Integrated
genetic algorithm - Artificial neural network strategy for modeling important
multiphase-flow characteristics
Industrial and
Engineering Chemistry Research, 41(10), 2002, 2543-2551.
Laurentiu A. Tarca, Bernard P.A. Grandjean and Faїçal Larachi
Department of Chemical Engineering & CERPIC
Laval University - Québec, Canada G1K 7P4
Abstract
Numerous investigations have shown that
artificial neural networks (ANN) can be successful for correlating experimental
data sets of macroscopic multiphase flow characteristics, e.g., hold-up,
pressure drop, interfacial mass transfer. The approach proved its worth
especially when rigorous fluid mechanics treatment based on the solution of
first-principle equations is not tractable. One perennial obstacle facing
correlations is the choice of low-dimensionality
input vector containing the most expressive dimensionless
independent variables allowing the best correlation of the dependent output
variable. As no clue is known in advance, one has recourse to laborious, often
inefficient and non-systematic trial-and-error procedure to identify from a
broad reservoir of possible candidates, the most relevant combination of ANN
input dimensionless variables. The combinatorial nature of the problem renders
the determination of the best combination, especially for multiphase flows,
computationally difficult due to the large scale of the search space of
combinations. A methodology is devised in this work to cope with this
computational complexity by illustrating the potential of genetic algorithms
(GA) to efficiently identify the elite
ANN input combination required for the prediction of a desired characteristics.
The multi-objective function to be minimized is a composite criterion that
includes ANN prediction errors on both learning and generalization data sets,
as well as a penalty function that embeds phenomenological rules accounting for
ANN model likelihood and adherence to behavior
dictated by the process physics. The proof-of-concept of the integrated GA-ANN
methodology was illustrated using a comprehensive database of experimental
total liquid hold-up for counter-current gas-liquid flows in randomly packed
towers for extracting the best liquid holdup
correlation.
Keywords genetic algorithm, artificial neural
network, database, multiphase flow, counter-current packed bed, liquid hold-up.