Hydraulic Performance Optimization of Pump Impeller Based on a Joint of Particle Swarm Algorithm and Least-Squares Support Vector Regression

Hua Fang,Jianfeng Ma,Wei Zhang,Hui Yang,Feng Chen,Xiaojun Li

doi:10.1109/access.2020.3036913

Abstract

The hydraulic performance of centrifugal pumps is considerably affected by the impeller, and an effective optimization method for centrifugal pump impeller has been developed in the current study. A combination of the least-squares support vector regression machine (LSSVR) and particle swarm optimization algorithm (PSO) is proposed to redesign the impeller and improve the hydraulic performance. In the case study, four key geometric parameters of the impeller, namely, inlet angle, outlet angle, wrap angle and number of blades are selected for optimization. Maximum efficiency and constant head are selected as the optimization targets. During the optimization design, the required database for the LSSVR agent model is designed according to design of experiments. The optimal solution is then found in the established agent model space by the particle swarm algorithm and then verified by computational fluid dynamics. Ultimately, an improved impeller structure with an improved efficiency is provided. Numerical results show that the optimized impeller's efficiency is increased by 1.29% under the condition that the head is essentially unchanged. Then, the reason for the improvement of impeller hydraulic efficiency is explained by the entropy production method. The conclusions show that the PSO-LSSVR method can be used to optimize the pump impeller and achieve higher pump performance.

Highlights

Centrifugal pumps, as crucial equipment for fluid conveyance, are widely used in the chemical industry, aquaculture, metallurgy, irrigation and other fields with huge energy consumption
Predicting the performance of the centrifugal pump from impeller parameters based on the particle swarm optimization algorithm (PSO)-least-squares support vector regression machine (LSSVR) method is feasible
This study introduces the PSO-LSSVR proxy model approach to design and optimize centrifugal pump impellers

Summary

Introduction

Centrifugal pumps, as crucial equipment for fluid conveyance, are widely used in the chemical industry, aquaculture, metallurgy, irrigation and other fields with huge energy consumption. The optimization design of a centrifugal pump to reduce energy consumption and improve performance has always been the focus of researchers. With the development of computers, the CFD numerical simulation provides designers with. Shojaeefard et al [5] studied the effect of certain geometric parameters on the performance of centrifugal pumps for pumping viscous fluids by CFD. Shi et al [6] analyzed the effect of different vane outlet widths of impellers on the performance of deep-well centrifugal pumps by numerical simulation and experiments. The use of CFD simplifies the modification of the pump’s parameters to determine if performance is improved. In many cases, CFD does not directly indicate the geometric modifications that should be made to improve the pump’s hydrodynamic performance

Methods

Results

Conclusion