CN112084597A - Single-exhaust-film cooling efficiency two-dimensional distribution AI prediction method based on bell-shaped curve - Google Patents
Single-exhaust-film cooling efficiency two-dimensional distribution AI prediction method based on bell-shaped curve Download PDFInfo
- Publication number
- CN112084597A CN112084597A CN202010937116.3A CN202010937116A CN112084597A CN 112084597 A CN112084597 A CN 112084597A CN 202010937116 A CN202010937116 A CN 202010937116A CN 112084597 A CN112084597 A CN 112084597A
- Authority
- CN
- China
- Prior art keywords
- cooling efficiency
- bell
- parameters
- dimensional distribution
- shaped curve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
- F01D5/00—Blades; Blade-carrying members; Heating, heat-insulating, cooling or antivibration means on the blades or the members
- F01D5/12—Blades
- F01D5/14—Form or construction
- F01D5/18—Hollow blades, i.e. blades with cooling or heating channels or cavities; Heating, heat-insulating or cooling means on blades
- F01D5/186—Film cooling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Fluid Mechanics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A bell-shaped curve-based AI prediction method for two-dimensional distribution of cooling efficiency of a single exhaust film relates to the field of aero-engines and solves the problems that the prediction result is relatively flat and the specific distribution of the cooling efficiency of the film on a cooling surface cannot be reflected by predicting a central line and the average cooling efficiency in the conventional cooling efficiency method. And then, constructing different working conditions according to the influence parameters to calculate three-dimensional data to obtain a flat plate surface cooling efficiency database. And then processing the database by using the bell-shaped curve distribution of the cooling efficiency in the transverse direction to obtain a new database. And finally, establishing a two-dimensional distribution neural network prediction model of the cooling efficiency by using the new database and the determined input-output parameters to obtain a two-dimensional adiabatic cooling efficiency distribution cloud chart of the flat plate single-row cylindrical holes.
Description
Technical Field
The invention relates to the field of aircraft engines, in particular to a single exhaust film cooling efficiency two-dimensional distribution prediction method based on an artificial intelligence algorithm.
Background
The turbine is one of the important parts of the aeroengine, and the working environment is very severe. The turbine front temperature of the prior advanced aeroengine reaches about 2000K and is higher than the temperature resistance limit of metal materials of turbine blades, so that an advanced cooling technology is required. The main cooling mode of the turbine blade of the aero-engine is air film cooling, and the turbine blade is a thermal protection measure for blocking the wall surface heating of main gas flow by spraying a coolant from a nozzle on a high-temperature wall surface, wherein the nozzle can be a two-dimensional seam or a hole row. The main flow parameters affecting the film cooling performance include blowing ratio, density ratio and main flow turbulence, and the main geometric parameters include jet angle, film hole length-diameter ratio, film hole interval, hole row number and hole geometry. The film cooling design is a process which needs to be iterated repeatedly, and therefore the adiabatic cooling efficiency of the film cooling needs to be obtained quickly and accurately.
Currently, common methods for predicting film cooling efficiency include empirical formula method and Computational Fluid Dynamics (CFD) method. However, the application range of the empirical formula is narrow, only some parameters with larger influence are researched, and the air film cooling prediction result of the real turbine blade is easy to have larger deviation; the Computational Fluid Dynamics (CFD) method requires a great amount of meshes for three-dimensional numerical simulation of a complex cooling structure, and the workload of mesh division and the calculation time length bring great obstacles to the design of the cooling structure. Therefore, a more efficient and accurate cooling efficiency prediction method is needed.
In recent years, aiming at the complex action form of film cooling, the prior art attempts to predict the film cooling efficiency by using a new modeling means, for example, a neural network-based method predicts the film cooling and obtains a better prediction result. In the paper [ Qinyan 26107073, Lixuen, conception, Jianghud, multiparameter air film cooling efficiency research [ J ] engineering thermophysics, 2011] based on BP neural network, experimental data in a large number of documents are used as training sets and test sets, parameters which have large influence on air film cooling efficiency, such as dimensionless flow direction distance X/D, blowing ratio M, density ratio DR, mainstream turbulence degree Tu, area ratio AR, hole pitch ratio P/D, are selected as input parameters of the neural network, and after training, the neural network can finally quickly and accurately obtain a central line, transverse average adiabatic cooling efficiency and a heat transfer coefficient ratio curve and can output in a data file format.
The above prediction method regarding cooling efficiency: the traditional empirical formula method and the traditional computational fluid dynamics method have certain limitations, but the traditional methods for predicting the cooling efficiency of the air film by the artificial intelligence only predict the central line and the average cooling efficiency, the prediction result is relatively smooth, and the specific distribution of the cooling efficiency of the air film on the cooling surface cannot be reflected.
Disclosure of Invention
The invention provides a bell-shaped curve-based two-dimensional distribution AI prediction method for single exhaust film cooling efficiency, which aims to solve the problems that the prediction result is relatively unilateral and the specific distribution of the film cooling efficiency on the cooling surface cannot be reflected by predicting the central line and the average cooling efficiency in the conventional cooling efficiency method. The iteration speed of the cooling structure design is improved.
The method combines a neural network and a bell-shaped curve to obtain the two-dimensional distribution of the heat insulation cooling efficiency of a flat plate single exhaust film hole, namely the local cooling efficiency; the method is specifically realized by the following steps:
extracting influence parameters influencing air film cooling efficiency, and constructing different working conditions according to the influence parameters influencing the air film cooling efficiency to carry out three-dimensional data calculation to obtain a flat plate surface cooling efficiency database;
step two, obtaining a variation curve of local cooling efficiency along with the transverse distance when the flow direction distance is fixed according to the flat plate surface cooling efficiency database in the step one; obtaining a function expression and parameters of the function expression of each curve graph according to the cooling efficiency change curve; constructing a new database by using the influencing factors of the cooling efficiency and the parameters of the function expression;
and step three, taking the influence parameters of the cooling efficiency in the new database constructed in the step two as the input of the neural network, taking the parameters of the function expression as the output to train the neural network, outputting the parameters through the trained neural network, and finally substituting the transverse distance into the function expression in the step two to obtain the two-dimensional distribution prediction model of the cooling efficiency.
The invention has the beneficial effects that:
(1) compared with the traditional formula method, the prediction method can predict the air film cooling efficiency under the action of various influence factors; compared with a computational fluid mechanics method, the method can rapidly obtain the two-dimensional distribution of the cooling efficiency, and for a flat plate cooling structure, the computational fluid mechanics method needs to grid the model firstly and then carry out numerical calculation for a long time; and the trained neural network can obtain two-dimensional distribution of cooling efficiency by running a program once.
(2) Compared with the existing prediction method of the air film cooling neural network, the prediction method of the invention focuses on predicting the flow distribution (central line cooling efficiency) of the air film cooling efficiency aiming at the research of the air film cooling efficiency prediction by the current researchers, but the prediction method of the invention can predict the transverse distribution of the air film cooling efficiency, improves the prediction precision by utilizing the bell-shaped curve distribution rule of the cooling efficiency in the transverse direction, and obtains the bell-shaped curve-based two-dimensional distribution AI prediction method of the single exhaust film cooling efficiency
Drawings
Fig. 1 is a schematic diagram of a bell-curve-based two-dimensional distribution AI prediction method for single-exhaust film cooling efficiency according to the present invention.
Fig. 2 is a graph showing the comparison effect between the predicted result and the CFD calculation result, wherein (a) is a schematic view of the CFD calculation result, and (b) is a schematic view of the predicted result using the method of the present invention.
Detailed Description
In the first embodiment, the first embodiment is described with reference to fig. 1, and the bell-shaped curve-based AI prediction method for two-dimensional distribution of cooling efficiency of a single exhaust film is implemented by combining computational fluid dynamics simulation software, an artificial neural network and a bell-shaped curve to quickly and accurately obtain two-dimensional distribution of adiabatic cooling efficiency of a flat plate single exhaust film hole. The specific implementation process is as follows:
firstly, accumulating cooling efficiency data based on computational fluid dynamics simulation software: for many influencing factors of the air film cooling efficiency, main 7 influencing parameters are extracted: density ratio DR ═ ρ2/ρ∞(wherein ρ is2Is the cold gas density, ρ∞Main stream density), blow ratio M ═ ρ2v2/ρ∞v∞(in the formula v2Is the velocity of cold air, v∞The main flow density), the main flow turbulence TU, the incident angle beta, the length-diameter ratio L/D of a gas film hole, the flow direction distance X/D and the transverse distance Z/D are subjected to three-dimensional numerical calculation under different working conditions to obtain a flat plate surface cooling efficiency database.
Secondly, data processing based on bell-shaped curve distribution:
bell curve based data processing: obtaining a change curve of local cooling efficiency along with a transverse distance Z/D when the flow direction distance X/D is fixed based on a flat plate surface cooling efficiency database; according to cooling efficiency etaLFitting the transverse distribution curve graphs to obtain a function expression of the bell-shaped curve corresponding to each curve graph
Wherein y represents the cooling efficiency ηLX represents the transverse distance Z/D, converted to an expression
And finally, forming a new database by using the influencing factors of the cooling efficiency and the parameters a, b and c of the function expression.
Thirdly, training and predicting data based on the BP neural network:
and a new database which is formed by the influencing factors of the cooling efficiency and the parameters a, b and c of the functional expression, wherein 90 percent of the database is used as training data, and 10 percent of the database is used as test data. Taking the influence factor of the cooling efficiency as the input of the neural network, taking the parameters a, b and c of the function expression as the output to train the neural network, obtaining the parameters a, b and c through the trained neural network, and finally substituting the transverse distance Z/D into the predicted expression
The local cooling efficiency eta of any point (X/D, Z/D) of the two-dimensional plane can be obtainedLAnd finally obtaining an accurate two-dimensional distribution prediction model of the cooling efficiency.
Second embodiment, the present embodiment is described with reference to fig. 1 and 2, and the present embodiment is an example of a bell-shaped curve-based two-dimensional distribution AI prediction method for single exhaust film cooling efficiency according to the first embodiment: the flow of predicting the two-dimensional distribution of the cooling efficiency of the surface of the flat plate in the embodiment is as follows:
(1) and obtaining an air film cooling efficiency database of the flat plate single-row cylindrical cooling holes under different working conditions through computational fluid mechanics simulation software.
(2) And carrying out data processing on the numerical calculation database by using bell-shaped curve fitting to obtain a new database containing the influence factors of the cooling efficiency and the function expression parameters a, b and c.
(3) And taking 90% of data in the new database as a neural network training set, and taking 10% of data in the new database as a test set to perform neural network training.
(4) Obtaining function expression parameters a, b and c through a trained neural network, and substituting the transverse distance Z/D into a predicted expression
The cooling efficiency eta of any point (X/D, Z/D) of the two-dimensional plane can be obtainedLAnd obtaining the two-dimensional distribution of the heat insulation cooling efficiency of the flat plate single exhaust film hole.
Referring to fig. 2, it can be seen from comparison between the CFD calculation result and the final prediction result that the cooling efficiency prediction model obtained by the method of the present embodiment can rapidly and accurately obtain the two-dimensional distribution of the film cooling efficiency. The cooling efficiency prediction result is closer to the CFD numerical calculation result, and the predicted average relative error is within 5 percent, which shows that the prediction model obtained by the embodiment not only can intuitively reflect the specific distribution of the cooling efficiency on the cooling surface, but also has a better prediction result.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (4)
1. The bell-shaped curve-based two-dimensional distribution AI prediction method for the cooling efficiency of the single exhaust film is characterized by comprising the following steps of: the method combines a neural network with a bell-shaped curve to obtain the two-dimensional distribution of the adiabatic cooling efficiency of the flat single-row gas film hole, namely the local cooling efficiency; the method is specifically realized by the following steps:
extracting influence parameters influencing air film cooling efficiency, and constructing different working conditions according to the influence parameters influencing the air film cooling efficiency to carry out three-dimensional data calculation to obtain a flat plate surface cooling efficiency database;
step two, obtaining a variation curve of local cooling efficiency along with the transverse distance when the flow direction distance is fixed according to the flat plate surface cooling efficiency database in the step one; obtaining a function expression and parameters of the function expression of each curve graph according to the cooling efficiency change curve; constructing a new database by using the influencing factors of the cooling efficiency and the parameters of the function expression;
and step three, taking the influence parameters of the cooling efficiency in the new database constructed in the step two as the input of the neural network, taking the parameters of the function expression as the output to train the neural network, outputting the parameters through the trained neural network, and finally substituting the transverse distance into the function expression in the step two to obtain the two-dimensional distribution prediction model of the cooling efficiency.
2. The bell-shaped curve based single exhaust film cooling efficiency two-dimensional distribution AI prediction method of claim 1 wherein: the influencing parameters in the step one comprise a blowing ratio M, a density ratio DR, a mainstream turbulence TU, an incidence angle beta, a gas film hole length-diameter ratio L/D, a flow direction distance X/D and a transverse distance Z/D.
3. The bell-shaped curve based single exhaust film cooling efficiency two-dimensional distribution AI prediction method of claim 1 wherein: in the second step:
according to cooling efficiency etaLFitting the transverse distribution curve graphs to obtain a function expression of the bell-shaped curve corresponding to each curve graph
Wherein y is the cooling efficiency etaLX is the transverse distance Z/D, and the expression is obtained by conversion
And (4) forming a new database by using the influence parameters of the cooling efficiency and the parameters a, b and c of the functional expression.
4. The bell-shaped curve based single exhaust film cooling efficiency two-dimensional distribution AI prediction method of claim 1 wherein: in step three, substituting the transverse distance Z/D into the predicted expression
Obtaining the local cooling efficiency eta of any point (X/D, Z/D) of the two-dimensional planeL；
And finally, converting the output of the prediction model into a TECPLET file format through MATLAB, and importing the TECPLET file to display a cooling efficiency two-dimensional distribution cloud map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010937116.3A CN112084597B (en) | 2020-09-08 | 2020-09-08 | Single-exhaust-film cooling efficiency two-dimensional distribution AI prediction method based on bell-shaped curve |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010937116.3A CN112084597B (en) | 2020-09-08 | 2020-09-08 | Single-exhaust-film cooling efficiency two-dimensional distribution AI prediction method based on bell-shaped curve |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112084597A true CN112084597A (en) | 2020-12-15 |
| CN112084597B CN112084597B (en) | 2021-06-15 |
Family
ID=73732482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010937116.3A Active CN112084597B (en) | 2020-09-08 | 2020-09-08 | Single-exhaust-film cooling efficiency two-dimensional distribution AI prediction method based on bell-shaped curve |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112084597B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7887294B1 (en) * | 2006-10-13 | 2011-02-15 | Florida Turbine Technologies, Inc. | Turbine airfoil with continuous curved diffusion film holes |
| CN104088671A (en) * | 2014-07-10 | 2014-10-08 | 东北电力大学 | Air film cooling effect orthogonality prediction method based on multi-parameter influences |
| CN105865521A (en) * | 2016-04-01 | 2016-08-17 | 浙江清华长三角研究院 | Intelligent fishery breeding online system |
| CN107194118A (en) * | 2017-06-19 | 2017-09-22 | 南京航空航天大学 | A kind of hot cooperative optimization method of turbo blade scallop hole gaseous film control structural air |
| CN107908816A (en) * | 2017-10-13 | 2018-04-13 | 北京航空航天大学 | Aero-engine cooling and the integrated design method of cooling air based on hollow fan blade |
| CN108399282A (en) * | 2018-01-30 | 2018-08-14 | 中国科学院工程热物理研究所 | Gas turbine air-cooled turbine air film hole optimization method |
| CN108846261A (en) * | 2018-04-26 | 2018-11-20 | 浙江工业大学 | Gene expression time series data classification method based on visual nomography |
| CN109189933A (en) * | 2018-09-14 | 2019-01-11 | 腾讯科技（深圳）有限公司 | A kind of method and server of text information classification |
| CN109751972A (en) * | 2019-03-01 | 2019-05-14 | 北京金轮坤天特种机械有限公司 | The cooling air film hole detection platform of high-pressure turbine working blade and test method |
| CN110210607A (en) * | 2019-06-05 | 2019-09-06 | 河南大学 | PearsonIII type parameter of curve prediction technique based on BP neural network model |
| CN110259520A (en) * | 2019-07-10 | 2019-09-20 | 西北工业大学 | A kind of design method of shaped air film cooling hole |
-
2020
- 2020-09-08 CN CN202010937116.3A patent/CN112084597B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7887294B1 (en) * | 2006-10-13 | 2011-02-15 | Florida Turbine Technologies, Inc. | Turbine airfoil with continuous curved diffusion film holes |
| CN104088671A (en) * | 2014-07-10 | 2014-10-08 | 东北电力大学 | Air film cooling effect orthogonality prediction method based on multi-parameter influences |
| CN105865521A (en) * | 2016-04-01 | 2016-08-17 | 浙江清华长三角研究院 | Intelligent fishery breeding online system |
| CN107194118A (en) * | 2017-06-19 | 2017-09-22 | 南京航空航天大学 | A kind of hot cooperative optimization method of turbo blade scallop hole gaseous film control structural air |
| CN107908816A (en) * | 2017-10-13 | 2018-04-13 | 北京航空航天大学 | Aero-engine cooling and the integrated design method of cooling air based on hollow fan blade |
| CN108399282A (en) * | 2018-01-30 | 2018-08-14 | 中国科学院工程热物理研究所 | Gas turbine air-cooled turbine air film hole optimization method |
| CN108846261A (en) * | 2018-04-26 | 2018-11-20 | 浙江工业大学 | Gene expression time series data classification method based on visual nomography |
| CN109189933A (en) * | 2018-09-14 | 2019-01-11 | 腾讯科技（深圳）有限公司 | A kind of method and server of text information classification |
| CN109751972A (en) * | 2019-03-01 | 2019-05-14 | 北京金轮坤天特种机械有限公司 | The cooling air film hole detection platform of high-pressure turbine working blade and test method |
| CN110210607A (en) * | 2019-06-05 | 2019-09-06 | 河南大学 | PearsonIII type parameter of curve prediction technique based on BP neural network model |
| CN110259520A (en) * | 2019-07-10 | 2019-09-20 | 西北工业大学 | A kind of design method of shaped air film cooling hole |
Non-Patent Citations (4)
| Title |
|---|
| KI-DON LEE 等: "Design Optimization of a Fan-Shaped Film-Cooling Hole Using a Radial Basis Neural Network Techniques", 《THE KSFM JOURNAL OF FLUID MACHINERY》 * |
| 潘炳华 等: "旋转状态下气膜冷却效率试验研究", 《燃气涡轮试验与研究》 * |
| 秦晏旻 等: "基于BP神经网络的多参数气膜冷却效率研究", 《工程热物理学报》 * |
| 秦晏旻 等: "多参数影响下的气膜冷却特性及预测方法", 《热力透平》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112084597B (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106227967A (en) | Industrial steam turbine low-pressure stage group vane type line optimization method | |
| CN112818573B (en) | Method for acquiring boundary layer non-local variable information for unstructured grid | |
| CN107194118B (en) | Pneumatic-thermal collaborative optimization method for turbine blade fan-shaped hole air film cooling structure | |
| CN106897520B (en) | Heat transfer system reliability analysis method containing fuzzy parameters | |
| Huang et al. | Multi-objective optimization of laidback fan-shaped film cooling hole on Turbine Vane Suction Surface | |
| Xu et al. | A cost-effective CNN-BEM coupling framework for design optimization of horizontal axis tidal turbine blades | |
| CN106919730B (en) | Wind power plant wake flow determination method adopting wind speed attenuation factor | |
| Chen et al. | Knowledge-based turbomachinery design system via a deep neural network and multi-output Gaussian process | |
| CN112084597B (en) | Single-exhaust-film cooling efficiency two-dimensional distribution AI prediction method based on bell-shaped curve | |
| Zhou et al. | Design methods and strategies for forward and inverse problems of turbine blades based on machine learning | |
| Ilieva | Numerical modeling and research of 3D turbine stage | |
| Lin et al. | Effective boundary conditions and numerical method for flow characteristics of aeroengine compressor at high Mach flight | |
| El Ayoubi et al. | Optimization of film cooling holes on the suction surface of a high pressure turbine blade | |
| CN114297807A (en) | Method for optimizing parameters of flute-shaped tube structure of anti-icing system | |
| Wang et al. | Data mining optimization of laidback fan-shaped hole to improve film cooling performance | |
| Ngetich et al. | A 3D conjugate approach for analysing a double-walled effusion-cooled turbine blade | |
| Yuan et al. | Optimal shape design and performance investigation of the diffuser for infrared suppression (IRS) device applying MO-SHERPA | |
| Wu et al. | A Combined Data-Driven and Simulation Approach for Wind Turbine Blade Icing Prediction in Cold Regions | |
| Wright | Validation Process for LEWICE by Use of a Naviér-Stokes Solver | |
| Akdag et al. | The investigation of the heat transfer characteristics of a cross-flow pulsating jet in a forced flow | |
| Yang et al. | Surrogate-based optimization of nacelle intake with fan-intake interaction: Mitigating flow separation under crosswind | |
| Dutta et al. | Numerical investigations on turbulent transport phenomena over a moving surface due to impinging annular jets | |
| Huang et al. | SHAPE OPTIMIZATION TO IMPROVE FILM-COOLING PERFORMANCE FOR LAIDBACK FAN-SHAPED FILM COOLING HOLE ON THE SUCTION SURFACE OF A TURBINE VANE | |
| Wang et al. | Experimental Study and Prediction of Film Cooling Effectiveness for a Guide Vane in Heavy Gas Turbine | |
| Davari et al. | Variable Population Models in a Neural Network-Augmented Genetic Algorithm for Shape Optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |