Adsorption material composition and process optimization, a systematical approach based on Deep Learning

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2021

Autores

Maria João Regufe (Autor) Outra; Vinícius V. Santana (Autor) Outra; Márcio M. Martins (Autor) Outra; Alexandre Ferreira (Autor) FEUP; José M. Loureiro (Autor) Outra; Alírio E. Rodrigues (Autor) Outra; Ana M. Ribeiro (Autor) FEUP; Ildefonso B. R. Nogueira (Autor) FEUP

Ata de Conferência Internacional

Título: IFAC PAPERSONLINE

Páginas: 43-48

16th IFAC Symposium on Advanced Control of Chemical Processes (ADCHEM)

ELECTR NETWORK, JUN 13-16, 2021

Indexação

ISI Web of Knowledge - 0 Citações

Scopus - 0 Citações

Projetos Associados

LA LSRE-LCM - Financiamento Plurianual 2020-2023 para a Unidade LA LSRE-LCM Laboratório de Processos de Separação e Reacção - Laboratório de Catálise e Materiais

Outras Informações

ID Authenticus: P-00V-F3A

DOI: 10.1016/j.ifacol.2021.08.216

Abstract (EN): The material screening is a preliminary step while designing an adsorption process. This step is carried out with a limited view of what concerns the material used. It usually focuses only on the materials' properties and not on their behavior while employed in the separation process. Furthermore, there is a lack of a systematic approach that uses an available materials database to identify the best material in a given process application. This leaves an open issue in the literature, which is getting attention with the advance of computer sciences. Hence, this work addresses this topic by proposing a systematic approach based on Deep Learning and a meta -heuristic optimization for simultaneous adsorbent screening and process optimization. This approach is developed with the main goal to make available a methodology for process optimization with material design that can be run at any time that the process needs to be reconfigured, without exhaustive simulations. As a case study, it is presented the carbon dioxide capture by Electric Swing Adsorption. The results show that the proposed methodology can identify the optimal material composition while providing the optimal process operating conditions. Copyright (C) 2021 The Authors.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 6