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

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-solvin...

Full description

Saved in:
Bibliographic Details
Main Authors: Y. Chen, W. Li, Y. Luo, L. Ji, S. Li, Y. Long
Format: Article
Language:English
Published: Isfahan University of Technology 2025-05-01
Series:Journal of Applied Fluid Mechanics
Subjects:
Online Access:https://www.jafmonline.net/article_2669_0e45fbc2c7e111bc8a15727f44514bf3.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849728149012611072
author Y. Chen
W. Li
Y. Luo
L. Ji
S. Li
Y. Long
author_facet Y. Chen
W. Li
Y. Luo
L. Ji
S. Li
Y. Long
author_sort Y. Chen
collection DOAJ
description 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.
format Article
id doaj-art-1e591f2eaf424f5ab8cd331dea0bdb1e
institution DOAJ
issn 1735-3572
1735-3645
language English
publishDate 2025-05-01
publisher Isfahan University of Technology
record_format Article
series Journal of Applied Fluid Mechanics
spelling doaj-art-1e591f2eaf424f5ab8cd331dea0bdb1e2025-08-20T03:09:38ZengIsfahan University of TechnologyJournal of Applied Fluid Mechanics1735-35721735-36452025-05-011871735174910.47176/jafm.18.7.32582669A Rapid Design Method for Centrifugal Pump Impellers Based on Machine LearningY. Chen0W. Li1Y. Luo2L. Ji3S. Li4Y. Long5Jiangsu University, National Research Center of Pumps, Zhenjiang, JiangSu, 212013, ChinaJiangsu University, National Research Center of Pumps, Zhenjiang, JiangSu, 212013, ChinaJiangsu University, National Research Center of Pumps, Zhenjiang, JiangSu, 212013, ChinaJiangsu University, National Research Center of Pumps, Zhenjiang, JiangSu, 212013, ChinaJiangsu University, National Research Center of Pumps, Zhenjiang, JiangSu, 212013, ChinaJiangsu University, National Research Center of Pumps, Zhenjiang, JiangSu, 212013, ChinaCentrifugal 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.https://www.jafmonline.net/article_2669_0e45fbc2c7e111bc8a15727f44514bf3.pdfcentrifugal pumpmachine learningimpeller designcross-sectional areaneural network
spellingShingle Y. Chen
W. Li
Y. Luo
L. Ji
S. Li
Y. Long
A Rapid Design Method for Centrifugal Pump Impellers Based on Machine Learning
Journal of Applied Fluid Mechanics
centrifugal pump
machine learning
impeller design
cross-sectional area
neural network
title A Rapid Design Method for Centrifugal Pump Impellers Based on Machine Learning
title_full A Rapid Design Method for Centrifugal Pump Impellers Based on Machine Learning
title_fullStr A Rapid Design Method for Centrifugal Pump Impellers Based on Machine Learning
title_full_unstemmed A Rapid Design Method for Centrifugal Pump Impellers Based on Machine Learning
title_short A Rapid Design Method for Centrifugal Pump Impellers Based on Machine Learning
title_sort rapid design method for centrifugal pump impellers based on machine learning
topic centrifugal pump
machine learning
impeller design
cross-sectional area
neural network
url https://www.jafmonline.net/article_2669_0e45fbc2c7e111bc8a15727f44514bf3.pdf
work_keys_str_mv AT ychen arapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT wli arapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT yluo arapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT lji arapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT sli arapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT ylong arapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT ychen rapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT wli rapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT yluo rapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT lji rapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT sli rapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning
AT ylong rapiddesignmethodforcentrifugalpumpimpellersbasedonmachinelearning