Two-Stage Hybrid Model for Efficiency Prediction of Centrifugal Pump

Liu, Yi; Xia, Zhaoshun; Deng, Hui‐Xiong; Zheng, Shi-Yi

doi:10.3390/s22114300

Cited by 6 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Efficiency η is a key performance parameter for evaluating the operating state of a centrifugal pump. It can be calculated for a given operating condition by using the experimentally measured flow rate Q, head H and shaft power N of the pump, according to equation ( 5) [19].…”

Section: Discussionmentioning

confidence: 99%

“…. , T as an example, the corresponding posterior probability P (GPR l |X t ) of the GPR model is defined as [19,41].…”

Section: Jgpr Modelmentioning

confidence: 99%

“…By combining these two approaches, a more accurate and robust predictive model can be developed. For instance, Liu et al [19] divided the efficiency of a centrifugal pump into two stages, the efficiency increase and efficiency decrease, and established a two-stage hybrid model using Gaussian process regression (GPR) and posterior probability. Although the new model accurately predicted all experimental data with a relative error less than 5%, there is still room for improvement at high flow rates.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of centrifugal pump performance parameters based on a multilayer hybrid model

Chai

Zhang

Xia

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

The present paper presents a multilayer hybrid model for sensorless measurement of pump operating status, with the objective of enabling safe and stable operations while reducing energy losses. The model takes easily measurable variables such as rotational frequency and valve opening as input features to predict the performance parameters of the centrifugal pump. By integrating Just-in-time learning (JITL) with Gaussian process regression (GPR) and leveraging the unique probability features of GPR, a JGPR is developed to extract valuable feature information. The JGPR sequentially predicts the flow rate, coefficient for dynamic head, and shaft power. The predicted values are extended to other input features, which can accurately capture the characteristics of the centrifugal pump and effectively replace the process of acquiring process parameters through sensors. Finally, the mechanism model is integrated into the multilayer JGPR model to calculate the performance parameters of centrifugal pump. The validation results indicate a strong agreement between predicted and experimental results, with predicted meeting performance parameters all engineering requirements. Compared to a single model, the multilayer hybrid model significantly improves the reliability of predictions, demonstrating the feasibility of using this approach to predict performance parameters. This research provides valuable insights into the measurement of sensorless pump operating states, enabling safe and efficient operation in complex conditions.

show abstract

Section: Discussionmentioning

confidence: 99%

“…. , T as an example, the corresponding posterior probability P (GPR l |X t ) of the GPR model is defined as [19,41].…”

Section: Jgpr Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of centrifugal pump performance parameters based on a multilayer hybrid model

Chai

Zhang

Xia

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, sometimes the difference between head and efficiency is small. Therefore, this paper used a more intuitive metric, the mean square error (MSE), to assess grid quality [17,22]. Additionally, the computational resources required for simulation were recorded.…”

Section: Fluid Domain and Meshmentioning

confidence: 99%

Research on the Flow Characteristics of Power-Law Fluids in Self-Priming Sewage Pumps

Li,

Zheng,

Shao

et al. 2024

Water

Self Cite

View full text Add to dashboard Cite

To conduct a more in-depth study of the flow mechanism of power-law fluids within sewage pumps, this paper focuses on self-priming sewage pumps, with typical power-law fluid (Carboxymethyl Cellulose, CMC) as the conveying medium. The constitutive equations for sewage and typical power-law fluid (CMC solution) were established using the power-law model. Through numerical calculation methods, the non-steady flow field inside the pump of different concentration power-law fluids was analyzed from various aspects such as velocity, pressure, vorticity, and wall shear stress. The pressure pulsations at key locations in the pump flow field were monitored and analyzed. At the rated flow rate, when the concentration of CMC solution increased from 0.5% to 2.0%, the channel pressure and tongue pressure decreased by 16.5% and 3.5%, respectively. This indicates that the pressure on the impeller blades, within the flow passages, and at the tongue of the volute all decrease with the increase in concentration of CMC solution. This may alter the fluid flow pattern, leading to more vortex motion and shear deformation, while also reducing the pump’s pressure boosting capability, thereby affecting the pump’s performance stability. It can be inferred from quantitative comparisons that changes in rheological properties had a significant impact on the flow characteristics of sewage pumps. This paper reveals that some flow characteristics of power-law fluids in sewage pumps, providing a theoretical and reference basis for the performance optimization and flow mechanism research of sewage pumps.

show abstract