Smart computing approach for design and scale-up of conical spouted beds with open-sided draft tubes--颗粒学报PARTICUOLOGY

Karimi, M., Vaferi, B., Hosseini, S. H., Olazar, M., & Rashidi, S. (2021). Smart computing approach for design and scale-up of conical spouted beds with open-sided draft tubes. Particuology, 55, 179-190. https://doi.org/10.1016/j.partic.2020.09.003

Smart computing approach for design and scale-up of conical spouted beds with open-sided draft tubes

M. Karimi ^a, B. Vaferi ^b *, S.H. Hosseini ^c, M. Olazar ^d, S. Rashidi ^e

a Laboratory of Separation and Reaction Engineering (LSRE), Associate Laboratory (LSRE/LCM), Department of Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, S/N, 4099-002 Porto, Portugal
b Department of Advanced Calculations, Chemical, Petroleum, and Polymer Engineering Research Center, Shiraz Branch, Islamic Azad University, Shiraz, Iran
c Department of Chemical Engineering, Ilam University, Ilam 69315-516, Iran
d Department of Chemical Engineering, University of the Basque Country UPV/EHU, P.O. Box 644, E48080 Bilbao, Spain
e Department of Petroleum Engineering, Omidiyeh Branch, Islamic Azad University, Omidiyeh, Iran

10.1016/j.partic.2020.09.003

Volume 55, April 2021, Pages 179-190

Received 16 October 2019, Revised 19 April 2020, Accepted 21 September 2020, Available online 31 October 2020, Version of Record 3 February 2021.

E-mail: behzad.vaferi@gmail.com; vaferi@iaushiraz.ac.ir

Highlights

• Conical spouted beds with open-sided draft tubes simulated by a smart model.

• Operating and peak pressure drops accurately estimated by a single approach.

• Overall MSE = 0.00039, AARD% = 1.30, and R² = 0.7609 obtained for operating pressure drop.

• Overall MSE = 0.22933, AARD% = 11.88, and R² = 0.8986 obtained for peak pressure drop.

• Guidelines are provided for minimizing both pressure drops in conical spouted beds.

Abstract

Open-sided draft tubes provide an optimal gas distribution through a cross flow pattern between the spout and the annulus in conical spouted beds. The design, optimization, control, and scale-up of the spouted beds require precise information on operating and peak pressure drops. In this study, a multi-layer perceptron (MLP) neural network was employed for accurate prediction of these hydrodynamic characteristics. A relatively huge number of experiments were accomplished and the most influential dimensionless groups were extracted using the Buckingham-pi theorem. Then, the dimensionless groups were used for developing the MLP model for simultaneous estimation of operating and peak pressure drops. The iterative constructive technique confirmed that 4-14-2 is the best structure for the MLP model in terms of absolute average relative deviation (AARD%), mean square error (MSE), and regression coefficient (R²). The developed MLP approach has an excellent capacity to predict the transformed operating (MSE = 0.00039, AARD% = 1.30, and R² = 0.76099) and peak (MSE = 0.22933, AARD% = 11.88, and R² = 0.89867) pressure drops.

Graphical abstract

Keywords

Conical spouted beds; Open-sided draft tubes; Operating pressure drops; Peak pressure drop; Smart modeling; Design guidelines

文章导读