skip to main content
Idioma:

Using scientific machine learning to develop universal differential equation for multicomponent adsorption separation systems

B. R. Nogueira, Idelfonso ; V. Santana, Vinicius ; Ribeiro, Ana M. ; Rodrigues, Alírio E.

Canadian journal of chemical engineering, 2022-09, Vol.100 (9), p.2279-2290 [Periódico revisado por pares]

Hoboken, USA: John Wiley & Sons, Inc

Texto completo disponível

Citações Citado por
  • Título:
    Using scientific machine learning to develop universal differential equation for multicomponent adsorption separation systems
  • Autor: B. R. Nogueira, Idelfonso ; V. Santana, Vinicius ; Ribeiro, Ana M. ; Rodrigues, Alírio E.
  • Assuntos: Adsorption ; Artificial neural networks ; Data points ; Fixed beds ; hybrid modelling ; Machine learning ; Mathematical models ; multicomponent adsorption ; Ordinary differential equations ; Parameter identification ; Partial differential equations ; Phenomenology ; scientific machine learning ; Separation ; universal differential equations
  • É parte de: Canadian journal of chemical engineering, 2022-09, Vol.100 (9), p.2279-2290
  • Notas: Funding information
    FCT–Fundação para a Ciência e Tecnologia under CEEC Institucional program and FCT‐MIT Portugal, Grant/Award Number: PRT/BD/152850/2021; national funds through FCT/MCTES (PIDDAC); Base‐UIDB/50020/2020 and Programmatic‐UIDP/50020/2020 Funding of LSRE‐LCM and ALiCE
  • Descrição: Universal differential equations are a concept in scientific machine learning that leverages the potential of the universal approximator theorem and the physical knowledge of a given system. Creating this level of hybridization within a stiff partial differential equation system is a challenge. On the other hand, adsorption phenomenological models have sink/source terms that describe the adsorption equilibrium through a well‐known simplified model (e.g., Langmuir; Sips; and Brunauer, Emmet, Teller [BET]). These suitable mechanistic assumptions are identified through experiments, providing the parameters of the sink/source model. However, these mechanistic assumptions are a simplification of the system phenomenology. Therefore, the resulting model is limited by its premises. In this scenario, the universal ordinary differential equations (UODE) is presented as an approach that conciliates the potential of artificial neural networks to learn given phenomena without conceptual simplifications. On the other hand, keeping into consideration the system physics. This work proposes a UODE system to solve the multicomponent separation by adsorption in a fixed bed column. Experimental data is used to identify the hybrid model. The required amount of data used in the model identification demonstrates that hybrid models can use a few data points to precisely describe the system. Furthermore, the obtained model can describe competitive adsorption with higher precision than the Langmuir model.
  • Editor: Hoboken, USA: John Wiley & Sons, Inc
  • Idioma: Inglês
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.