Adaptive Recurrent Neural Network Control of Biological Wastewater Treatment

• Tipo: Artigo em Revista Científica Internacional
• Data: 2005

Autores

Ieroham S. Baruch (Autor) FEUP; Petia Georgieva (Autor) FEUP; Josefina Barrera-Cortes (Autor) Outra; Sebastiao Feyo de Azevedo (Autor) FEUP

Revista

Título: International Journal of Intelligent Systems

Vol. 20 Nº 2

Páginas: 173-193

ISSN: 0884-8173

Editora: Wiley-Blackwell

Indexação

ISI Web of Science

Scopus

INSPEC

COMPENDEX

Classificação Científica

FOS: Ciências da engenharia e tecnologias > Engenharia química

CORDIS: Ciências Tecnológicas > Engenharia > Engenharia química

Outras Informações

Abstract (EN): Three adaptive neural network control structures to regulate a biological wastewater treatment process are introduced: indirect, inverse model, and direct adaptive neural control. The objective is to keep the concentration of the recycled biomass proportional to the influent flow rate in the presence of periodically acting disturbances, process parameter variations, and measurement noise. This is achieved by the so-called Jordan Canonical Recurrent Trainable Neural Network, which is a completely parallel and parametric neural structure, permitting the use of the obtained parameters, during the learning phase, directly for control system design. Comparative simulation results confirmed the applicability of the proposed control schemes.

Idioma: Inglês

Tipo (Avaliação Docente): Científica