Discrete Optimization on Unsteady Pressure Fluctuation of a Centrifugal Pump Using ANN and Modified GA DOI Creative Commons
Wenjie Wang, Qifan Deng, Ji Pei

et al.

Chinese Journal of Mechanical Engineering, Journal Year: 2023, Volume and Issue: 36(1)

Published: July 31, 2023

Abstract Pressure fluctuation due to rotor-stator interaction in turbomachinery is unavoidable, inducing strong vibration the equipment and shortening its lifecycle. The investigation of optimization methods for an industrial centrifugal pump was carried out reduce intensity pressure extend lifecycle these devices. Considering time-consuming transient simulation unsteady pressure, a novel strategy proposed by discretizing design variables genetic algorithm. Four highly related parameters were chosen, 40 sample cases generated simulated using automatic program. 70% them used training surrogate model, others verifying accuracy model. Furthermore, modified discrete algorithm (MDGA) cost owing numerical simulation. For benchmark test, MDGA showed great advantage over original regarding searching speed effectively dealt with dramatically increasing convergence rate. After optimization, performance stability inline improved. efficiency increased more than 2.2%, decreased 20% under condition. This research method reducing characteristics pumps.

Language: Английский

Pump as turbine cavitation performance for both conventional and reverse operating modes: A review DOI
Kan Kan, Maxime Binama, Huixiang Chen

et al.

Renewable and Sustainable Energy Reviews, Journal Year: 2022, Volume and Issue: 168, P. 112786 - 112786

Published: July 16, 2022

Language: Английский

Citations

136
Energy-saving oriented optimization design of the impeller and volute of a multi-stage double-suction centrifugal pump using artificial neural network DOI Creative Commons
Jiantao Zhao, Ji Pei,

Jianping Yuan

et al.

Engineering Applications of Computational Fluid Mechanics, Journal Year: 2022, Volume and Issue: 16(1), P. 1974 - 2001

Published: Sept. 30, 2022

To broaden the efficient operating zone and increase energy efficiency of a multi-stage double-suction centrifugal pump, multi-component multi-condition optimization design method involving high-precision performance predictions, flow loss visualization technique based on entropy production theory, machine learning is proposed. First, accuracy baseline pump numerical methodology verified via grid convergence analysis experiments. Thereafter, nine parameters impeller double volute are selected as variables. Subsequently, 150 designs created according to Latin hypercube sampling (LHS) numerically simulated using an automatic simulation program. A backpropagation neural network (BPNN) multi-objective genetic algorithm (MOGA) adopted maximize at 0.6Qd, 1.0Qd, 1.2Qd. Finally, optimal results calculations analyzed. The indicate that optimized increased by 2.05%, 3.56%, 5.36% 1.2Qd, respectively. comparative characteristics reveals improved can be attributed matching between rotor stator. This research further demonstrates reliability artificial (ANN).

Language: Английский

Citations

44
Entropy generation minimization of a pump running in reverse mode based on surrogate models and NSGA-II DOI
Mohammad Mahdi Ghorani, Mohammad Hadi Sotoude Haghighi, Alireza Riasi

et al.

International Communications in Heat and Mass Transfer, Journal Year: 2020, Volume and Issue: 118, P. 104898 - 104898

Published: Oct. 4, 2020

Language: Английский

Citations

62
Investigation of unsteady pressure fluctuations and methods for its suppression for a double suction centrifugal pump DOI
Arihant Sonawat, Sung Kim,

Sang-Bum Ma

et al.

Energy, Journal Year: 2022, Volume and Issue: 252, P. 124020 - 124020

Published: April 16, 2022

Language: Английский

Citations

36
Blade redesign based on inverse design method for energy performance improvement and hydro-induced vibration suppression of a multi-stage centrifugal pump DOI
Jiantao Zhao, Ji Pei, Wenjie Wang

et al.

Energy, Journal Year: 2024, Volume and Issue: 308, P. 132862 - 132862

Published: Aug. 28, 2024

Language: Английский

Citations

8
Optimization Design and Internal Flow Characteristics Analysis Based on Latin Hypercube Sampling Method DOI
Guangjie Peng, Li’e Ma, Shiming Hong

et al.

Arabian Journal for Science and Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: June 25, 2024

Language: Английский

Citations

5
Internal flow structure, fault detection, and performance optimization of centrifugal pumps DOI
Zheming Tong, Jiage Xin,

Shuiguang Tong

et al.

Journal of Zhejiang University. Science A, Journal Year: 2020, Volume and Issue: 21(2), P. 85 - 117

Published: Feb. 1, 2020

Language: Английский

Citations

39
Application of intelligent methods in energy efficiency enhancement of pump system: A review DOI Creative Commons
Xingcheng Gan, Ji Pei, Giorgio Pavesi

et al.

Energy Reports, Journal Year: 2022, Volume and Issue: 8, P. 11592 - 11606

Published: Sept. 19, 2022

Energy consumption around the world is growing at an alarming rate. That brings enormous pressure on energy production and environmental issues. Nowadays, efficiency enhancement strategies are considered crucial approaches to release this problem. The pumps accounts for nearly 21% of electricity industrial motor-driven systems. Hence, much research focused improving their According works literature, level design most applications already extremely high while system performance could be further improved by regulations, average savings potential achievable through pump adjustments about 30%. This paper focuses advanced characteristic modeling methods, regulation parallel pumping system. A comprehensive summary traditional scheduling methods based computational intelligence has been made provide insight future research.

Language: Английский

Citations

22
Improving the Modeling of Pressure Pulsation and Cavitation Prediction in a Double-Volute Double-Suction Pump Using Mosaic Meshing Technology DOI Open Access
Virgel M. Arocena, Louis Angelo M. Danao

Processes, Journal Year: 2023, Volume and Issue: 11(3), P. 660 - 660

Published: Feb. 22, 2023

Over the years, Computational Fluid Dynamics (CFD) has been an integral part of most pump design processes. Unfortunately, as calculation schemes and flow investigations become more complicated, cost conducting numerical simulations also becomes expensive in terms computational time. To remedy this, cutting-edge technology, together with novel techniques, are continuously introduced end target producing accurate results faster computing In this paper, CFD run on a model double-volute double-suction prepared using ANSYS Fluent Mosaic meshing technology. Poly-Hexcore, first application fills bulk region octree hexes, keeps high-quality layered poly-prism mesh boundary layer, conformally connects these two meshes general polyhedral elements. This technology promises to provide lower number cells along significant increase speed. steady state Poly-Hexcore ~37% fewer produced comparable similarly sized multi-block structured hexagonal mesh. The predicted head, efficiency shaft power under conditions were within 1% for both models, while time was reduced by ~25%. Additional showed that able closely predict pump’s NPSH3 0.8QD, 1.0QD, 1.2QD compared manufacturer’s data. Under cavitating conditions, formation vapor bubbles observed suction side, starting at leading edge blade slowly forming thin sheets towards trailing pressure is reduced. Lastly, fluctuations from coefficient data collected several monitoring points volute impeller. It seen due interaction between stationary casing rotating impeller, pulsations equivalent passing frequency its harmonics.

Language: Английский

Citations

12
Unsteady flow characteristics and cavitation prediction in the double-suction centrifugal pump using a novel approach DOI
Ji Pei, Majeed Koranteng Osman, Wenjie Wang

et al.

Proceedings of the Institution of Mechanical Engineers Part A Journal of Power and Energy, Journal Year: 2019, Volume and Issue: 234(3), P. 283 - 299

Published: July 24, 2019

The recent advances in centrifugal pump design do not only require a better suction performance but also there have been attempts to reduce time at lower cost. traditional trial-and-error optimization method, however, depends on the designer's experience, which requires longer cycles. This is because computational process of calculating net positive head required (NPSHr) involves several calculation steps and this consumes lot time. An investigation was therefore carried out test novel NPSHr prediction method double-suction using unsteady numerical simulations. In new approach, boundary pair introduced an algorithm used estimate good value for static pressure that correlates 3% drop determine critical cavitation point. Experiments were conducted validate hydraulic model. characteristic “sudden” head-drop very well predicted by approach three simulation steps. internal flow analysis showed 0.6 Q d , around volute tongue uneven NPSH = 10.06 m, inducing separation recirculation region. Attached cavities observed ring spiral domain. fluctuations analyzed dominant frequency outlet region blade passing frequency. Consequently, proved robust efficient would be alternative shorten during pumps.

Language: Английский

Citations

35