基于BP神经网络的立式离心泵导叶与蜗壳优化设计

张德胜; 杨港; 赵旭涛; 杨雪琪; 高雄发

基于BP神经网络的立式离心泵导叶与蜗壳优化设计

江苏大学国家水泵及系统工程技术研究中心

基金项目:

国家自然科学基金项目(51979125)

江苏省重点研发计划项目(BE2019089)

江苏省普通高校研究生实践创新计划项目(SJCX21_1682)

详细信息

作者简介:
张德胜(1982—),男,研究员,博士生导师,主要从事流体机械设计理论及流动特性研究,E-mail:zds@ujs.edu.cn

中图分类号: TH311;TP183
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
出版历程
- 收稿日期: 2021-05-16
- 刊出日期: 2022-04-24

Optimization Design of Vane Diffuser and Volute in Vertical Centrifugal Pump Based on Back Propagation Neural Network

National Research Center of Pumps and Pumping System, Jiangsu University

摘要

摘要: 立式离心泵是大型灌溉和长距离调水工程的核心动力装备，单机配套功率能够达到40 MW级。为了降低立式离心泵的运行能耗，以效率指标为优化目标，基于BP(反向传播)神经网络模型与多岛遗传算法对其多个过流部件进行优化设计。考虑到各过流部件的匹配性，采用Plackett-Burman试验设计从导叶与蜗壳的10个设计参数中筛选出优化设计变量。运用最优拉丁超立方采样方法设计了106组方案，并搭建了立式离心泵自动数值模拟优化平台。基于BP神经网络模型构建了优化设计变量和优化目标之间的高精度非线性关系，最终通过多岛遗传算法得到导叶与蜗壳的最优参数组合。研究结果表明，运用SST k-ω湍流模型能够准确地预测立式离心泵的性能参数；BP神经网络是映射泵设计参数和性能参数间内在联系的有效方法；优化后模型设计工况下效率达到90.21%,较原始模型提高了3.61个百分点；优化后的导叶与蜗壳对立式离心泵设计工况和小流量工况下的性能影响更为显著；优化后导叶与其他过流部件匹配性提高，导叶与蜗壳内部流动特性得到明显改善。
- 立式离心泵 /
- 过流部件匹配 /
- 自动优化 /
- BP神经网络 /
- 多岛遗传算法
Abstract: Vertical centrifugal pump is a high specific speed centrifugal pump, which is usually with radial vane diffuser structure. As the core power equipment for large-scale irrigation projects and long-distance water transfer, the matching motor power for vertical centrifugal pump is huge and can reach 40 MW, and the efficiency directly determines its operating energy consumption. In order to reduce the energy consumption of vertical centrifugal pumps, an optimization on multi-components was proposed based on back propagation neural network（BPNN） and multi-island genetic algorithm（MIGA）. The matching of the hydraulic components was taken into account and the Plackett-Burman test design was used to screen out the optimal design variables from the 10 design parameters of the vane diffuser and the volute. Then, totally 106 sets of cases were sampled by using optimal Latin hypercube sampling（OLHS）, and an automatic numerical simulation optimization platform for the vertical centrifugal pump was built to quickly obtain the optimization objective values corresponding to each set of case. The BPNN was used to construct the high-precision nonlinear relationship between the optimization variables and the optimization objective. Finally, the optimal parameter combination of vane diffuser and volute was obtained through MIGA. The results showed that the performance parameters of vertical centrifugal pump could be more accurately predicted by using SST k-ω turbulence model. BPNN was an effective method to construct high-precision nonlinear relationship between pump design parameters and performance parameters. The efficiency of the optimized model under design condition reached 90.21%, which was 3.61 percentage points higher than that of the original model. The optimized vane diffuser and volute had a more obvious influence on the performance of vertical centrifugal pumps under design condition and part-load conditions. The matching between the vane diffuser and other hydraulic components was better, and the internal flow pattern of the vane diffuser was significantly improved after optimization. The optimization method proposed could provide a certain reference for the optimization design of centrifugal pumps.
- vertical centrifugal pump /
- matching of hydraulic components /
- automatic optimization /
- back propagation neural network /
- multi-island genetic algorithm

HTML全文

参考文献(25)

[1]	GAO Z X,ZHU W R,LU L,et al.Numerical and experimental study of unsteady flow in a large centrifugal pump with stay vanes[J].Journal of Fluids Engineering,2014,136(7):071101.
[2]	江伟,李挺,王玉川,等.导叶式离心泵内部流场数值模拟与试验[J].农业机械学报,2017,48(9):121-128.JIANG Wei,LI Ting,WANG Yuchuan,et al.Numerical simulation and experiment of flow field in centrifugal pump with vane diffuser[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(9):121-128.(in Chinese)
[3]	阳君,袁寿其,裴吉,等.带导叶离心泵内部旋转失速研究进展[J].排灌机械工程学报,2015,33(5):369-373.YANG Jun,YUAN Shouqi,PEI Ji,et al.Overview of rotating stall in centrifugal pumps with vaned diffuser[J].Journal of Drainage and Irrigation Machinery Engineering,2015,33(5):369-373.(in Chinese)
[4]	朱相源,王凤鸣,谢昌成,等.大流量下动静干涉对离心泵叶轮做功的影响[J].华中科技大学学报(自然科学版),2020,48(3):12-17.ZHU Xiangyuan,WANG Fengming,XIE Changcheng,et al.Influence of rotor stator interaction on impeller work for centrifugal pump[J].Journal of Huazhong University of Science and Technology (Natural Science Edition),2020,48(3):12-17.(in Chinese)
[5]	邓文剑,楚武利,吴艳辉,等.基于试验设计近似模型优化方法及其在离心泵上的应用[J].西北工业大学学报,2008,26(6):707-711.DENG Wenjian,CHU Wuli,WU Yanhui,et al.An optimization method based on design of experiments and its application to centrifugal pumps[J].Journal of Northwestern Polytechnical University,2008,26(6):707-711.(in Chinese)
[6]	WANG W J,PEI J,YUAN S Q,et al.Optimization of the diffuser in a centrifugal pump by combining response surface method with multi-island genetic algorithm[J].Proc.Inst.Mech.Eng.Part E:Journal of Process Mechanical Engineering,2017,231(2):191-201.
[7]	王春林,叶剑,曾成,等.基于NSGA-Ⅱ遗传算法高比转速混流泵多目标优化设计[J].农业工程学报,2015,31(18):100-106.WANG Chunlin,YE Jian,ZENG Cheng,et al.Multi-objective optimum design of high specific speed mixed-flow pump based on NSGA-Ⅱ genetic algorithm[J].Transactions of the CSAE,2015,31(18):100-106.(in Chinese)
[8]	裴吉,甘星城,王文杰,等.基于人工神经网络的管道泵进水流道性能优化[J].农业机械学报,2018,49(9):130-137.PEI Ji,GAN Xingcheng,WANG Wenjie,et al.Hydraulic optimization on inlet pipe of vertical inline pump based on artificial neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(9):130-137.(in Chinese)
[9]	MENG F,LI Y J,YUAN S Q,et al.Multiobjective combination optimization of an impeller and diffuser in a reversible axial-flow pump based on a two-layer artificial neural network[J].Processes,2020,8(3):1-26.
[10]	童哲铭,陈尧,童水光,等.基于NSGA-Ⅲ算法的低比转速离心泵多目标优化设计[J].中国机械工程,2020,31(18):2239-2246.TONG Zheming,CHEN Yao,TONG Shuiguang,et al.Multi-objective optimization design of low specific speed centrifugal pumps[J].China Mechanical Engineering,2020,31(18):2239-2246.(in Chinese)
[11]	赵斌娟,仇晶,赵尤飞,等.双流道泵蜗壳多目标多学科设计优化[J].农业机械学报,2015,46(12):96-101.ZHAO Binjuan,QIU Jing,ZHAO Youfei,et al.Multi-objective and multidisciplinary optimization of double-channel pump[J].Transactions of the Chinese Society for Agricultural Machinery,2015,46(12):96-101.(in Chinese)
[12]	PEI J,GAN X C,WANG W J,et al.Multi-objective shape optimization on the inlet pipe of a vertical inline pump[J].Journal of Fluids Engineering,2019,141(6):061108.
[13]	陆荣,袁建平,李彦军,等.基于神经网络模型和CFD的轴流泵自动优化[J].排灌机械工程学报,2017,35(6):481-487.LU Rong,YUAN Jianping,LI Yanjun,et al.Automatic optimization of axial flow pump based on radial basis functions neural network and CFD[J].Journal of Drainage and Irrigation Machinery Engineering,2017,35(6):481-487.(in Chinese)
[14]	KIM J H,KIM K Y.Analysis and optimization of a vaned diffuser in a mixed flow pump to improved hydrodynamic performance[J].Journal of Fluids Engineering,2012,134(7):071104.
[15]	王文杰,裴吉,袁寿其,等.基于径向基神经网络的叶轮轴面投影图优化[J].农业机械学报,2015,46(6):78-83.WANG Wenjie,PEI Ji,YUAN Shouqi,et al.Optimization of impeller meridional shape based on radial basis neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2015,46(6):78-83.(in Chinese)
[16]	WANG L Y,ASOMANI S N,YUAN J P,et al.Geometrical optimization of pump-as-turbine (PAT) impellers for enhancing energy efficiency with 1-D theory[J].Energies,2020,13(16):4120.
[17]	MENTER F R.Review of the shear-stress transport turbulence model experience from an industrial perspective[J].International Journal of Computational Fluid Dynamics,2009,23(4):305-316.
[18]	王福军.计算流体动力学分析[M].北京:清华大学出版社,2004.
[19]	王春林,胡蓓蓓,冯一鸣,等.基于径向基神经网络与粒子群算法的双叶片泵多目标优化[J].农业工程学报,2019,35(2):25-32.WANG Chunlin,HU Beibei,FENG Yiming,et al.Multi-objective optimization of double vane pump based on radial basis neural network and particle swarm[J].Transactions of the CSAE,2019,35(2):25-32.(in Chinese)
[20]	赖宇阳.Isight参数优化理论与实例讲解[M].北京:北京航空航天大学出版社,2012.
[21]	ROSSI M,RENZI M.A general methodology for performance prediction of pumps-as-turbines using artificial neural networks[J].Renewable Energy,2018,128(29):265-274.
[22]	陈俊英,姚志华,张智韬,等.大田葵花土壤含盐量无人机遥感反演研究[J].农业机械学报,2020,51(7):178-191.CHEN Junying,YAO Zhihua,ZHANG Zhitao,et al.UAV remote sensing inversion of soil salinity in field of sunflower[J].Transactions of the Chinese Society for Agricultural Machinery,2020,51(7):178-191.(in Chinese)
[23]	黄宝洲,杨俊华,卢思灵,等.基于改进粒子群算法优化神经网络算法的波浪捕获功率预测[J].太阳能学报,2021,42(2):302-307.HUANG Baozhou,YANG Junhua,LU Siling,et al.Wave capture power forecasting based on improved particle swarm optimization neural network algorithm[J].Acta Energiae Solaris Sinica,2021,42(2):302-307.(in Chinese)
[24]	马永杰,云文霞.遗传算法研究进展[J].计算机应用研究,2012,29(4):1201-1210.MA Yongjie,YUN Wenxia.Research progress of genetic algorithm[J].Application Research of Computers,2012,29(4):1201-1210.(in Chinese)
[25]	LIANG T,LU H.A novel method based on multi-island genetic algorithm improved variational mode decomposition and multi-features for fault diagnosis of rolling bearing[J].Entropy,2020,22(9):995.