Abstract
To increase efficiency at the design point of a centrifugal pump, this study adopted an artificial neural network in the construction of an accurate nonlinear function between the optimization objective and the design variables of impellers. Modified particle swarm optimization was further applied to refine the mathematical model globally. The database, which consisted of 200 sets of impellers, were generated from the Latin hypercube sampling method, and their corresponding efficiencies were obtained automatically from numerical simulation. Design variables were the distributions of blade angles, and results established that the difference between the numerical performance curve and the experimental results was acceptable. Optimization with a two-layer feedforward network improved the pump efficiency at the design point by 0.454 %. Flow complexity improved as the blade curvature increased. The application of the multilayer neural network could provide a meaningful reference to single- and multi-objective optimization of complex and nonlinear pump performance.
Similar content being viewed by others
References
J. F. Gülich, Centrifugal Pumps, Berlin: Springer (2008).
M. Zangeneh, A. Goto and T. Takemura, Suppression of secondary flows in a mixed-flow pump impeller by application of 3d inverse design method: Part 1—design and numerical valition, ASME 1994 International Gas Turbine and Aeroengine Congress and Exposition, American Society of Mechanical Engineers (1994) V001T01A014-V001T01A014.
M. A. A. Chikh et al., Efficiency of bio-and socio-inspired optimization algorithms for axial turbomachinery design, Applied Soft Computing, 64 (2018) 282–306
N. Timnak and A. Jahangirian, Multi-point optimization of transonic airfoils using an enhanced genetic algorithm, Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 232 (7) (2018) 1347–1360
A. Oyama, M. S. Liou and S. Obayashi, Transonic axial-flow blade optimization: Evolutionary algorithms/three-dimensional Navier-Stokes solver, Journal of Propulsion and Power, 20 (4) (2004) 612–619
W. Wahba and A. A. Tourlidakis, Genetic algorithm applied to the design of blade profiles for centrifugal pump impellers, 15th AIAA Computational Fluid Dynamics Conference (2001) 2582.
M. A. Bezerra et al., Response surface methodology (RSM) as a tool for optimization in analytical chemistry, Talanta, 76 (5) (2008) 965–977
J. P. C. Kleijnen, Kriging metamodeling in simulation: A review, European Journal of Operational Research, 192 (3) (2009) 707–716
N. Murata, S. Yoshizawa and S. Amari, Network information criterion-determining the number of hidden units for an artificial neural network model, IEEE Transactions on Neural Networks, 5 (6) (1994) 865–872
M. S. Cao et al., Neural network ensemble-based parameter sensitivity analysis in civil engineering systems, Neural Computing and Applications, 28 (7) (2017) 1583–1590
L. Darvishvand, B. Kamkari and F. Kowsary, Optimal design approach for heating irregular-shaped objects in three-dimensional radiant furnaces using a hybrid genetic algorithm–artificial neural network method, Engineering Optimization, 50 (3) (2018) 452–470
S. Chatterjee et al., Particle swarm optimization trained neural network for structural failure prediction of multisto-ried RC buildings, Neural Computing and Applications, 28 (8) (2017) 2005–2016
S. Derakhshan et al., Numerical shape optimization of a centrifugal pump impeller using artificial bee colony algorithm, Computers & Fluids, 81 (2013) 145–151
B. Duan et al., Multi-objective hydraulic optimization and analysis in a minipump, Science Bulletin, 60 (17) (2015) 1517–1526
H. S. Shim, K. Y. Kim and Y. S. Choi, Three-objective optimization of a centrifugal pump to reduce flow recirculation and cavitation, Journal of Fluids Engineering, 140 (9) (2018) 091202.
J. W. Suh et al., A study on numerical optimization and performance verification of multiphase pump for offshore plant, Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy, 231 (5) (2017) 382–397
J. W. Suh et al., Multi-objective optimization of the hydro-dynamic performance of the second stage of a multi-phase pump, Energies, 10 (9) (2017) 1334.
F. Miao et al., Swarm intelligence based on modified PSO algorithm for the optimization of axial-flow pump impeller, Journal of Mechanical Science and Technology, 29 (11) (2015) 4867–4876
J. Zhang et al., Multi-objective shape optimization of helico-axial multiphase pump impeller based on NSGA-II and ANN, Energy Conversion and Management, 52 (1) (2011) 538–546
A. Goto, Historical perspective on fluid machinery flow optimization in an industry, International Journal of Fluid Machinery and Systems, 9 (1) (2016) 75–84
R. C. Eberhart and J. Kennedy, Particle swarm optimization, Proceedings of the IEEE International Conference on Neural Networks, 4 (1995) 1942–1948
S. K. S. Fan and E. Zahara, A hybrid simplex search and particle swarm optimization for unconstrained optimization, European Journal of Operational Research, 181 (2) (2007) 527–548
K. E. Parsopoulos and M. N. Vrahatis, Particle swarm optimization method for constrained optimization problems, intelligent technologies–Theory and application, New Trends in Intelligent Technologies, 76 (1) (2002) 214–220
G. Haisi, Numerical and Experimental Investigation on the Influence of Blade Trailing Edge Profile on Internal Flow Characteristics in Centrifugal Pump, Jiangsu University (2017).
F. R. Menter, Review of the shear-stress transport turbulence model experience from an industrial perspective, International Journal of Computational Fluid Dynamics, 23 (4) (2009) 305–316
G. Ardizzon, G. Cavazzini and G. Pavesi, Adaptive acceleration coefficients for a new search diversification strategy in particle swarm optimization algorithms, Information Sciences, 299 (2015) 337–378
Acknowledgments
This work is supported by the National Key Research and Development Program (Grant No. 2018YFB0606103), National Natural Science Foundation of China (Grant Nos. 51879121, 51779107), China Postdoctoral Science Foundation funded project (Grant No. 2019M651736), Six Talent Peaks Project (GDZB-047) and Qing Lan Project of Jiangsu Province.
Author information
Authors and Affiliations
Corresponding author
Additional information
Recommended by Associate Editor Weon Gyu Shin
Ji Pei is currently an Associate Professor in National Research Center of Pumps, Jiangsu University. His research interests include optimization of pumps, unsteady flow, flow-induced vibration and fluid-structure interaction in fluid machinery. He received his Ph.D. degree from Jiangsu University in 2013.
Wenjie Wang is currently a Research Associate in National Research Center of Pumps, Jiangsu University. His research interests include the optimization design and analysis of the unsteady flow of centrifugal pumps. He received his Ph.D. degree from Jiangsu University in 2017.
Rights and permissions
About this article
Cite this article
Pei, J., Wang, W., Osman, M.K. et al. Multiparameter optimization for the nonlinear performance improvement of centrifugal pumps using a multilayer neural network. J Mech Sci Technol 33, 2681–2691 (2019). https://doi.org/10.1007/s12206-019-0516-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-019-0516-6