期刊
ENGINEERING OPTIMIZATION
卷 43, 期 10, 页码 1095-1113出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/0305215X.2010.542811
关键词
particle swarm optimization; centrifugal pumps; multi-objective optimization; NPSHr; computational fluid dynamics
In the present study, multi-objective optimization of centrifugal pumps is performed in three steps. In the first step, efficiency (eta) and the required net positive suction head (NPSHr) in a set of centrifugal pumps are numerically investigated using commercial software. Two meta-models based on the evolved group method of data handling (GMDH) type neural networks are obtained in the second step for modeling of eta and NPSHr with respect to geometrical design variables. Finally, using the obtained polynomial neural networks, a multi-objective particle swarm optimization method (MOPSO) is used for Pareto-based optimization of centrifugal pumps considering two conflicting objectives, eta and NPSHr. The Pareto results of the MOPSO method are also compared with those of a multi-objective genetic algorithm (NSGA II). It is shown that some interesting and important relationships as useful optimal design principles involved in the performance of centrifugal pumps can be discovered by Pareto-based multi-objective optimization of the obtained polynomial metamodels representing eta and NPSHr characteristics.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据