Accurate prediction of liquid-solid fluidized bed porosity in drinking water treatment processes using empirical data-driven genetic programming models

Accurate prediction of liquid-solid fluidized bed porosity in drinking water treatment processes using empirical data-driven genetic programming models

Kramer, O.J.I. (TU Delft Complex Fluid Processing; Waternet; Hogeschool Utrecht)
El Hasadi, Yousef M.F. (TU Delft Complex Fluid Processing)
de Moel, P.J. (TU Delft Sanitary Engineering; Omnisys)
Baars, Eric T. (Waternet)
Padding, J.T. (TU Delft Complex Fluid Processing)
van der Hoek, J.P. (TU Delft Sanitary Engineering; Waternet)

2019

For an accurate prediction of the porosity of a liquid-solid homogenous fluidized bed, various empirical prediction models have been developed. Symbolic regression machine learning techniques are suitable for analyzing experimental fluidization data to produce empirical expressions for porosity as a function not only of fluid velocity and viscosity but also of particle size and shape. On the basis of this porosity, it becomes possible to calculate the specific surface area for reactions for seeded crystallization in a fluidized bed.

liquid-solid fluidization
drinking water
porosity
hydraulic models
symbolic regression
genetic programming

http://resolver.tudelft.nl/uuid:3244311d-a89e-42b7-93bf-351f13560ec1

Proceedings of the 10th International Conference on Multiphase Flow (ICMF 2019): Rio de Janeiro, Brazil, May 19 – 24, 2019

10th International Conference on Multiphase Flow, 2019-05-19 → 2019-05-24, Rio de Janeiro, Brazil

Institutional Repository

conference paper

© 2019 O.J.I. Kramer, Yousef M.F. El Hasadi, P.J. de Moel, Eric T. Baars, J.T. Padding, J.P. van der Hoek