Automatic optimization of axial flow pump based on radial basis functions neural network and CFD
LU Rong1, YUAN Jianping1, LI Yanjun1, JIANG Hongying2
1.National Research Center of Pumps, Jiangsu University, Zhenjiang, Jiangsu 212013, China; 2.Jiangsu Province Water Engineering Sci-tech Consulting Co. Ltd., Nanjing, Jiangsu 210000, China
Abstract:Parametric design and computational fluid dynamics(CFD)techniques have been widely applied to the optimum design of fluid machinery. In this paper, the axial flow pump was designed by turbomachinery design software-CFturbo, which was integrated with PumpLinx by batch commands based on Isight software to realize the CFD automatic optimization of axial flow pump. Seven design variables of the blade profile and diffuser were selected through Optimal Latin Hypercube Design(Opt LHD)to generate design points within the selected design space. The hydraulic efficiency at a designed flow rate was set as the objective function. A surrogate model, Radial Basis Functions(RBF)neural network was constructed for the objective function based on the numerical results. Finally, the best combination of the design variables was obtained by solving the approximation model with the Multi-Island Genetic Algorithm(MIGA). The results show that the performance curve simulated by CFD had a good agreement with that of the experiment, thus the RBF model can predict the efficiency accurately. After optimization, the efficiency was improved by 4.46%, while the head kept almost constant under the design condition. Through the Pareto Graph analysis, the significance levels of design variables were obtained, which can provide a certain reference for optimum design of the axial flow pump.
陆荣,袁建平,李彦军,蒋红樱. 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, JIANG Hongying. Automatic optimization of axial flow pump based on radial basis functions neural network and CFD. Journal of Drainage and Irrigation Machinery Engin, 2017, 35(6): 481-487.
[1]宋文武,符杰. 基于轴流泵间隙流动的新水力设计方法[J]. 中国机械工程,2012,23(10):1170-1174. SONG Wenwu, FU Jie. A new hydraulic design method based on clearance flow of axial flow pump[J]. China mechanical engineering, 2012,23(10):1170-1174.(in Chinese)[2]LI F Y, LUO Z, RONG J H, et al. Interval multi-objective optimisation of structures using adaptive Kriging approximations[J]. Computers and structures, 2013, 119(4):68-84.[3]GOEL T, VAIDYANATHAN R, HAFTKA R T, et al. Response surface approximation of Pareto optimal front in multi-objective optimization[J]. Computer methods in applied mechanics and engineering, 2007, 196(S4/5/6):879-893.[4]袁丹青,韩泳涛,丛小青,等. 多级离心泵新型空间导叶设计及优化分析[J]. 排灌机械工程学报,2015,33(10):853-858,894. YUAN Danqing, HAN Yongtao, CONG Xiaoqing, et al. Design and optimization of new-type space guide vanes for multistage centrifugal pump[J]. Journal of drainage and irrigation machinery engineering, 2015, 33(10): 853-858,894.(in Chinese)[5]KANG C, YU X, GONG W, et al. Influence of stator vane number on performance of the axial-flow pump[J]. Journal of mechanical science and technology, 2015, 29(5):2025-2034.[6]TANG Y L, ZHENG G L, ZHANG S R. Optimal control approaches of pumping stations to achieve energy efficiency and load shifting[J]. International journal of electrical power & energy systems, 2014, 55:572-580.[7]ZHU B S, WANG X H, TAN L, et al. Optimization design of a reversible pump—turbine runner with high efficiency and stability[J]. Renewable energy, 2015, 81:366-376.[8]黄友根,刘辉,王军,等. 基于模糊集理论轴流风机多工况优化研究[J]. 工程热物理学报,2015(5):1000-1004. HUANG Yougen, LIU Hui, WANG Jun, et al. Analysis of multi-points optimization design of axial flow fan based on the fuzzy set theory[J]. Journal of engineering thermophysics, 2015(5):1000-1004.(in Chinese)[9]王凯,刘厚林,袁寿其,等. 离心泵叶轮轴面图的全自动CFD优化[J]. 农业工程学报,2011,27(10):39-43. WANG Kai, LIU Houlin, YUAN Shouqi, et al. Automatic optimization of impeller meridional shape for centrifugal pumps based on CFD[J]. Transactions of the CSAE, 2011, 27(10): 39-43.(in Chinese)[10]王文杰,袁寿其,裴吉,等. 基于Kriging模型和遗传算法的泵叶轮两工况水力优化设计[J]. 机械工程学报,2015,51(15):33-38. WANG Wenjie, YUAN Shouqi, PEI Ji, et al. Two-point hydraulic optimization of pump impeller based on Kriging model and neighborhood cultivation genetic algorithm[J]. Journal of mechanical engineering, 2015,51(15):33-38.(in Chinese)[11]石丽建,汤方平,雷翠翠,等. 轴流泵叶片设计协同优化算法[J]. 农业工程学报,2014,30(17):93-100. SHI Lijian, TANG Fangping, LEI Cuicui, et al. Colla-borative optimization algorithm on axial-flow pump blade design[J]. Transactions of the CSAE, 2014, 30(17): 93-100.(in Chinese)[12]KIM J H, CHOI J H, HUSAIN A, et al. Performance enhancement of axial fan blade through multi-objective optimization techniques[J]. Journal of mechanical science and technology, 2010, 24(10): 2059-2066.[13]LEE K Y, CHOI Y S, KIM Y L, et al. Design of axial fan using inverse design method[J]. Journal of mechanical science & technology, 2008, 22(10): 1883-1888.[14]韩鼎,郑建荣. 工程优化设计中的近似模型技术[J]. 华东理工大学学报(自然科学版),2012,38(6):762-768. HAN Ding, ZHENG Jianrong. A survey of metamode-ling techniques in engineering optimization[J]. Journal of East China University of Science and Technology(natural science edition),2012,38(6):762-768.(in Chinese)[15]黄俊,亢庆,金平伟,等. 基于神经网络和粒子群算法产流量模型构建[J]. 排灌机械工程学报,2015,33(9):773-780. HUANG Jun, KANG Qing, JIN Pingwei, et al. Study on runoff production model by artificial neural network and particle swarm algorithm[J]. Journal of drainage and irrigation machinery engineering, 2015,33(9): 773-780.(in Chinese)[16]赖宇阳. Isight参数优化理论与实例详解[M]. 北京:北京航空航天大学出版社,2012.[17]关醒凡. 现代泵理论与设计[M]. 北京:中国宇航出版社,2011.