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

G. Bagnato, S. Liguori, A. Iulianelli, S. Curcio, A. Basile

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publicationProceedings of the 6th European Fuel Cell - Piero Lunghi Conference, EFC 2015
EditorsChiara Barchiesi, Michela Chianella, Viviana Cigolotti
PublisherENEA
Pages363-364
Number of pages2
ISBN (Electronic)9788882863241
Publication statusPublished - 2015
Event6th European Fuel Cell Technology and Applications Conference - Piero Lunghi Conference - Naples, Italy
Duration: 16 Dec 201518 Dec 2015

Publication series

NameProceedings of the 6th European Fuel Cell - Piero Lunghi Conference, EFC 2015

Conference

Conference6th European Fuel Cell Technology and Applications Conference - Piero Lunghi Conference
Abbreviated titleEFC 2015
Country/TerritoryItaly
CityNaples
Period16/12/1518/12/15

Fingerprint

Dive into the research topics of 'Artificial neural network model for water gas shift reaction in a dense Pd-Ag membrane reactor'. Together they form a unique fingerprint.

Cite this