Optimization of twisted blade of centrifugal pump based on high dimensional machine learning method
-
摘要: 提出将高维表示方法与机器学习中的支持向量机方法结合对离心泵扭曲叶片优化。选用1台中比转速离心泵为研究对象,通过对扭曲叶片3条叶片型线的参数化,分离控制变量并确定代理模型的训练空间。经过对离心泵扭曲叶片水力模型的算法学习,得到以叶片型线参数为自变量,效率为目标函数的离心泵代理模型,运用遗传算法求解并反馈叶片型线参数。采用数值模拟及试验的方法验证了代理模型的预测结果,并从动能方程的角度分析了优化前后扭曲叶片叶轮内流场的变化。结果表明:在设计工况点,优化后的扭曲叶片离心泵数值模拟效率值比原型泵提高了1.72%,扬程提升了0.41 m,试验效率值比原型泵提高了1.5%,扬程提升了0.35 m。Abstract: The combination of high dimensional model representation (HDMR) and support vector machine (SVM) in machine learning was proposed to optimize the twisted blade of centrifugal pump.A centrifugal pump with medium specific speed was selected as the research object.The three blade profiles of twisted blade were parameterized,the control variables were separated and the training space of surrogate model was determined.After algorithm learning of the hydraulic models of the twisted blade of the centrifugal pump,the surrogate model of the centrifugal pump with the blade profile parameters as the independent variables and the efficiency as the objective function was obtained.The prediction results of the surrogate model were verified by numerical simulation and experiment.The change of flow field in twisted blade impeller before and after optimization was analyzed from the view of kinetic energy equation.The results showed that at the design operating point,the numerical simulation efficiency of the optimized twisted blade centrifugal pump was 1.72% higher than that of the prototype pump,and the head was 0.41 m higher;the test efficiency was 1.5% higher than that of the prototype pump,and the head was 0.35 m higher than that of the prototype pump.
-
[1] TONG Zheming,XIN Jiage,TONG Shuiguang,et al.Review:internal flow structure,fault detection,and performance optimization of centrifugal pumps[J].Journal of Zhejiang University:Science A (Applied Physics and Engineering),2020,21(2):85-117. [2] 关醒凡.现代泵理论与设计[M].北京:中国宇航出版社,2011. [3] 张人会,郭广强,杨军虎,等.基于不完全敏感性方法的低比转速离心叶轮优化研究[J].机械工程学报,2014,50(4):162-166. [4] 苗森春,杨军虎,王晓晖,等.基于神经网络-遗传算法的液力透平叶片型线优化[J].航空动力学报,2015,30(8):1918-1925. [5] 王春林,冯一鸣,叶剑,等.基于RBF神经网络与NSGA-Ⅱ算法的渣浆泵多目标参数优化[J].农业工程学报,2017,33(10):109-115. [6] 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. [7] ZHANG Renhui,GUO Rong,YANG Junhu,et al.Inverse method of centrifugal pump impeller based on proper orthogonal decomposition (POD) method[J].Chinese Journal of Mechanical Engineering,2017,30(2):1025-1031. [8] 张人会,陈学炳,郭广强,等.低比转数离心泵叶轮内流场重构与模态分析[J].农业机械学报,2018,49(12):143-149. [9] 郭广强,张人会,陈学炳,等.低比转速离心叶轮的 POD 代理模型优化方法[J].华中科技大学学报(自然科学版),2019,47(7):50-55. [10] 王春林,彭海菠,丁剑,等.基于响应面法的消防泵 S 型叶片改进优化设计[J].机械工程学报,2013,49(10):170-177. [11] 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. [12] 张人会,郭苗,杨军虎,等.基于伴随方法的离心泵叶轮优化设计[J].排灌机械工程学报,2014,32(11):943-954. [13] CHAHINE C,SEUME J R,VERSTRAETE T.The influence of metamodeling techniques on the multidisciplinary design optimization of a radial compressor impeller[R].ASME Paper GT2012-68358,2012. [14] ANDRéS E,SALCEDO S S,MONGE F,et al.Efficient aerodynamic design through evolutionary programming and support vector regression algorithms[J].Expert Systems with Applications,2012,39(12):10700-10708. [15] XIONG Huadi,CHEN Zhenzhong,QIU Haobo,et al.Adaptive SVR-HDMR metamodeling technique for high dimensional problems[C]∥ AASRI Procedia:The 2012 International Conference on Modeling,Identification and Control .Amsterdam: Elsevier,2012:95-100.[16] CHEN Liming,WANG Hu,YE Fan,et al.Comparative study of HDMRs and other popular metamodeling techniques for high dimensional problems[J].Structural and Multidisciplinary Optimization,2019,59(1):21-42. [17] 姜丙孝,杨军虎,白小榜,等.基于高维混合模型与遗传算法的离心泵叶片优化[J].华中科技大学学报(自然科学版),2020,48(7):128-132. [18] JOHANN F G.Centrifugal pumps[M].Berlin:Springer,2020. [19] SOBOL I M.Sensitivity estimates for nonlinear mathematical models[J].Mathematical Modelling and Computational Experiment,1993,1(4):407-414. [20] TUNGA M A.An approximation method to model multivariate interpolation problems:indexing HDMR[J].Mathematical and Computer Modelling,2011,53(9/10):1970-1982. [21] RABITZ H,ALI? ? F.General foundations of high-dimensional model representations[J].Journal of Mathematical Chemistry,1999,25:197-233. [22] ALI? ? F,RABITZ H.Efficient implementation of high dimensional model representations[J].Journal of Mathematical Chemistry,2001,29(2):127-142. [23] 杨晓伟,郝志峰.支持向量机的算法设计与分析[M].北京:科学出版社,2013. [24] 李晓俊,袁寿其,潘中永,等.离心泵边界层网格的实现及应用评价[J].农业工程学报,2012,28(20):67-72. [25] 章梓雄,董曾南.粘性流体力学[M].北京:清华大学出版社,2011. [26] DAVID C W.Turbulence modeling for CFD[M].San Diego,US:DCW Industries,2006.
点击查看大图
计量
- 文章访问数: 116
- HTML浏览量: 19
- PDF量: 55
- 被引次数: 0