Multi-objective optimization and characteristic analysis of contra-rotating fan double-row blades coupling
To enhance the aerodynamic performance of contra-rotating fan and ensure the safe working environment of mine, based on feedforward neural network agent model and genetic algorithm, the multi-objective optimization of contra-rotating fan double-row blades coupling is carried out. Initially, double-r...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Safety in Coal Mines
2025-07-01
|
| Series: | Meikuang Anquan |
| Subjects: | |
| Online Access: | https://www.mkaqzz.com/cn/article/doi/10.13347/j.cnki.mkaq.20241623 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849429697446805504 |
|---|---|
| author | Xinyu ZHANG Hua JIANG Wuqi GONG |
| author_facet | Xinyu ZHANG Hua JIANG Wuqi GONG |
| author_sort | Xinyu ZHANG |
| collection | DOAJ |
| description | To enhance the aerodynamic performance of contra-rotating fan and ensure the safe working environment of mine, based on feedforward neural network agent model and genetic algorithm, the multi-objective optimization of contra-rotating fan double-row blades coupling is carried out. Initially, double-row blades of the contra-rotating fan are parameterized, with the installation angles of each blade’s height span and the control parameters of the mean cambers selected as high-dimensional optimization variables. Secondly, Latin hypercube sampling is conducted in the high-dimensional decision space to obtain the decision sample set, and the aerodynamic sample set corresponding to the decision sample set is solved through numerical simulation. The sample set data is used to construct a neural network surrogate model, and the weights and thresholds of the neural network are optimized in combination with the genetic algorithm to improve the generalization ability of the surrogate model. The optimization objectives focus on maximizing total pressure efficiency of contra-rotating fan at low, design and high flow rates, with genetic algorithm used for global optimization to output the Pareto optimal solution set, the optimal geometric parameter combinations that maximize total pressure efficiency across all operating conditions are then determined, leading to the optimized contra-rotating fan model; the optimization results are verified by numerical simulation, and the aerodynamic performance and flow field distribution of the contra-rotating fan before and after optimization are compared. The results indicate that the overall pressure efficiency of contra-rotating fan has improved by 0.59%, 0.88% and 1.21% under low, design and high mass flow rates, respectively, significantly broadening the range of stable operating conditions; after optimization, the increase of the first-stage blade installation angle can improve the flow stability while causing partial energy loss, and the decrease of the second-stage blade installation angle can increase the blade’s work ability and improve the impeller’s aerodynamic efficiency; the range and entropy of the high entropy area near the tip of the two-stage blade are reduced, the flow separation and wake loss are weakened, the relative velocity distribution of the tip section is improved, and the adaptability of contra-rotating fan to the change of mass flow rate is enhanced. |
| format | Article |
| id | doaj-art-2be68100af0c4fa68fb22065f1d99fc7 |
| institution | Kabale University |
| issn | 1003-496X |
| language | zho |
| publishDate | 2025-07-01 |
| publisher | Editorial Office of Safety in Coal Mines |
| record_format | Article |
| series | Meikuang Anquan |
| spelling | doaj-art-2be68100af0c4fa68fb22065f1d99fc72025-08-20T03:28:17ZzhoEditorial Office of Safety in Coal MinesMeikuang Anquan1003-496X2025-07-0156719420410.13347/j.cnki.mkaq.20241623jMKAQ20241623Multi-objective optimization and characteristic analysis of contra-rotating fan double-row blades couplingXinyu ZHANG0Hua JIANG1Wuqi GONG2School of Energy, Xi’an University of Science and Technology, Xi’an 710054, ChinaSchool of Energy, Xi’an University of Science and Technology, Xi’an 710054, ChinaSchool of Energy and Power Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaTo enhance the aerodynamic performance of contra-rotating fan and ensure the safe working environment of mine, based on feedforward neural network agent model and genetic algorithm, the multi-objective optimization of contra-rotating fan double-row blades coupling is carried out. Initially, double-row blades of the contra-rotating fan are parameterized, with the installation angles of each blade’s height span and the control parameters of the mean cambers selected as high-dimensional optimization variables. Secondly, Latin hypercube sampling is conducted in the high-dimensional decision space to obtain the decision sample set, and the aerodynamic sample set corresponding to the decision sample set is solved through numerical simulation. The sample set data is used to construct a neural network surrogate model, and the weights and thresholds of the neural network are optimized in combination with the genetic algorithm to improve the generalization ability of the surrogate model. The optimization objectives focus on maximizing total pressure efficiency of contra-rotating fan at low, design and high flow rates, with genetic algorithm used for global optimization to output the Pareto optimal solution set, the optimal geometric parameter combinations that maximize total pressure efficiency across all operating conditions are then determined, leading to the optimized contra-rotating fan model; the optimization results are verified by numerical simulation, and the aerodynamic performance and flow field distribution of the contra-rotating fan before and after optimization are compared. The results indicate that the overall pressure efficiency of contra-rotating fan has improved by 0.59%, 0.88% and 1.21% under low, design and high mass flow rates, respectively, significantly broadening the range of stable operating conditions; after optimization, the increase of the first-stage blade installation angle can improve the flow stability while causing partial energy loss, and the decrease of the second-stage blade installation angle can increase the blade’s work ability and improve the impeller’s aerodynamic efficiency; the range and entropy of the high entropy area near the tip of the two-stage blade are reduced, the flow separation and wake loss are weakened, the relative velocity distribution of the tip section is improved, and the adaptability of contra-rotating fan to the change of mass flow rate is enhanced.https://www.mkaqzz.com/cn/article/doi/10.13347/j.cnki.mkaq.20241623contra-rotating fanparametric modelingneural networkgenetic algorithmmulti-objective optimization |
| spellingShingle | Xinyu ZHANG Hua JIANG Wuqi GONG Multi-objective optimization and characteristic analysis of contra-rotating fan double-row blades coupling Meikuang Anquan contra-rotating fan parametric modeling neural network genetic algorithm multi-objective optimization |
| title | Multi-objective optimization and characteristic analysis of contra-rotating fan double-row blades coupling |
| title_full | Multi-objective optimization and characteristic analysis of contra-rotating fan double-row blades coupling |
| title_fullStr | Multi-objective optimization and characteristic analysis of contra-rotating fan double-row blades coupling |
| title_full_unstemmed | Multi-objective optimization and characteristic analysis of contra-rotating fan double-row blades coupling |
| title_short | Multi-objective optimization and characteristic analysis of contra-rotating fan double-row blades coupling |
| title_sort | multi objective optimization and characteristic analysis of contra rotating fan double row blades coupling |
| topic | contra-rotating fan parametric modeling neural network genetic algorithm multi-objective optimization |
| url | https://www.mkaqzz.com/cn/article/doi/10.13347/j.cnki.mkaq.20241623 |
| work_keys_str_mv | AT xinyuzhang multiobjectiveoptimizationandcharacteristicanalysisofcontrarotatingfandoublerowbladescoupling AT huajiang multiobjectiveoptimizationandcharacteristicanalysisofcontrarotatingfandoublerowbladescoupling AT wuqigong multiobjectiveoptimizationandcharacteristicanalysisofcontrarotatingfandoublerowbladescoupling |