Home > Research > Publications & Outputs > Artificial neural network model for water gas s...
View graph of relations

Artificial neural network model for water gas shift reaction in a dense Pd-Ag membrane reactor

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published
  • G. Bagnato
  • S. Liguori
  • A. Iulianelli
  • S. Curcio
  • A. Basile
Close
Publication date18/12/2015
Host publicationProceedings of the 6th European Fuel Cell - Piero Lunghi Conference, EFC 2015
PublisherENEA
Pages363-364
Number of pages2
ISBN (print)9788882863241
<mark>Original language</mark>Undefined/Unknown
Event6th European Fuel Cell Piero Lunghi Conference - Naples, Italy
Duration: 16/12/201518/12/2015
https://www.enea.it/en/publications/abstract/proceedings-6-european-fuel-cell-lunghi

Conference

Conference6th European Fuel Cell Piero Lunghi Conference
Country/TerritoryItaly
CityNaples
Period16/12/1518/12/15
Internet address

Conference

Conference6th European Fuel Cell Piero Lunghi Conference
Country/TerritoryItaly
CityNaples
Period16/12/1518/12/15
Internet address

Abstract

The water gas shift reaction was studied in membrane reactors for training an artificial neural network model. In particular, we have lead experiment varying many parameters as the reaction pressure, reaction temperature, gas hourly space velocity, sweep gas flow rate, H2O/CO feed molar ratio and feed configuration have been considered from both a modelling and an experimental point of view in order to analyze their influence on the water gas shift performance in two membrane reactors. Meanwhile, the artificial neural network model has been validated by using experimental tests as training results and it was validated whit a new data set, obtained optimizing the system to achieve as much as possible high hydrogen recovery. The model predicted the experimental performance of the water gas shift membrane reactors with an error on CO conversion lower than 0.5% and around 10% for the H2 recovery.