A Rapid Design Method for Centrifugal Pump Impellers Based on Machine Learning

Chen, Y.; Li, W.; Luo, Y.; Ji, L.; Li, S.; Long, Y.

doi:10.47176/jafm.18.7.3258

A Rapid Design Method for Centrifugal Pump Impellers Based on Machine Learning

Document Type : Regular Article

Authors

Jiangsu University, National Research Center of Pumps, Zhenjiang, JiangSu, 212013, China

10.47176/jafm.18.7.3258

Abstract

Centrifugal pumps are widely used across various industries, and the design of high-efficiency centrifugal pumps is essential for energy savings and emission reductions. The development of centrifugal pump models primarily uses an iterative design approach combining direct and inverse problem-solving based on one-dimensional flow theory. However, this semi-empirical, semi-theoretical design process is time-consuming and costly. To reduce development time and costs, this paper proposes a rapid impeller design method focused on hydraulic performance, integrating traditional similarity design theory with machine learning. The proposed model uses neural networks to predict empirical coefficients, determine key dimensions such as the impeller’s inlet diameter, outlet diameter, outlet width, and axial distance. Once these parameters are defined, the main dimensions of the impeller can be calculated. The blade profile is defined using a 5-point B´ezier curve. Variations in the cross-sectional area of the flow passage influence the internal flow state of the centrifugal pump, ultimately impacting its hydraulic efficiency. A genetic algorithm, guided by variations in the cross-sectional area of the flow passage, optimizes the blade profile, achieving an improved impeller flow path and completing the rapid design of the centrifuge. This method significantly shortens the development cycle and lowers design costs, making it a promising technique for future impeller designs.

Keywords

Main Subjects

Artificial Intelligence in Fluid Mechanics

References

Adnan, M., Alarood, A. A. S., Uddin, M. I., & ur Rehman, I. (2022). Utilizing grid search cross-validation with adaptive boosting for augmenting performance of machine learning models. Peer J Computer Science, 8, e803. https://doi.org/10.7717/peerj-cs.803

Barsi, D., Lengani, D., & Simoni, D. (2022). Analysis of the loss production mechanism due to cavity–main flow interaction in a low-pressure turbine stage. Journal of Turbomachinery, 144(9), 091004. https://doi.org/10.1115/1.4053745

Baydas, S., & Karakas, B. (2019). Defining a curve as a Bezier curve. Journal of Taibah University for Science, 13(1), 522–528. https://doi.org/10.1080/16583655.2019.1601913

Chernobrova, A., Moloshnyi, O., & Szulc, P. (2024). Influence of Volute Casing Design Methods and Changes in Geometric Parameters on Pump Operation. Energies, 17(18), 4590. https://doi.org/10.3390/en17184590

Cioffi, R., Travaglioni, M., Piscitelli, G., Petrillo, A., & De Felice, F. (2020). Artificial intelligence and machine learning applications in smart production: Progress, trends, and directions. Sustainability, 12(2), 492. https://doi.org/10.3390/su12020492

Guan, X. F. (2011). Modern Pump Theory and Design. Beijing: China Machine Press.

Huang, R., Zhang, Z., Zhang, W., Mou, J., Zhou, P., & Wang, Y. (2020). Energy performance prediction of the centrifugal pumps by using a hybrid neural network. Energy, 213, 119005. https://doi.org/10.1016/j.energy.2020.119005

Joshi, S. S., Dalvi, V. H., Vitankar, V. S., J. B. Joshi, & A. J. Joshi (2024). Development of new correlation for the prediction of power number for closed clearance impellers using machine learning methods trained on literature data. The Canadian Journal of Chemical Engineering. https://doi.org/10.1002/cjce.25385

Ju, Y., Liu, Y., Jiang, W., & Zhang, C. (2021). Aerodynamic analysis and design optimization of a centrifugal compressor impeller considering realistic manufacturing uncertainties. Aerospace Science and Technology, 115, 106787. https://doi.org/10.1016/j.ast.2021.106787

Kim, H. I., Roh, T. S., Huh, H., & Lee, H. J. (2022). Development of ultra-low specific speed centrifugal pumps design method for small liquid rocket engines. Aerospace, 9(9), 477. https://doi.org/10.3390/aerospace9090477

Li, C., Wang, J., Guo, Z., Song, L., & Li, J. (2019a). Aero-mechanical multidisciplinary optimization of a high-speed centrifugal impeller. Aerospace Science and Technology, 95, 105452. https://doi.org/10.1016/j.ast.2019.105452

Li, J., Cheng, J. H., Shi, J. Y., & Huang, F. (2012). Brief introduction of back propagation (BP) neural network algorithm and its improvement. Advances in Computer Science and Information Engineering: Volume 2 (pp. 553–558). Springer. https://doi.org/10.1007/978-3-642-30223-7_87

Li, W., Yang, Q., Yang, Y., Ji, L., Shi, W., & Agarwal, R. (2024). Optimization of pump transient energy characteristics based on response surface optimization model and computational fluid dynamics. Applied Energy, 362, 123038. https://doi.org/10.1016/j.apenergy.2024.123038

Li, Y., Wei, C., & Ma, T. (2019b). Towards explaining the regularization effect of initial large learning rate in training neural networks. Advances in Neural Information Processing Systems, 32. https://doi.org/10.48550/arXiv.1907.04595

Ma, Y., Gao, E., Zhang, X., & Huang, S. (2024). Parametric analysis and design optimization of a fully open absorption heat pump for heat and water recovery of flue gas. Applied Energy, 375, 124144. https://doi.org/10.1016/j.apenergy.2024.124144

Mineur, Y., Lichah, T., Castelain, J. M., & Giaume, H. (1998). A shape controlled fitting method for Bézier curves. Computer Aided Geometric Design, 15(9), 879–891. https://doi.org/10.1016/S0167-8396(98)00025-9

Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536. https://doi.org/10.1038/323533a0

Shao, L., & Zhou, H. (1996). Curve fitting with Bezier cubics. Graphical Models and Image Processing, 58(3), 223–232. https://doi.org/10.1006/gmip.1996.0019

Singh, D., & Singh, B. (2022). Feature wise normalization: An effective way of normalizing data. Pattern Recognition, 122, 108307. https://doi.org/10.1016/j.patcog.2021.108307

Stepanoff, A. (1943). Centrifugal-pump performance as a function of specific speed. Transactions of the American Society of Mechanical Engineers, 65(6), 629–636. https://doi.org/10.1115/1.4018866

Turing, A. M. (2009). Computing machinery and intelligence. Springer. https://doi.org/10.1007/978-1-4020-6710-5_3

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

Van Oudheusden, B. W., Scarano, F., Roosenboom, E. W., Casimiri, E. W., & Souverein, L. J. (2007). Evaluation of integral forces and pressure fields from planar velocimetry data for incompressible and compressible flows. Experiments in Fluids, 43, 153–162. https://doi.org/10.1007/s00348-007-0261-y

Verde, W. M., Kindermann, E., Bulgarelli, N. A. V., Pastre, L. F., Foresti, B., & Bannwart, A. C. (2024). A critical analysis and improvements of empirical models for predicting the performance of Electrical Submersible Pumps under viscous flow. Geoenergy Science and Engineering, 238, 212871. https://doi.org/10.1016/j.geoen.2024.212871

Verhoeven, J. J. (1988). Rotordynamic considerations in the design of high-speed centrifugal pumps. Proceedings of the 5th International Pump Users Symposium. Turbomachinery Laboratories, Department of Mechanical Engineering, Texas A & M. https://hdl.handle.net/1969.1/164295

Wadi Al-Fatlawi, A., Hashemi, J., Hossain, S., & M. El Haj Assad (2024). Applying machine learning in CFD to study the impact of thermal characteristics on the aerodynamic characteristics of an airfoil. Journal of Applied Fluid Mechanics, 17(4). https://doi.org/10.47176/jafm.17.4.2276.

Wang, C., Shi, W., Wang, X., Jiang, X., Yang, Y., Li, W., & Zhou, L. (2017). Optimal design of multistage centrifugal pump based on the combined energy loss model and computational fluid dynamics. Applied Energy, 187, 10–26. https://doi.org/10.1016/j.apenergy.2016.11.046

Wilson, K. C., Addie, G. R., Sellgren, A., & Clift, R. (2006). Centrifugal pumps. Springer. https://doi.org/10.1007/b101079

Wu, J. Z., Ma, H. Y., & Zhou, J. Z. (2007). Vorticity and vortex dynamics. Springer NetLibrary, Inc.

Zhao, B., Dong, X., Guo, Y., Jia, X., & Huang, Y. (2022). PCA dimensionality reduction method for image classification. Neural Processing Letters. https://doi.org/10.1007/s11063-021-10632-5

Zhao, X., Xiao, Y., Wang, Z., Luo, Y., & Cao, L. (2018). Unsteady flow and pressure pulsation characteristics analysis of rotating stall in centrifugal pumps under off-design conditions. Journal of Fluids Engineering, 140(2), 021105. https://doi.org/10.1115/1.4037973

Zhou, L., Hang, J., Bai, L., Krzemianowski, Z., El-Emam, M. A., Yasser, E., & Agarwal, R. (2022). Application of entropy production theory for energy losses and other investigation in pumps and turbines: A review. Applied Energy, 318, 119211. https://doi.org/10.1016/j.apenergy.2022.119211