基于NSGA-Ⅲ算法的低比转速离心泵多目标优化设计

doi:10.3969/j.issn.1004-132X.2020.18.012

摘要/Abstract

摘要： 为提高IJ125-100-400-00型低比转速离心泵的水力性能，采用基于参考点的非支配排序遗传算法（NSGA-Ⅲ）结合近似模型、数值模拟等方法对叶片进行了多目标优化。根据水力损失模型和灵敏度分析结果，选取叶轮出口宽度、叶轮出口直径以及叶轮出口角度3个参数作为设计变量; 使用拉丁超立方抽样随机生成了60组设计方案，针对非简化模型进行了数值模拟，得到了对应的外特性值，并建立了高效的BP神经网络近似模型；最终采用NSGA-Ⅲ算法对近似模型进行了多目标寻优，得到了最优设计变量组合。研究结果表明：初始模型的数值模拟结果与实验值具有很好的一致性，两者在额定工况下扬程的绝对误差小于2.14%，；BP神经网络拟合预测效果良好；优化后的离心泵水力效率提高了6.86%，扬程满足设计需求，泵内部流场明显改善。

关键词: 离心泵, 数值模拟, 神经网络, 多目标优化, NSGA-Ⅲ算法

Abstract: In order to improve the hydraulic performance of the IJ125-100-400-00 low specific speed centrifugal pumps, a non-dominated sorting genetic algorithm based on reference point(NSGA-Ⅲ) combined with approximate model and numerical simulation was used to optimize the multi-objective optimization of the blades. According to the hydraulic loss model and sensitivity analysis results, three parameters of impeller exit width, impeller exit diameter and impeller exit angle were selected as design variables. Sixty sets of design schemes were randomly generated by using Latin hypercube sampling, and the numerical simulations were performed for non-simplified models. The external characteristic values were obtained, and an efficient BP neural network approximation model was established. Finally, the NSGA-Ⅲ algorithm was used to optimize the approximate model and the optimal design variable combination was obtained. The results show that the numerical simulation results of the initial model are in good agreement with the measured values. The head absolute errors of the two values under rated conditions are less than 2.14%. The BP neural network has good prediction results. Optimized centrifugal pump hydraulic efficiency is increased by 6.86%, the lift meets the design requirements, and the internal flow field of the pumps is significantly improved.

Key words: centrifugal pump, numerical simulation, neural network, multi-objective optimization, NSGA-Ⅲ algorithm

中图分类号:

TH311

童哲铭1；陈尧1；童水光1；余跃1；李进富2；郝国帅3. 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, DOI: 10.3969/j.issn.1004-132X.2020.18.012.

TONG Zheming1；CHEN Yao1；TONG Shuiguang1；YU Yue1；LI Jinfu2；HAO Guoshuai3. Multi-objective Optimization Design of Low Specific Speed Centrifugal Pumps Based on NSGA-Ⅲ Algorithm[J]. China Mechanical Engineering, DOI: 10.3969/j.issn.1004-132X.2020.18.012.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.cmemo.org.cn/CN/10.3969/j.issn.1004-132X.2020.18.012

http://www.cmemo.org.cn/CN/Y2020/V31/I18/2239

参考文献

[1]关醒凡.现代泵理论与设计[M].北京：中国宇航出版社，2011.
GUAN Xingfan. Modern Pump Theory and Design[M]. Beijing: China Aerospace Publishing House, 2011.
[2]袁寿其,王文杰,裴吉,等.低比转数离心泵的多目标优化设计[J].农业工程学报，2015，31(5)：46-52.
YUAN Shouqi, WANG Wenjie, PEI Ji, et al.Multi-objective Optimization Design of Low Specific Speed Centrifugal Pump[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(5):46-52.
[3]司乔瑞,林刚,袁寿其,等.高效低噪无过载离心泵多目标水力优化设计[J].农业工程学报，2016,32(4)：69-77.
SI Qiaorui, LIN Gang, YUAN Shouqi, et al. Multi-objective Hydraulic Optimization Design of High Efficiency Low Noise and No Overload Centrifugal Pump[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(4):69-77.
[4]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 Optimization Design of High Specific Speed Mixed Flow Pump Based on NSGA-Ⅱ Genetic Algorithm[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(18):100-106.
[5]曲延鹏,陈颂英,杨新振,等.低比转速离心泵叶轮几何参数多目标优化[J].山东大学学报(工学版），2009，39(3)：103-105.
QU Yanpeng, CHEN Songying, YANG Xinzhen,et al. Multi-objective Optimization of Geometric Parameters of Centrifugal Pump with Low Specific Speed[J].Journal of Shandong University(Engineering Science),2009,39(3):103-105.
[6]杨乐乐.离心泵参数化设计与内部流场仿真研究[D].秦皇岛：燕山大学,2017.
YANG Lele. Parametric Design of Centrifugal Pump and Simulation of Internal Flow Field[D].Qinhuangdao：Yanshan University, 2017.
[7]张进军.低比转数离心泵性能预测方法与软件开发[D].上海：上海交通大学,2008.
ZHANG Jinjun. Performance Prediction Method and Software Development of Low Specific Speed Centrifugal Pump[D].Shanghai： Shanghai Jiao Tong University, 2008.
[8]叶剑.基于径向基神经网络与NSGA-Ⅱ算法的渣浆泵多目标优化设计[D].镇江：江苏大学,2016.
YE Jian.Multi-objective Optimization Design of Slurry Pump Based on Radial Basis Neural Network and NSGA-Ⅱ Algorithm[D]. Zhenjiang：Jiangsu University,2016.
[9]张宇,覃刚,张云清,等.基于克里金元模型的离心泵水力性能多目标优化[J].华中科技大学学报(自然科学版),2015,43(4):54-57.
ZHANG Yu, QIN Gang, ZHANG Yunqing,et al.Multi-objective Optimization of Hydraulic Performance of Centrifugal Pump Based on Kriging Element Model[J].Journal of Huazhong University of Science and Technology(Natural Science),2015,43(4):54-57.
[10]黄思,宋志光,张雪娇，等.离心泵多目标多变量优化设计模型实用化研究[J].中国农村水利水电,2014(5):130-132.
HUANG Si, SONG Zhiguang, ZHANG Xuejiao,et al. Study on the Practical Application of Multi-objective Multivariable Optimization Design Model for Centrifugal Pump[J].China Rural Water and Hydropower,2014(5):130-132.
[11]滕书格.离心泵水力模型多目标优化研究[D].济南：山东大学,2008.
TENG Shuge. Multi-objective Optimization of Hydraulic Model of Centrifugal Pump[D].Jinan：Shandong University,2008.
[12]王幼民,唐铃凤,秦小建.中低比转速离心泵叶轮多目标优化设计[J].机械传动,2003(2):27-29.
WANG Youmin, TANG Lingfeng, QIN Xiaojian.Multi-objective Optimization Design of Centrifugal Pump Impeller in Medium and Low Specific Speed[J].Journal of Mechanical Transmission,2003(2):27-29.
[13]毕晓君,王朝.一种基于参考点约束支配的NSGA-Ⅲ算法[J].控制与决策,2019,34(2):369-376.
BI Xiaojun, WANG Chao. An NSGA-Ⅲ Algorithm Based on Reference Point Constraint Control[J].Control and Decision, 2019,34(2):369-376.
[14]DEB K, JAIN H.An Evolutionary Many-objective Optimization Algorithm Using Reference-Point-Based Non-dominated Sorting Approach, Part I:Solving Problems with Box Constraints[J].IEEE Transactions on Evolutionary Computation, 2014,18

(4):577-601.
[15]王秀礼,袁寿其,朱荣生,等.长短叶片离心泵汽蚀性能数值模拟分析及实验研究[J].中国机械工程,2012,23(10):1154-1157.
WANG Xiuli, YUAN Shouqi, ZHU Rongsheng, et al. Numerical Simulation Analysis and Experimental Research of Cavitation Performance of Long and Short Blade Centrifugal Pumps[J]. China Mechanical Engineering, 2012, 23(10): 1154-1157.