Skip to main content

Advertisement

SpringerLink
Log in

Centrifugal pump impeller and volute shape optimization via combined NUMECA, genetic algorithm, and back propagation neural network

  • Industrial Application
  • Published:
Structural and Multidisciplinary Optimization Aims and scope Submit manuscript

Abstract

This paper presents a fast, efficient, and convenient shape optimization design method for the centrifugal pump impeller and volute. A meridional curve, stream surface, blade stacking, and two-dimensional blade profile are obtained for impeller parameterized fitting by NUMECA, which substantially decreases the parameters to be optimized. A combination of genetic algorithm (GA) and back propagation neural network (BPNN) is then employed to optimize the impeller design while preventing prematurity or stagnation due to the GA. The head and efficiency of the optimized impeller under the designed flow rate condition increase by 7.69% and 4.74%, respectively, while power decreases by 2.56% post-optimization. Static pressure in the optimized impeller middle span is more uniform post-optimization, and the hydraulic performance of the centrifugal pump with the optimized impeller exceeds that of the original centrifugal pump under low and designed flow rate conditions. Head increases by 2.69 m and efficiency increases by 4.32% under the designed flow rate condition as well. The base circle diameter, volute inlet width, and volute baffle tongue can be modified to optimize the volute shape design. The head of the centrifugal pump with the optimized volute and optimized impeller increases by 4.83 m and 6.35 m and efficiency increases by 9.12% and 18.65% under 1.2 and 1.4 times the designed flow rate compared to the pump with the original volute and optimized impeller. Vortices in the optimized volute are reduced significantly and particularly relative energy losses. Under low flow rate conditions, compared with the original centrifugal pump, the head and efficiency of the experimental centrifugal pump with optimized impeller and optimized volute increase by 1.56 m and 1.12%; under the designed flow rate condition, they increase by 4.34 m and 5.23%; and under the high flow rate condition, they increase by 3.71 m and 8.54%, respectively. Compared to the traditional optimization method, as evidenced by numerous shape optimization design cases, NUMECA-GA-BPNN produces better optimized shapes with stronger hydraulic performance more quickly and efficiently.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25
Fig. 26
Fig. 27
Fig. 28
Fig. 29
Fig. 30
Fig. 31
Fig. 32
Fig. 33
Fig. 34
Fig. 35
Fig. 36
Fig. 37
Fig. 38
Fig. 39
Fig. 40
Fig. 41
Fig. 42
Fig. 43
Fig. 44
Fig. 45
Fig. 46
Fig. 47
Fig. 48
Fig. 49

Similar content being viewed by others

References

  • Balamurugan R, Ramakrishnan CV, Swaminathan N (2011) A two phase approach based on skeleton convergence and geometric variables for topology optimization using genetic algorithm. Struct Multidiscip Optim 43(3):381–404

    Article  Google Scholar 

  • Chen HX, He JW, Liu C (2017) Design and experiment of the centrifugal pump impellers with twisted inlet vice blades. J Hydrodyn 29(6):1085–1088

    Article  Google Scholar 

  • Deng HY, Liu Y, Li P, Zhang SC (2017) Whole flow field performance prediction by impeller parameters of centrifugal pumps using support vector regression. Adv Eng Softw 114:258–267

    Article  Google Scholar 

  • Derakhshan S, Bashiri C (2018) Investigation of an efficient shape optimization procedure for centrifugal pump impeller using eagle strategy algorithm and ANN (case study: slurry flow). Struct Multidiscip Optim 58:459–473

    Article  Google Scholar 

  • Derakhshan S, Pourmahdavi M, Abdolahnejad E, Reihani A, Ojaghi A (2013) Numerical shape optimization of a centrifugal pump impeller using artificial bee colony algorithm. Comput Fluids 81:145–151

    Article  Google Scholar 

  • Elhoseny M, Tharwat A, Hassanien AE (2018) Bezier curve based path planning in a dynamic field using modified genetic algorithm. J Comput Sci-Neth 45:339–350

    Article  Google Scholar 

  • Guan XF (2011) Modern pumps theory and design. China Astronautic Publishing House, Beijing

    Google Scholar 

  • Gülich JF (2007) Centrifugal pumps. Springer, Berlin

    Google Scholar 

  • Lee J, Jesong H, Kang S (2008) Derivative and GA-based methods in metamodeling of back-propagation neural networks for constrained approximate optimization. Struct Multidiscip Optim 35(1):29–40

    Article  Google Scholar 

  • Lobanoff VS, Ross RR (1992) Centrifugal pump: design and application. Gulf Professional Publishing, Texas

    Google Scholar 

  • Lomakin VO, Chaburko PS, Kuleshova MS (2017) Multi-criteria optimization of the flow of a centrifugal pump on energy and vibroacoustic characteristics. Procedia Engineering 176:476–482

    Article  Google Scholar 

  • Lumley JL (1970) Stochastic tools in turbulence. Academic Press, Elsevier, Cambridge

    MATH  Google Scholar 

  • Meng JH, Hu J, Xiao HD, Lv MY (2017) Hierarchical optimization of the composite blade of a stratospheric airship propeller based on genetic algorithm. Struct Multidiscip Optim 56(6):1341–1352

    Article  Google Scholar 

  • Nelik L (1999) Centrifugal and rotary pumps: fundamentals with applications. CRC Press, Florida

    Book  Google Scholar 

  • NUMECA International (1991) https://www.numeca.com/home

  • Nourbakhsh A, Safikhani H, Derakhshan S (2011) The comparison of multi-objective particle swarm optimization and NSGA II algorithm: applications in centrifugal pumps. Eng Optimiz 43(10):1095–1113

    Article  MathSciNet  Google Scholar 

  • Oskouei AV, Fard SS, Aksogan O (2012) Using genetic algorithm for the optimization of seismic behavior of steel planar frames with semi-rigid connections. Struct Multidiscip Optim 45(2):287–302

    Article  Google Scholar 

  • Pathak KK, Sehgal DK (2010) Gradientless shape optimization using artificial neural networks. Struct Multidiscip Optim 41(5):699–709

    Article  Google Scholar 

  • Pei J, Wang WJ, Yuan SQ (2016) Multi-point optimization on meridional shape of a centrifugal pump impeller for performance improvement. J Mech Sci Technol 30(11):4949–4960

    Article  Google Scholar 

  • Riccietti E, Bellucci J, Checcucci M, Marconcini M, Arnone A (2017) Support vector machine classification applied to the parametric design of centrifugal pumps. Eng Optimiz:1–21

  • Shi FZ (2015) CAGD & NURBS. Higher Education Press, Beijing

    Google Scholar 

  • Shiau TN, Kang CH, Liu DS (2008) Interval optimization of rotor-bearing systems with dynamic behavior constraints using an interval genetic algorithm. Struct Multidiscip Optim 36(6):623–631

    Article  Google Scholar 

  • Sirovich L (1987) Turbulence and the dynamics of coherent structures: part I: coherent structures. Q Appl Math 45(3):561–571

    Article  Google Scholar 

  • Ltd SP (2010) Centrifugal pump handbook. Butterworth-Heinemann, Oxford

    Google Scholar 

  • Tuzson J (2000) Centrifugal pump design. John Wiley & Sons, New Jersey

    Google Scholar 

  • Wu ZH (1979) Three-dimensional turbomachine flow equations expressed with respect to non-orthogonal curvilinear coordinates and non-orthogonal velocity components and methods of solution. Chin J Mech Eng 15:1): 1–1):23

    Google Scholar 

  • Xu Y, Tan L, Cao SL, Qu WS (2017) Multiparameter and multiobjective optimization design of centrifugal pump based on orthogonal method. P I Mech Eng C-J Mec 231(14):2569–2579

    Article  Google Scholar 

  • Yakhot V, Orzag SA (1986) Renormalization group analysis of turbulence: basic theory. J Sci Comput 1(1):3–11

    Article  MathSciNet  Google Scholar 

  • Yedidiah S (1996) Centrifugal pump user’s guidebook: problems and solutions. Springer US, NewYork

    Book  Google Scholar 

  • Yeniay O (2005) Penalty function methods for constrained optimization with genetic algorithms. Math Comput Appl 10(1):45–56

    MathSciNet  Google Scholar 

  • Zhang Y, Hu SB, Wu JL, Zhang YQ, Chen LP (2014) Multi-objective optimization of double suction centrifugal pump using Kriging metamodels. Adv Eng Softw 74:16–26

    Article  Google Scholar 

  • Zhou G, Ma ZD, Cheng AG, Li GY, Huang J (2015) Design optimization of a runflat structure based on multi-objective genetic algorithm. Struct Multidiscip Optim 51(6):1363–1371

    Article  Google Scholar 

Download references

Acknowledgments

The authors gratefully acknowledge the technical support from Kaiquan Motor & Pump Co. Ltd. (Shanghai and Hefei).

Funding

This study was financially supported by the National Key Basic Research Program of China (No. 2014CB239203), the National Natural Science Foundation of China (No. 51804318 and No. 51474158), and the Hubei Provincial Natural Science Foundation of China (No. 2016CFA088).

Author information

Authors and Affiliations

  1. Key Laboratory of Hydraulic Machinery Transients, Ministry of Education, Wuhan University, Wuhan, 430072, Hubei, China

    Xiangdong Han, Yong Kang & Yi Hu

  2. Department of Mechanical Engineering, National University of Singapore, Singapore, 117576, Singapore

    Xiangdong Han

  3. Hubei Key Laboratory of Waterjet Theory and New Technology, Wuhan University, Wuhan, 430072, Hubei, China

    Xiangdong Han, Yong Kang & Yi Hu

  4. School of Energy and Power Engineering, Lanzhou University of Technology, Lanzhou, 730050, Gansu, China

    Jianping Sheng & Weiguo Zhao

  5. Hefei Kaiquan Motor & Pump CO. LTD, Hefei, 230000, Anhui, China

    Jianping Sheng

  6. College of Petroleum Engineering, China University of Petroleum, Beijing, 102249, Beijing, China

    Yi Hu

Authors
  1. Xiangdong Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yong Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jianping Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yi Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Weiguo Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yi Hu.

Ethics declarations

Conflict of interest

All authors declare no conflict of interest.

Additional information

Responsible Editor: Somanath Nagendra

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Highlights

• The impeller described by discrete points is converted into one new parameterized model. The optimization parameters needed decrease obviously. The associated investigations are few.

• The prematurity and stagnation of genetic algorithm could be avoided via the coupling of genetic algorithm and back propagation neural network. The related investigations are few.

• α2 and α3 are new optimization parameters, which were seldom employed to make impeller shape optimization design in the previously published literatures.

• Three different kinds of hexahedral structured grids are employed to discretize the impeller computational domain to guarantee numerical simulation results precision. Few scholars have employed this method to discretize the impeller computational domain in the previously published literatures.

• One new dimensionless number, volute relative energy loss degree ΔRLV, is defined to assess the energy losses in the volute and evaluate the volute shape optimization design effects, which has not been published in the previous literatures.

• One fast, efficient, and convenient centrifugal pump shape optimization design method is provided.

• More cases are studied to prove that NUMECA-GA-BPNN is superior to traditional optimization method. Three indices, total time consumption, head, and efficiency, are compared.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Han, X., Kang, Y., Sheng, J. et al. Centrifugal pump impeller and volute shape optimization via combined NUMECA, genetic algorithm, and back propagation neural network. Struct Multidisc Optim 61, 381–409 (2020). https://doi.org/10.1007/s00158-019-02367-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00158-019-02367-8

Keywords

Search

Navigation