文档名:Comparison of Artificial Neural Networks and Genetic Algorithms for Predicting Liquid Sloshing Parameters
Abstract:Thispaperdevelopsanumericalcodeformodellingliquidsloshing.Thecoupledboundaryelement-finiteelementmethodwasusedtosolvetheLaplaceequationforinviscidfluidandnonlinearfreesurfaceboundaryconditions.UsingNakayamaandWashizu'sresults,thecodeperformancewasvalidated.Usingthedevelopednumericalmode,weproposedartificialneuralnetwork(ANN)andgeneticalgorithm(GA)methodsforevaluatingsloshingloadsandcomparingthem.Tocomparetheefficiencyofthesuggestedmethods,themaximumfreesurfacedisplacementandthemaximumhorizontalforceexertedonarectangulartank'sperimeterareexamined.ItcanbeseenfromtheresultsthatbothANNsandGAscanaccuratelypredictηmaxandFmax.