Application of computational fluid dynamics and surrogate-coupled evolutionary computing to enhance centrifugal-pump performance

Abstract

To reduce the total design and optimization time, numerical analysis with surrogate-based approaches is being used in turbomachinery optimization. In this work, multiple surrogates are coupled with an evolutionary genetic algorithm to find the Pareto optimal fronts (PoFs) of two centrifugal pumps with different specifications in order to enhance their performance. The two pumps were used a centrifugal pump commonly used in industry (Case I) and an electrical submersible pump used in the petroleum industry (Case II). The objectives are to enhance head and efficiency of the pumps at specific flow rates. Surrogates such as response surface approximation (RSA), Kriging (KRG), neural networks and weighted-average surrogates (WASs) were used to determine the PoFs. To obtain the objective functions' values and to understand the flow physics, Reynolds-averaged Navier-Stokes equations were solved. It is found that the WAS performs better for both the objectives than any other individual surrogate. The best individual surrogates or the best predicted error sum of squares (PRESS) surrogate (BPS) obtained from cross-validation (CV) error estimations produced better PoFs but was still unable to compete with the WAS. The high CV error-producing surrogate produced the worst PoFs. The performance improvement in this study is due to the change in flow pattern in the passage of the impeller of the pumps.

Design Optimization of the Centrifugal Pumps via Low Fidelity Models

“…The pump performance is greatly affected by viscosity of the fluid pumped. In recent decades, the effect of surface roughness on the performance of centrifugal pump has been studied experimentally as well as numerically by several authors [5,[59][60][61][62]. Bellary and Samad [61] study on pumping crude oil using centrifugal pump shows that combined effect of an increase in exit blade angles and surface roughness can increase head with negligible increase in efficiency.…”

Segmentation model based on convolutional neural networks for extracting vegetation from Gaofen-2 images

“…17,18 Advancements in deep learning enable us to address these problems with deep neural networks (DNNs). [19][20][21][22] As one of the most important branches of deep learning, the convolutional neural network (CNN) is commonly applied to image data owing to its superior feature learning ability. [23][24][25] The CNN is a deep learning network composed of multiple, nonlinear mapping layers with strong learning abilities that obtain excellent results in image segmentation.…”

Numerical study on the impact of the coupling of diffuser parameters on the performance of submersible pumps used in town water distribution systems

“…Researchers have performed considerable studies on the optimization design and performance prediction of centrifugal pumps. Based on the concept that submersible pumps belong to the category of centrifugal pumps, research mostly focuses on the calculations pertaining to and characteristic analysis of the internal flow field surrounding the centrifugal pump impeller and volute [10][11][12][13][14][15][16][17][18]. For submersible pumps with diffusers, pertinent studies on electrical submersible pumps (ESPs), in which the impeller and diffuser compose a single stage, have been reported in the literature [19][20][21]; these studies include those pertaining to independent structural parameters that affect the pump performance and structural optimization [22][23][24].…”