Software sensors for biomass concentration in a SSC process using Artificial Neural Networks and Support Vector Machine

Author

Acuña, Gonzalo ; Ramirez, Cristián ; Curilem, Millaray

Author_Institution

Dept. de Ingenieri a Inf., Univ. de Santiago de Chile, Santiago, Chile

fYear

2012

fDate

3-6 July 2012

Firstpage

359

Lastpage

363

Abstract

In this work NARX-ANN, NARMAX-ANN and NARX-SVM models are compared when acting as software sensors of a relevant state variable for a Solid-substrate cultivation (SSC) process. Results show that NARX-SVM outperforms the other models with an Index of Agreement close to 1.0 even under very noisy conditions thus confirming the claimed superiority of SVM over other black-box techniques for approximating non-linear functions. NARMAX-ANN outperforms NARX-ANN because of its better predictive capabilities.

Keywords

bioenergy conversion; chemical analysis; function approximation; neural nets; nonlinear functions; sensors; support vector machines; NARMAX-ANN models; NARX-ANN models; NARX-SVM models; SSC process; artificial neural networks; biomass concentration; black-box techniques; index of agreement; nonlinear functions approximation; predictive capabilities; relevant state variable; software sensors; solid-substrate cultivation process; support vector machine; very noisy conditions; Artificial neural networks; Biological system modeling; Biomass; Mathematical model; Predictive models; Sensors; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Control & Automation (MED), 2012 20th Mediterranean Conference on

Conference_Location

Barcelona

Print_ISBN

978-1-4673-2530-1

Electronic_ISBN

978-1-4673-2529-5

Type

conf

DOI

10.1109/MED.2012.6265664

Filename

6265664