基于正交设计的气液混输泵增压单元优化设计  

Optimization Design of Compress Unit for Multiphase Pumps Based on Orthogonal Design

作　　者：马希金[1] 李新凯[1] 王楠[2] 

机构地区：[1]兰州理工大学能源与动力工程学院,甘肃兰州730050 [2]江苏大学电气信息工程学院,江苏镇江212013

出　　处：《西华大学学报（自然科学版）》2011年第3期77-81,共5页Journal of Xihua University:Natural Science Edition

基　　金：甘肃省科技攻关项目(KG954-3-11)

摘　　要：以自主研制的第三代YQH-100气液混输泵增压单元为优化对象,以混输泵相对扬程及效率为优化目标,采用正交实验设计方法设计优化方案,利用FLUENT软件对部分实验方案进行数值计算,预测混输泵的相对扬程和效率。针对数值模拟计算量大等问题,分别采用BP神经网络及GRNN网络建立目标函数与优化变量间的复杂响应关系。预测结果表明,GRNN网络较BP神经网络预测性能更优,用训练好的GRNN网络预测混输泵水力性能,优化后混输泵的相对扬程和效率分别提高了0.74%、0.83%。Based on the boosting cell parameters of independently developed third generation multiphase pump YQH-100,orthogonal experimental design was used to design the optimization scheme.Using relative head and efficiency as the evaluation targets for the optimization design,the relative head and efficiency of the multiphase pump were predicted by software FLUENT.BP neural networks and GRNN model were adopted to construct the response relation between the design variables and the objective function.The results of prediction show that the prediction performance of GRNN model was much better than that of BP neural network.The optimization results show that relative head and efficiency of the multiphase pump were increased by 0.74% and 0.83%,respectively.

关 键 词：气液混输泵 正交设计 神经网络 数值模拟 

分 类 号：TH312[机械工程—机械制造及自动化]