A hybrid neural approach to model batch fermentation of dairy industry wastes

Alessandra Saraceno, Sascha Sansonetti, Stefano Curcio, Vincenza Calabro, Gabriele Iorio

Research output: Contribution to journalConference articleResearchpeer-review

Abstract

In this work, the fermentation of “Ricotta cheese whey” for the production of ethanol was simulated by means of a Hybrid Neural Model (HNM), obtained by coupling neural network approach to mass balance equations describing the time evolution of lactose (substrate), ethanol (product) and biomass concentrations. The realized HNM was compared with a pure neural network model (NM) and the advantages gained from the hybrid approach were emphasized. The experimental data, necessary to develop the model, were collected during batch fermentation runs. For all the proposed networks, the inputs were chosen as the operating variables exhibiting the highest influence on the reaction rate. The simulation results showed that the HNM was capable of an accurate representation of system behavior by predicting biomass, lactose and ethanol concentration profiles with an average error percentage lower than 10%. Moreover, especially if compared with the NM, the HNM showed good forecasting capability even with fermentation run never seen during the training phase.
Keyword: Artificial neural networks,Grey-box models,Modeling,Batch fermentation
Original languageEnglish
Book seriesComputer Aided Chemical Engineering
Volume28
Pages (from-to)739-744
ISSN1570-7946
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event20th European Symposium on Computer Aided Process Engineering - Ischia, Italy
Duration: 6 Jun 20109 Jun 2010
Conference number: 20
http://www.aidic.it/escape20/

Conference

Conference20th European Symposium on Computer Aided Process Engineering
Number20
CountryItaly
CityIschia
Period06/06/201009/06/2010
Internet address

Fingerprint

Dive into the research topics of 'A hybrid neural approach to model batch fermentation of dairy industry wastes'. Together they form a unique fingerprint.

Cite this