Assessment of pressure drop in conical spouted beds of biomass by artificial neural networks and comparison with empirical correlations--颗粒学报PARTICUOLOGY

Saldarriaga, J. F., Cruz, Y., Estiati, I., Tellabide, M., & Olazar, M. (2022). Assessment of pressure drop in conical spouted beds of biomass by artificial neural networks and comparison with empirical correlations. Particuology, 70, 1-9. https://doi.org/10.1016/j.partic.2021.12.004

Assessment of pressure drop in conical spouted beds of biomass by artificial neural networks and comparison with empirical correlations

Juan F. Saldarriaga^a *, Yuby Cruz^a, Idoia Estiati^b, Mikel Tellabide^b, Martin Olazar^b

a Department of Civil and Environmental Engineering, Universidad de los Andes, Carrera 1Este #19A-40, Bogota, Colombia
b Department of Chemical Engineering, University of the Basque Country, Barrio Sarriena s/n, Leioa, Spain

10.1016/j.partic.2021.12.004

Volume 70, November 2022, Pages 1-9

Received 11 October 2021, Revised 26 November 2021, Accepted 14 December 2021, Available online 24 December 2021, Version of Record 14 January 2022.

E-mail: jf.saldarriaga@uniandes.edu.co; juanfelorza@gmail.com

Highlights

• Pressure drop is an essential parameter in the operation of conical spouted beds.

• Artificial neural networks (ANNs) were used in this study for prediction of operating and peak pressure drops.

• Experimental data fitting of operating and the peak pressure drop was better.

• ANNs have been proven suitable for prediction of pressure drop.

• ANN accuracy is significantly better than empirical correlations.

Abstract

Pressure drop is an essential parameter in the operation of conical spouted beds (CSB) and depends on its geometric factors and materials used. Irregular materials, like biomass, are complex to treat and, unlike other gas–solid contact methods, CSB turn out to be a suitable technology for their treatment. Artificial neural networks were used in this study for the prediction of operating and peak pressure drops, and their performance has been compared with that of empirical correlations reported in the literature. Accordingly, a multi-layer perceptron network with backward propagation was used due to its ability to model non-linear multivariate systems. The fitting of the experimental data of both operating and peak pressure drop was significantly better than those reported in the literature, specifically in the case of the peak pressure drop, with R² being 0.92. Therefore, artificial neural networks have been proven suitable for the prediction of pressure drop in CSB.

Graphical abstract

Keywords

Pressure drop; Artificial neural networks; Biomass; Spouted bed

文章导读