Energy performance prediction of the centrifugal pumps by using a hybrid neural network

Mahardhika

2021

JRM

Diameter trimming is one of the most common modification on centrifugal pump impeller aimed to keep conformity between pump performance and required head and flow rate. In its application, centrifugal pump performance with trimmed diameter could be predicted by using affinity equations which based on geometrical similarity between pre- and post-trimming impeller. However, diameter trimming also alter the dimension ratio in blade passage which prompt further investigation on performance prediction of pump with trimmed impeller diameter. This research is carried out by using numerical simulation to analyze performance of pump with trimmed impeller diameter. The simulation is conducted on radial-type centrifugal pump with impeller diameter 105 mm, inlet blade angle 200, outlet blade angle 280, and operating on mass flow rate 1.5 kg/s at rotational speed 2800 rpm. RNG k-e model is used to model turbulence while trimmed diameter values are 100 mm and 95 mm. Results indicate that there is significant differences on head and consumed power between predicted value by simulation and predicted value obtained by employing affinity equations.

Section: Pendahuluanunclassified

Section: Gambar 2: Hasil Monitoring Residualunclassified

Analisis Kinerja Pompa Sentrifugal pada Variasi Trim Diameter Menggunakan Simulasi Numerik

Mahardhika

2021

JRM

Advances in Mechanical Engineering

“…3-5 1 Many interesting studies have been conducted to investigate and optimize the performance of standard centrifugal pumps. [6][7][8][9] Wang et al 10 numerically optimized the impeller based on the Latin Hypercube method and found that the efficiency of the optimized pump is improved, and the vibration intensity is attenuated. Zhang et al 11 investigated the effects of modifying the blade pressure side (EPS profile) on unsteady pressure pulsations and flow structures in a low specific speed centrifugal pump using experimental and numerical methods and found that the newly introduced EPS profile helps to reduce pressure pulsations and improves the uniformity of the flow field in the blade trailing edge region.…”

Section: Introductionmentioning

confidence: 99%

Optimization and CFD performance analysis of an automotive coolant pump

Liu

Jiang

Yong

et al. 2022

The blade outlet angle, wrap angle, and number of blades of the impeller are optimized to increase the pumping efficiency of the automotive coolant pump while keeping the size constant. Three new variants were designed and the optimal one was selected for the comparison with the original scheme. The experiment was conducted to test the hydraulic performance of the optimized impeller. The results show that the energy characteristics of the optimized impeller are in reasonable agreement with the experimental data. The energy characteristics and internal flow details of original scheme and optimized scheme are analyzed and compared. It was found that increasing the wrap angle while decreasing blade outlet angle appropriately can improve the flow conditions and the pressure distribution in the impeller and the volute, especially at low flow rates. At the designed flow rate, increasing the wrap angle while decreasing the number of blades and blade outlet angle can significantly increase the efficiency of the pump. And the maximum efficiency of the optimized impeller is 4.8% higher than the efficiency of the original impeller. The results of the study can guide designers in optimizing an automotive centrifugal coolant pump and reduce energy consumption of the automotive cooling system.

Proceedings of the Institution of Mechanical Engineers, Part C:

“…30 Mathematically modeling the head, efficiency, shaft power and other performances of centrifugal pump by neural network is a research hotspot in recent years. 31–33 In this study, a typical centrifugal impeller is studied in pump mode. 34 Through large quantity of numerical simulation samples and neural network training and prediction samples, the reason of neural network fitting the correlation between centrifugal pump blade angles and performance is explained, the influences of blade profile including installation angles and wrap angles on pump performance are discussed in detail with abundant statistical investigations.…”

Section: Introductionmentioning

confidence: 99%

A machine-learning approach to predicting the energy conversion performance of centrifugal pump impeller influenced by blade profile

Tao

Zhu

et al. 2021

Centrifugal pump is a kind of energy conversion machine for fluid delivering. It transfers the mechanical energy of impeller to the potential and kinetic energy of fluid. As a key factor in influencing the energy conversion performance of centrifugal pump, blade profile design is crucial. Traditional design concepts have ideal assumptions. To have a better design guidance, machine-learning based on neural network is used in this study. A typical centrifugal pump with simplified blade profile is numerically studied with experimental validation for a better discussion. Statistical results show that, for the high dimensional nonlinear relationship between blade angle and performance of centrifugal pump, neural network can adapt to this complex correlation better. The blade installation angle at leading-edge ( βLE′) and trailing-edge ( βTE′) and the wrap angle (Δ θ′) has significant correlation with the performance including pump head H, pump efficiency η, impeller head Himp, impeller efficiency ηimp and volute loss Δ Hvol. The influence level of blade angle follows the high-to-low order of Δ θ′, βLE′ and βTE′. Determination of blade profile can be done for improving the energy conversion efficiency. Optimal blade profiles have higher βLE′ and Δ θ′ with better flow-control ability. Compared with the blade parameters of the initial pump, the blade profile with the best centrifugal pump efficiency is the best βLE′ increased by 1.926°, Δ θ′ increased by 9.858°, Optimization of impeller efficiency βLE′ increased by 1.855°, Δ θ′ increased by 9.421°. Computational fluid dynamics indicate the elimination of vortex in impeller after optimal selection. Then, βTE′ and Δ θ′ are found influential in aggravating the circumferential flow component in this special circular-volute with generating higher loss. βTE′ has a positive correlation with impeller head which suits traditional theory. In general, the machine-learning using neural network is effective in determining blade profiles for enhancing the performance of centrifugal pump.