intermediate and output layers. The objective function found was 6.1.10-10, which demonstrates the great potential of generalization of artificial neural networks and its potential application in the field of kinetic modeling.
Descrição
Palavras-chave
Redes neurais artificiais, Modelagem cinética, Tratamento de efluentes, Biossorção, Artificial neural network, Kinetic model, Wastewaster treatment, Biosorption
Citação
CHOJI, Thamyres Tetsue et al. Cinética da biossorção da mistura Ni+²–Cr+³ via redes neurais artificiais. Revista de Engenharia e Tecnologia, Ponta Grossa, v. 13, n. 1, p. 200-210, mar. 2021.
Disponível em: https://revistas.uepg.br/index.php/ret/article/view/17565. Acesso em: 20 jun. 2023.