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
|
摘要
针对双叶片泵存在水力性能比相同比转速的多叶片离心泵低的缺陷,该文以一台型号为80QW50-15-4的双叶片污水泵作为研究对象,将其设计流量点的扬程和效率定为优化目标,运用ANSYS CFX(computational fluid dynamics x)进行数值模拟获得性能数据,采用径向基(radial basis function,RBF)神经网络建立结构参数与扬程、效率性能间的预测模型,并将其用作粒子群算法的适应值评价模型,在样本空间内进行最优值求解,获得扬程和效率的Pareto解。选取扬程最优个体和效率最优个体进行数值模拟,研究其在输运不同介质时的性能与内流场差异,并与初始模型的数值模拟数据相比较。经试验验证,清水介质中设计流量点扬程最优个体的扬程较初始个体增加0.96 m,增幅达到5.5%;效率最优个体的效率较初始个体提升了10.11个百分点。该优化方法改善了叶轮水力特性,使双叶片泵性能得到提高。
The double vane pump is a special type of flow vane centrifugal pump. It adopts a design with less blades, which leads to a disadvantage that the performance of the double vane pump is inferior to that of the multi-blade pump at the same specific velocity. Its stability is 3%-8% lower than of a vane centrifugal pump.Therefore, it is necessary to improve the work efficiency by optimizing the hydraulic design. This article took a double-passage sewage pump model 80 QW50-15-4 as the research object. The optimization objective was to design the head and efficiency of the flow point. ANSYS CFX(computational fluid dynamics x) was used to perform numerical simulation to obtain performance data. According to the two-dimensional hydraulic drawing of the initial model pump, the three-dimensional modeling software Pro/Engineer5.0 was used to simulate the water body of the impeller and the volute and to perform mesh division and irrelevance verification. The model pump was subjected to numerical simulation and experiment of clear water medium, and the performance curve was obtained and compared. The error analysis showed that the maximum error of head and efficiency was 3.9% and 1.7%, which meant that the performance prediction model established by this method had high accuracy. Partial initial model impeller structure parameters were selected for performance impact analysis. The Plackett-Burman screening test was used to determine the blade wrap angle, blade outlet angle and impeller outlet width were significant factors affecting head and efficiency of design flow. According to Fang Kaitai's unified design table, training samples of RBF(radial basis function) neural network were arranged, so as to establish important structural parameters and performance prediction models, and generated 5 groups of structural parameters random for neural network testing and error analysis. The head and efficiency performance prediction model trained by radial basis neural network was introduced into the particle swarm optimization algorithm as the fitness evaluation model of particle swarm optimization algorithm. The Pareto optimal solution set of head and efficiency was obtained, and the optimal head and efficiency were selected. In addition, this paper also studied the performance and internal flow field differences of the initial individual, the optimal individual of head and the optimal individual of efficiency when transporting different media. It was known from the performance curve that the performance of individuals was improved when transporting different media. The reason for the performance improvement was revealed by the internal flow field distribution map. In order to verify the practicability of the optimization results, a clear water test was performed on the optimal head and the most efficient individual to obtain a performance curve and compared with the performance curve of the initial individual. Among them, the experimental head of the optimal head at the design flow point increased by 0.96 m than the initial individual, the increase rate reached 5.5%, the efficiency increased by 1.6 percentage point; the efficiency of the best individual increased by 10.11 percentage point, the head decreased slightly but met the design requirements. The test proved that the optimization effect was obvious. This optimization method improves the hydraulic characteristics of impeller and the performance of double vane pump.
The double vane pump is a special type of flow vane centrifugal pump. It adopts a design with less blades, which leads to a disadvantage that the performance of the double vane pump is inferior to that of the multi-blade pump at the same specific velocity. Its stability is 3%-8% lower than of a vane centrifugal pump.Therefore, it is necessary to improve the work efficiency by optimizing the hydraulic design. This article took a double-passage sewage pump model 80 QW50-15-4 as the research object. The optimization objective was to design the head and efficiency of the flow point. ANSYS CFX(computational fluid dynamics x) was used to perform numerical simulation to obtain performance data. According to the two-dimensional hydraulic drawing of the initial model pump, the three-dimensional modeling software Pro/Engineer5.0 was used to simulate the water body of the impeller and the volute and to perform mesh division and irrelevance verification. The model pump was subjected to numerical simulation and experiment of clear water medium, and the performance curve was obtained and compared. The error analysis showed that the maximum error of head and efficiency was 3.9% and 1.7%, which meant that the performance prediction model established by this method had high accuracy. Partial initial model impeller structure parameters were selected for performance impact analysis. The Plackett-Burman screening test was used to determine the blade wrap angle, blade outlet angle and impeller outlet width were significant factors affecting head and efficiency of design flow. According to Fang Kaitai's unified design table, training samples of RBF(radial basis function) neural network were arranged, so as to establish important structural parameters and performance prediction models, and generated 5 groups of structural parameters random for neural network testing and error analysis. The head and efficiency performance prediction model trained by radial basis neural network was introduced into the particle swarm optimization algorithm as the fitness evaluation model of particle swarm optimization algorithm. The Pareto optimal solution set of head and efficiency was obtained, and the optimal head and efficiency were selected. In addition, this paper also studied the performance and internal flow field differences of the initial individual, the optimal individual of head and the optimal individual of efficiency when transporting different media. It was known from the performance curve that the performance of individuals was improved when transporting different media. The reason for the performance improvement was revealed by the internal flow field distribution map. In order to verify the practicability of the optimization results, a clear water test was performed on the optimal head and the most efficient individual to obtain a performance curve and compared with the performance curve of the initial individual. Among them, the experimental head of the optimal head at the design flow point increased by 0.96 m than the initial individual, the increase rate reached 5.5%, the efficiency increased by 1.6 percentage point; the efficiency of the best individual increased by 10.11 percentage point, the head decreased slightly but met the design requirements. The test proved that the optimization effect was obvious. This optimization method improves the hydraulic characteristics of impeller and the performance of double vane pump.
引文
[1]赵斌娟,侯多华,陈汇龙,等.叶轮流道结构对双流道泵性能的影响[J].排灌机械,2013,31(4):294-299.Zhao Binjuan,Hou Duohua,Chen Huilong et al.Influence of impeller runner structure on performance of dual-channel pump[J].Drainage and Irrigation Machinery,2013,31(4):294-299.(in Chinese with English abstract)
[2]刘厚林,谈明高.双流道泵[M].镇江:江苏大学出版社,2012.
[3]曹新智.螺旋离心泵内部流场的数值计算[D].镇江:江苏大学,2010.Cao Xinzhi.Numerical Calculation of Internal Flow Field in Spiral Centrifugal Pump[D].Zhenjiang:Jiangsu University,2010.(in Chinese with English abstract)
[4]张德胜,张启华,施卫东编著.叶片泵设计数值模拟基础与应用[M].北京:机械工业出版社,2015.
[5]严俊峰,陈炜.基于遗传算法的低比转速高速泵的优化设计[J].火箭推进,2006,32(3):1-7.Yan Junfeng,Chen Wei.Optimization design of low specific speed high speed pump based on genetic algorithm[J].Rocket Propulsion,2006,32(3):1-7.(in Chinese with English abstract)
[6]刘峰.柱塞式燃油泵多目标结构优化[D].南京:南京航空航天大学,2008.Liu Feng.Multi-objective Structure Optimization of Plunger Fuel Pump[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2008.(in Chinese with English abstract)
[7]陶海坤,曹树良.遗传算法的改进及其在流体机械领域的应用[J].排灌机械工程学报,2010,28(5):428-433.Tao Haikun,Cao Shuliang.Improvement of genetic algorithm and its application in fluid machinery[J].Journal of Drainage and Irrigation Machinery Engineering,2010,28(5):428-433.(in Chinese with English abstract)
[8]朱增宝,李灿,季军.基于遗传算法的三柱塞往复泵曲轴优化设计[J].煤矿机械,2011,32(11):45-46.Zhu Zengbao,Li Can,Ji Jun.Optimization design of crankshaft of three-piston reciprocating pump based on genetic algorithm[J].Coal Mine Machinery,2011,32(11):45-46.(in Chinese with English abstract)
[9]刘毅,谭磊,曹树良.微遗传算法及其在混流泵叶轮优化设计中的应用[J].机械设计与制造,2012(9):1-3.Liu Yi,Tan Lei,Cao Shuliang.Micro-genetic algorithm and its application in optimization design of mixed flow pump impeller[J].Machinery Design&Manufacture,2012(9):1-3.(in Chinese with English abstract)
[10]鲍鹏飞.代理模型的微蜂群优化及在叶轮机械中的作用[D].大连:大连理工大学,2014.Bao Pengfei.Optimization of Micro-bee Colony in Proxy Model and its Role in Turbomachinery[D].Dalian:Dalian University of Technology,2014.(in Chinese with English abstract)
[11]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.Miao Senchun,Yang Junhu,Wang Xiaohui,et al.Optimization of hydraulic turbine blade profile based on neural network-genetic algorithm[J].Journal of Aerospace Power,2015,30(8):1918-1925.(in Chinese with English abstract)
[12]叶剑.基于径向基神经网络与NAGA-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 NAGA-IIAlgorithm[D].Zhenjiang:Jiangsu University,2016.(in Chinese with English abstract)
[13]吕云.混流泵能量性多参数优化研究[D].镇江:江苏大学,2017.LüYun.Energy Multi-parameter Optimization Study of Mixed Flow Pump[D].Zhenjiang:Jiangsu University,2017.(in Chinese with English abstract)
[14]赵斌娟.双流道泵内非定常三维湍流数值模拟及PIV测试[D].镇江:江苏大学,2007.Zhao Binjuan.Unsteady Three-dimensional Turbulent Numerical Simulation and PIV Test in a Dual-channel Pump[D].Zhenjiang:Jiangsu University,2007.(in Chinese with English abstract)
[15]Shojaeefard M H,Tahani M,Ehghaghi M B,et al.Numerical study of the effects of some geometric characteristics of a centrifugal pump impeller that pumps a viscous fluid[J].Computers and Fluids,2012,60:61-70.
[16]董亮,刘厚林.叶片泵CFD数值计算实例详解[M].北京:机械工业出版社,2015.
[17]Zheng Sulu,Wang Xiangping,et al.Computation of viscous flow inside a double-channel centrifugal pump[J].The Open Mechanical Engineering Journal,2014,8(1):613-618.
[18]方开泰.在水平数不同的正交试验中决定因素主次关系的一种方法[J].数学的实践与认识,1978(1):35-38.Fang Kaitai.A method for determining the relationship between primary and secondary factors in orthogonal experiments with different levels[J].Mathematics in Practice and Theory,1978(1):35-38.(in Chinese with English abstract)
[19]朱增宝,李灿,季军.基于遗传算法的三柱塞往复泵曲轴优化设计[J].煤矿机械,2011,32(11):45-46.Zhu Zengbao,Li Can,Ji Jun.Optimization design of crankshaft of three-piston reciprocating pump based on genetic algorithm[J].Coal Mine Machinery,2011,32(11):45-46.(in Chinese with English abstract)
[20]Mendes R.Population Topologies and their Influence in Particle Swarm Performance[D].Minho:University of Minho,2004.
[21]Srinivas N,Deb K.Multiobjective optimization using nondominated sorting in gentic algorithm[J].Evolutionary Computation,1994,4(3):221-248.
[22]Deb K,Pratap A,Agarwal S,et al.A fast and elitist multiobjective genetic algorithm:Nsga-II[J].IEEE Transactions on Evolutional Computations,2002,8(2):182-197.
[23]赵乃刚,邓景顺.粒子群优化算法综述[J].科技创新导报,2015,12(26):216-217.Zhao Naigang,Deng Jingshun.Overview of particle swarm optimization algorithm[J].Science and Technology Innovation Review,2015,12(26):216-217.(in Chinese with English abstract)
[24]Deb K,Pratap A,Agarwal S,et al.A fast and elitist multiobjective genetic algorithm:NSGA-II[J].IEEETransactions on Evolutionary Computation,2002,6(2):182-197.
[25]Goldberg D E.Genetic Algorithm in Search,Optimization and Machine Learning[M].Massachusetts:Addison-Westley Publishing Company,1989.
[26]Tatsumi K,Ibuki T,Tanino T.A chaotic particle swarm optimization exploiting a virtual quartic objective function based on the personal and global best solutions[J].Applied Mathematics and Computation,2013,219(17):8991-9011.
[27]Sun Y,Zhu S,Li Q,et al.A Kind of Decay-Curve Inertia Weight Particle Swarm Optimization Algorithm[M].Intelligent Computing and Information Science.Springer Berlin Heidelberg,2011.
[28]Coello C C A,Van Veldhuizen D A,Lamount G B.Evolutionary Algorithms for Solving Multi-Objective Problems[M].Norwell:Kluwer,2002.
[29]张勇,巩敦卫.先进多目标粒子群优化理论及其应用[M].北京:科学出版社,2005.
[30]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(Transactions of the CSAE),2015,31(18):100-106.(in Chinese with English abstract)
[2]刘厚林,谈明高.双流道泵[M].镇江:江苏大学出版社,2012.
[3]曹新智.螺旋离心泵内部流场的数值计算[D].镇江:江苏大学,2010.Cao Xinzhi.Numerical Calculation of Internal Flow Field in Spiral Centrifugal Pump[D].Zhenjiang:Jiangsu University,2010.(in Chinese with English abstract)
[4]张德胜,张启华,施卫东编著.叶片泵设计数值模拟基础与应用[M].北京:机械工业出版社,2015.
[5]严俊峰,陈炜.基于遗传算法的低比转速高速泵的优化设计[J].火箭推进,2006,32(3):1-7.Yan Junfeng,Chen Wei.Optimization design of low specific speed high speed pump based on genetic algorithm[J].Rocket Propulsion,2006,32(3):1-7.(in Chinese with English abstract)
[6]刘峰.柱塞式燃油泵多目标结构优化[D].南京:南京航空航天大学,2008.Liu Feng.Multi-objective Structure Optimization of Plunger Fuel Pump[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2008.(in Chinese with English abstract)
[7]陶海坤,曹树良.遗传算法的改进及其在流体机械领域的应用[J].排灌机械工程学报,2010,28(5):428-433.Tao Haikun,Cao Shuliang.Improvement of genetic algorithm and its application in fluid machinery[J].Journal of Drainage and Irrigation Machinery Engineering,2010,28(5):428-433.(in Chinese with English abstract)
[8]朱增宝,李灿,季军.基于遗传算法的三柱塞往复泵曲轴优化设计[J].煤矿机械,2011,32(11):45-46.Zhu Zengbao,Li Can,Ji Jun.Optimization design of crankshaft of three-piston reciprocating pump based on genetic algorithm[J].Coal Mine Machinery,2011,32(11):45-46.(in Chinese with English abstract)
[9]刘毅,谭磊,曹树良.微遗传算法及其在混流泵叶轮优化设计中的应用[J].机械设计与制造,2012(9):1-3.Liu Yi,Tan Lei,Cao Shuliang.Micro-genetic algorithm and its application in optimization design of mixed flow pump impeller[J].Machinery Design&Manufacture,2012(9):1-3.(in Chinese with English abstract)
[10]鲍鹏飞.代理模型的微蜂群优化及在叶轮机械中的作用[D].大连:大连理工大学,2014.Bao Pengfei.Optimization of Micro-bee Colony in Proxy Model and its Role in Turbomachinery[D].Dalian:Dalian University of Technology,2014.(in Chinese with English abstract)
[11]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.Miao Senchun,Yang Junhu,Wang Xiaohui,et al.Optimization of hydraulic turbine blade profile based on neural network-genetic algorithm[J].Journal of Aerospace Power,2015,30(8):1918-1925.(in Chinese with English abstract)
[12]叶剑.基于径向基神经网络与NAGA-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 NAGA-IIAlgorithm[D].Zhenjiang:Jiangsu University,2016.(in Chinese with English abstract)
[13]吕云.混流泵能量性多参数优化研究[D].镇江:江苏大学,2017.LüYun.Energy Multi-parameter Optimization Study of Mixed Flow Pump[D].Zhenjiang:Jiangsu University,2017.(in Chinese with English abstract)
[14]赵斌娟.双流道泵内非定常三维湍流数值模拟及PIV测试[D].镇江:江苏大学,2007.Zhao Binjuan.Unsteady Three-dimensional Turbulent Numerical Simulation and PIV Test in a Dual-channel Pump[D].Zhenjiang:Jiangsu University,2007.(in Chinese with English abstract)
[15]Shojaeefard M H,Tahani M,Ehghaghi M B,et al.Numerical study of the effects of some geometric characteristics of a centrifugal pump impeller that pumps a viscous fluid[J].Computers and Fluids,2012,60:61-70.
[16]董亮,刘厚林.叶片泵CFD数值计算实例详解[M].北京:机械工业出版社,2015.
[17]Zheng Sulu,Wang Xiangping,et al.Computation of viscous flow inside a double-channel centrifugal pump[J].The Open Mechanical Engineering Journal,2014,8(1):613-618.
[18]方开泰.在水平数不同的正交试验中决定因素主次关系的一种方法[J].数学的实践与认识,1978(1):35-38.Fang Kaitai.A method for determining the relationship between primary and secondary factors in orthogonal experiments with different levels[J].Mathematics in Practice and Theory,1978(1):35-38.(in Chinese with English abstract)
[19]朱增宝,李灿,季军.基于遗传算法的三柱塞往复泵曲轴优化设计[J].煤矿机械,2011,32(11):45-46.Zhu Zengbao,Li Can,Ji Jun.Optimization design of crankshaft of three-piston reciprocating pump based on genetic algorithm[J].Coal Mine Machinery,2011,32(11):45-46.(in Chinese with English abstract)
[20]Mendes R.Population Topologies and their Influence in Particle Swarm Performance[D].Minho:University of Minho,2004.
[21]Srinivas N,Deb K.Multiobjective optimization using nondominated sorting in gentic algorithm[J].Evolutionary Computation,1994,4(3):221-248.
[22]Deb K,Pratap A,Agarwal S,et al.A fast and elitist multiobjective genetic algorithm:Nsga-II[J].IEEE Transactions on Evolutional Computations,2002,8(2):182-197.
[23]赵乃刚,邓景顺.粒子群优化算法综述[J].科技创新导报,2015,12(26):216-217.Zhao Naigang,Deng Jingshun.Overview of particle swarm optimization algorithm[J].Science and Technology Innovation Review,2015,12(26):216-217.(in Chinese with English abstract)
[24]Deb K,Pratap A,Agarwal S,et al.A fast and elitist multiobjective genetic algorithm:NSGA-II[J].IEEETransactions on Evolutionary Computation,2002,6(2):182-197.
[25]Goldberg D E.Genetic Algorithm in Search,Optimization and Machine Learning[M].Massachusetts:Addison-Westley Publishing Company,1989.
[26]Tatsumi K,Ibuki T,Tanino T.A chaotic particle swarm optimization exploiting a virtual quartic objective function based on the personal and global best solutions[J].Applied Mathematics and Computation,2013,219(17):8991-9011.
[27]Sun Y,Zhu S,Li Q,et al.A Kind of Decay-Curve Inertia Weight Particle Swarm Optimization Algorithm[M].Intelligent Computing and Information Science.Springer Berlin Heidelberg,2011.
[28]Coello C C A,Van Veldhuizen D A,Lamount G B.Evolutionary Algorithms for Solving Multi-Objective Problems[M].Norwell:Kluwer,2002.
[29]张勇,巩敦卫.先进多目标粒子群优化理论及其应用[M].北京:科学出版社,2005.
[30]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(Transactions of the CSAE),2015,31(18):100-106.(in Chinese with English abstract)