Volume Flow Rate Optimization of an Axial Fan by Artificial Neural Network and Genetic Algorithm

Zhang, Yingkun; Wang, Yu; Li, Jingyin

doi:10.4236/ojfd.2019.93014

Cited by 4 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An axial fan is one of the most used fluid machineries. And most of the research related to fluid machinery focuses on the adjustable blades (Li et al, 2007) and the rotor tip area (Zhang et al, 2019). Varade et al (Varade et al, 2015) used a threedimensional Navier-Stokes equations simulation method to study the effects of swept and leaned blades on the fan flow field.…”

Section: Introductionmentioning

confidence: 99%

IGV Optimization for a Large Axial Flow Fan Based on MRGP Model and Sobol’ Method

Zhou

et al. 2022

Front. Energy Res.

View full text Add to dashboard Cite

Large axial flow fans with inlet guide vanes (IGVs) have been widely used in building ventilation systems. However, it does not readily satisfy the increasing demand for energy saving, high efficiency, or noise reduction. The rotor-stator interaction between the IGVs and the impeller is particularly important for the aerodynamic performance and noise of the fans. Therefore, this article takes a large axial fan, combined with parameterization methods to optimize the IGVs. Based on numerical simulation analysis, the multiple-response Gaussian process (MRGP) approximate model was established to optimize the IGVs structure, and the Sobol´ method was employed for sensitivity analysis. The best model was selected for proofing analysis, and the experimental and numerical simulation results show that the total pressure of the optimized fan increased by 144.4 Pa and the noise decreased by 7.2 dB. These results verify that the multi-objective optimization design method combining the MRGP approximate model and the Sobol´ method demonstrates high credibility and provides a key design direction for the design optimization of large axial flow fans. This novel optimization method also has easy-to-understand parameters and the coupling relationships between parameters and responses, which has potential value for the design of other types of fluid machinery and provides new ideas for the optimization of fluid machinery.

show abstract

Section: Introductionmentioning

confidence: 99%

IGV Optimization for a Large Axial Flow Fan Based on MRGP Model and Sobol’ Method

Zhou

et al. 2022

Front. Energy Res.

View full text Add to dashboard Cite

show abstract

“…by using the global optimization algorithm has the advantages of less calculation and accurate optimization results. It is often used in fluid machinery such as fan, 7–10 pump, 11–13 compressor, 14–16 pump-turbine, 17 etc. Due to the complexity of the structure of the range hood and a large number of impeller blades of the squirrel cage fan, the numerical calculation of the whole range hood system is large, and the multi-objective optimization method using the surrogate model mentioned above model can effectively reduce the number of CFD.…”

Section: Introductionmentioning

confidence: 99%

Multi-objective optimization of squirrel cage fan for range hood based on Kriging model

Xiao

Wang

Jiang

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

In view of the multi-objective optimization design of the squirrel cage fan for the range hood, a blade parameterization method based on the quadratic non-uniform B-spline (NUBS) determined by four control points was proposed to control the outlet angle, chord length and maximum camber of the blade. Morris-Mitchell criteria were used to obtain the optimal Latin hypercube sample based on the evolutionary operation, and different subsets of sample numbers were created to study the influence of sample numbers on the multi-objective optimization results. The Kriging model, which can accurately reflect the response relationship between design variables and optimization objectives, was established. The second-generation Non-dominated Sorting Genetic algorithm (NSGA-II) was used to optimize the volume flow rate at the best efficiency point (BEP) and the maximum volume flow rate point (MVP). The results show that the design parameters corresponding to the optimization results under different sample numbers are not the same, and the fluctuation range of the optimal design parameters is related to the influence of the design parameters on the optimization objectives. Compared with the prototype, the optimized impeller increases the radial velocity of the impeller outlet, reduces the flow loss in the volute, and increases the diffusion capacity, which improves the volume flow rate, and efficiency of the range hood system under multiple working conditions.

show abstract

Design of Transmission Line Maintenance Tool Based on Artificial Neural Network Algorithm

Zhang,

Mu,

Zhao

et al. 2023

2023 International Conference on Power, Electrical Engineering, Electronics and Control (PEEEC)

View full text Add to dashboard Cite

Volume Flow Rate Optimization of an Axial Fan by Artificial Neural Network and Genetic Algorithm

Cited by 4 publications

References 17 publications

IGV Optimization for a Large Axial Flow Fan Based on MRGP Model and Sobol’ Method

IGV Optimization for a Large Axial Flow Fan Based on MRGP Model and Sobol’ Method

Multi-objective optimization of squirrel cage fan for range hood based on Kriging model

Design of Transmission Line Maintenance Tool Based on Artificial Neural Network Algorithm

Contact Info

Product

Resources

About