Modeling of paper mill sewage sludge drying using artificial neural networks: Reduction of the training database through Taguchi's method. Issue 5 (4th April 2017)

• Record Type: Journal Article
• Authors: Salgado, Mario A. Heredia; Neto da Silva, Fernando José
• Is Part Of: Drying technology. Volume 35:Issue 5(2017)
• Page Start: 534
• Page End: 544
• Publication Date: 2017-04-04
• Subjects: Artificial neural networks -- drying kinetics -- paper mill sewage sludge -- Taguchi method; Drying -- Periodicals; Desiccation; 660.28426
• DOI: 10.1080/07373937.2016.1187162
• Languages: English
• ISSNs: 0737-3937

Abstract

ABSTRACT: Drying of sewage sludge is typically modeled as simultaneous heat and mass transfer phenomena. The capability of conventional models to take into account crust formation, cracks, and shrinking is limited. Artificial neural networks (ANNs) are suitable tools for dynamic representation of drying processes; however, obtaining a suitable database is a resource consuming task. Based on the Taguchi method, nine experiments were defined to set up a training database and to develop an ANN model. A high Pearson correlation coefficient was verified when comparing the drying kinetic curve generated by the ANN model with the one obtained during the validation experiments.