Comparison of Artificial Neural Networks and Genetic Algorithms for Predicting Liquid Sloshing Parameters

Abstract

This paper develops a numerical code for modelling liquid sloshing. The coupled boundary element-finite element method was used to solve the Laplace equation for inviscid fluid and nonlinear free surface boundary conditions. Using Nakayama and Washizu’s results, the code performance was validated. Using the developed numerical mode, we proposed artificial neural network (ANN) and genetic algorithm (GA) methods for evaluating sloshing loads and comparing them. To compare the efficiency of the suggested methods, the maximum free surface displacement and the maximum horizontal force exerted on a rectangular tank’s perimeter are examined. It can be seen from the results that both ANNs and GAs can accurately predict η _max and F _max.

Keywords

Sloshing loads / Fluid structure interactions / Potential flow analysis / Artificial neural network / Genetic algorithm