Hydraulic optimization of multiphase pump based on CFD and genetic algorithm

24Citations
Citations of this article
10Readers
Mendeley users who have this article in their library.

Abstract

Impellers of helicon-axial multiphase pump are optimized based on CFD and genetic algorithm. The method mainly includes: CFD numerical calculation, to establish nonlinear relation through neural network, and genetic algorithm optimization extreme. Firstly, the profile of blades is parametric by spline surface and Choose 12 control points as optimization variables. Then, every optimization variable is given optimal dimension. Finally, sample database is got by using standard L27_3_13 orthogonal design table. Next, output values are got by modeling every sample, meshing generation and using CFD numerical calculation. Train neural networks through the database; thus the nonlinear relation between the blade parameter and pump performance parameters is built by applying the nonlinear fitting ability of BP neural networks. Regard the trained neural network as a fitness function of the genetic algorithm and use the characteristic of nonlinear global optimization of genetic algorithm to optimize the multiphase pump. Optimization result shows that the hydraulic efficiency of the multiphase pump is increased by 1.91%.

Cite

CITATION STYLE

APA

Hao, H., Xinkai, L., & Bo, G. (2015). Hydraulic optimization of multiphase pump based on CFD and genetic algorithm. International Journal of Grid and Distributed Computing, 8(6), 161–170. https://doi.org/10.14257/ijgdc.2015.8.6.16

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free