CN107194118B - Pneumatic-thermal collaborative optimization method for turbine blade fan-shaped hole air film cooling structure - Google Patents
Pneumatic-thermal collaborative optimization method for turbine blade fan-shaped hole air film cooling structure Download PDFInfo
- Publication number
- CN107194118B CN107194118B CN201710464122.XA CN201710464122A CN107194118B CN 107194118 B CN107194118 B CN 107194118B CN 201710464122 A CN201710464122 A CN 201710464122A CN 107194118 B CN107194118 B CN 107194118B
- Authority
- CN
- China
- Prior art keywords
- fan
- shaped hole
- obj
- radial basis
- basis function
- 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.)
- Active
Links
- 238000001816 cooling Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000005457 optimization Methods 0.000 title claims abstract description 23
- 230000006870 function Effects 0.000 claims description 66
- 238000012360 testing method Methods 0.000 claims description 30
- 238000013528 artificial neural network Methods 0.000 claims description 26
- 238000013461 design Methods 0.000 claims description 24
- 239000002245 particle Substances 0.000 claims description 23
- 210000002569 neuron Anatomy 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 239000003795 chemical substances by application Substances 0.000 claims description 2
- 230000001537 neural effect Effects 0.000 claims 1
- 239000007789 gas Substances 0.000 description 13
- 238000011161 development Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000002737 fuel gas Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000237503 Pectinidae Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 235000020637 scallop Nutrition 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Turbine Rotor Nozzle Sealing (AREA)
- Structures Of Non-Positive Displacement Pumps (AREA)
Abstract
The invention discloses a pneumatic-thermal collaborative optimization method for a turbine blade fan-shaped hole air film cooling structure. The method overcomes the characteristic that the traditional air film cooling structure optimization method needs to depend on a large number of samples, and has the advantages of nonlinear prediction capability, high prediction precision, strong memory capability and robustness, and good global approximation capability. And the weight of the aerodynamic performance and the thermal performance can be adjusted according to the actual requirement, and the optimal fan-shaped hole air film cooling structure with both the aerodynamic performance and the thermal performance is designed.
Description
Technical Field
The invention relates to a pneumatic-thermal cooperative optimization method for a turbine blade fan-shaped hole air film cooling structure, and belongs to the technical field of enhanced cooling.
Background
In the technical development process of an aircraft gas turbine engine, the pressure increase ratio of a compressor and the temperature of gas at the inlet of a turbine show a trend of increasing continuously. According to the future development trend of advanced aviation gas turbine engine technology, the thrust-weight ratio of a new generation engine reaches about 15, and the gas temperature at the inlet of the turbine reaches 2200K-2300K at the moment. The heat load of hot end parts such as turbine blades, a combustor flame tube, an exhaust nozzle and the like is greatly increased due to the increase of the temperature of the gas at the inlet of the turbine; at the same time, the improvement of the compression-air pressure ratio also leads to a reduction in the quality of the cooling air for the hot-end components. Hot-end component cooling technology is therefore a key technical issue in improving gas turbine engines.
Film cooling is widely applied to turbine blades of aircraft engines as an efficient cooling mode. The principle of the method is that secondary cooling air flow is introduced into a main flow from an air film hole of a high-temperature wall surface, the cooling air flow bends downstream under the action of pressure and friction force of the main flow and is attached to a certain area of the wall surface to form a cold air film with lower temperature to isolate the wall surface from high-temperature fuel gas and take away part of the high-temperature fuel gas, so that the wall surface is well cooled and protected. The development of maximum cooling efficiency with minimum cooling air volume and at the same time aerodynamic losses has been the focus of air film cooling research. Traditional optimization of the film hole cooling structure needs to rely on a large number of experiments and numerical simulation to summarize the law, so that not only a large amount of time needs to be consumed, but also the cost is relatively high.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the prior art, the pneumatic-thermal collaborative optimization method for the turbine blade fan-shaped hole air film cooling structure is provided, the turbine blade fan-shaped hole air film cooling structure is used for carrying out nonlinear mapping on an air film cooling pneumatic parameter and a thermal parameter, and the method has the advantages of high prediction precision, high efficiency and good global approximation capability.
The technical scheme is as follows: a pneumatic-thermal collaborative optimization method for a turbine blade fan-shaped hole air film cooling structure comprises the following steps:
step 7, CFD evaluation is carried out on the optimization design point, and if the radial basis function value F is predicted by the radial basis function neural networkobj,preAnd CFD calculates the objective function value Fobj,calIf the error is more than 5%, the optimization design point is expanded to a training sample database, and iteration is started from the step 4 again until the radial basis function value F is predicted by the radial basis function neural networkobj,preAnd CFD calculates the objective function value Fobj,calAnd (5) stopping iteration when the error is within a preset range to obtain a global optimal design point.
Further, the design variables to be optimized in step 1 include the following parameters: the corresponding variation ranges of the inclination angle alpha of the fan-shaped hole of the turbine blade, the lateral spread angle beta of the fan-shaped hole and the forward spread angle gamma of the fan-shaped hole are respectively 25-55 degrees, 10-20 degrees and 3-15 degrees.
Further, the step of designing the data sample in step 2 includes:
step 2.1, designing 25 groups of data as training samples by adopting a Latin hypercube design method, wherein the parameters to be optimized are the inclination angle alpha of a fan-shaped hole of the turbine blade, the lateral spread angle beta of the fan-shaped hole and the forward spread angle gamma of the fan-shaped hole;
2.2, randomly combining the inclination angle alpha of a fan-shaped hole, the lateral expansion angle beta of the fan-shaped hole and the forward expansion angle gamma of the fan-shaped hole of the turbine blade to be optimized, and designing 8 groups of data to be used as a test sample;
step 2.3, normalization processing is carried out on the parameters to be optimized, and the method comprises the following steps:
in the formula:for the normalized data, x is the actual value of the parameter to be optimized, xmaxFor the maximum value of the parameter to be optimized, xminIs the minimum value of the parameter to be optimized.
Further, the objective function in step 3 is expressed as:
F(α,β,γ)=λ1ηad,av+λ2Cd
in the formula: lambda [ alpha ]1η is the average cooling efficiency weight ratio of the turbine blade facead,avIs a vortexAverage cooling efficiency of the blade faces of the wheel; lambda [ alpha ]2The weight ratio of the flow coefficient of the fan-shaped hole is used; cdIs the flow coefficient of the fan-shaped hole.
Further, the radial basis function neural network in step 4 is expressed as follows:
the radial basis function neural network is divided into three layers: an input layer, a hidden layer, an output layer,
the input value of the ith neuron node center of the hidden layer is expressed as:
Hi=||X-Ci||
in the formula: x ═ X1,x2,…,xk) For the network input vector, k denotes the number of network inputs, xjRepresents the jth network input, j ═ 1,2,3.. k; ci=(c1i,c2i,…,cki) Is the center of the i-th neuron node, cjiA center of an ith neuron node representing a jth network input; | | represents the euclidean norm;
the output value of the jth neuron node of the hidden layer is expressed as:
in the formula: representing the expansion speed of the radial basis function neural network;
the output values for the output layer neurons are expressed as:
in the formula: w ═ w (w)1,w2,…,wn) N represents the number of hidden layers for the weight connecting the hidden layers and the output layers.
Further, the radial basis function neural network of step 5 predicts an objective function value Fobj,preAnd test specimen Fobj.testThe error is expressed as:
obtaining a radial basis function value F predicted by a radial basis function neural network based on a large-range expansion speed by applying a trial-and-error methodobj,preAnd a test sample Fobj.testThe minimum error.
Further, the particle group algorithm optimization problem in step 6 is expressed as:
max F(α,β,γ)=λ1ηad,av+λ2Cd
wherein F (α, gamma) is fitness function, αmin、αmaxThe parameter α corresponds to the maximum value and the minimum value of the variation range βmin、βmaxThe parameter β corresponds to the maximum and minimum values of the variation range, gammamin、γmaxThe parameter gamma corresponds to the maximum value and the minimum value of the variation range;
step 6.1, setting maximum iteration times, particle swarm size, inertia weight and learning factors, and initializing particles and particle speed;
step 6.2, detecting the particle fitness;
6.3, searching individual extremum and group extremum;
step 6.4, updating speed and position;
step 6.5, calculating the particle fitness;
6.6, updating the individual extremum and the group extremum;
and 6.7, judging whether the termination condition is met, and if not, returning to the step 6.4.
Further, the inertial weight in step 6.1 adopts a dynamic change method, and the formula is as follows:
w(k)=wstart-(wstart-wend)(k/Nmax)2
in the formula: k is the current iteration algebra, and w (k) is the inertial weight of the current iteration; w is astartIs an initial inertial weight, wstart=0.9;wendFor the inertial weight at the maximum number of iterations,wend=0.4;Nmaxis the maximum iteration algebra.
Further, the radial basis function neural network of step 7 predicts an objective function value Fobj,preAnd CFD calculates the objective function value Fobj,calThe error is expressed as:
has the advantages that: according to the method, a CFD model verified through experiments is utilized, a training sample and a test sample are utilized to perform function approximation based on a Radial Basis Function Neural Network (RBFNN), and an optimal design point is obtained by coupling particle swarm algorithm global search; the optimization algorithm is based on a particle swarm algorithm, and in order to solve the problem that the local minimum value is possibly trapped, the inertia weight adopts a dynamic change method; the invention can expand the database, and can search out the accurate optimal design point globally by a small amount of training samples and testing samples; according to the invention, the weight of the aerodynamic performance and the thermal performance can be adjusted according to the actual requirement, and an air film cooling structure of the optimal fan-shaped hole with both the aerodynamic performance and the thermal performance is designed; the invention has high efficiency and less resource consumption, and can greatly reduce the time and economic cost.
Drawings
FIG. 1 is a flow chart of a method for the aerodynamic-thermal collaborative optimization of a turbine blade fan-shaped hole film cooling structure;
FIG. 2 is a geometric model of a turbine blade fan hole film cooling;
FIG. 3 is a partial enlarged view of the sector holes;
FIG. 4 is a front view of the fan-shaped hole;
FIG. 5 is a top view of the scallops;
FIG. 6 is a radial basis function neural network structure;
number designation in the figures: 1. the main flow inlet, 2 main flow and secondary flow outlets, 3 turbine blade suction surfaces, 4 turbine blade pressure surfaces, 5 cold air cavities, 6 fan-shaped holes, 7 fan-shaped holes, 8 fan-shaped hole cold air inlets and 9 fan-shaped hole cold air outlets.
Detailed Description
The invention is further explained below with reference to the drawings.
FIG. 1 is a flow chart of a method for the aerodynamic-thermal collaborative optimization of a turbine blade fan hole film cooling structure according to the invention, and the method will be described with reference to FIG. 1.
The pitch P of the fan-shaped holes is set to be 4.5D, the height h of the fan-shaped holes is set to be 2.5D, and the forward expansion length l of the fan-shaped holes1D, the lateral expansion length l of the fan-shaped hole2Length l of cylindrical part of sector hole for 2D3Selecting an inclination angle α of a fan-shaped hole of the turbine blade for (h/sin α -3D), wherein the lateral spread angle β of the fan-shaped hole and the forward spread angle gamma of the fan-shaped hole are design variables to be optimized, and the change ranges are respectively 25-55 degrees, 10-20 degrees and 3-15 degrees, and the structure diagram is shown in FIG. 3.
TABLE 1
Normalization processing is carried out on the parameters to be optimized, and the normalization processing method comprises the following steps:
in the formula:for the normalized data, x is the actual value of the parameter to be optimized, xmaxFor the maximum value of the parameter to be optimized, xminIs the minimum value of the parameter to be optimized.
F(α,β,γ)=λ1ηad,av+λ2Cd
in the formula: lambda [ alpha ]1η is the average cooling efficiency weight ratio of the turbine blade facead,avAverage cooling efficiency for turbine blade faces; lambda [ alpha ]2The weight ratio of the flow coefficient of the fan-shaped hole is used; cdIs the flow coefficient of the fan-shaped hole.
Turbine blade face average cooling efficiency ηad,avThe expression is as follows:
wherein D is the circular diameter of the inlet of the fan-shaped hole, ηad,avxThe line average adiabatic film cooling efficiency is given. Coefficient of flow CdThe expression is as follows:
in the formula: m is the actual flow through the gas film channel; a is the cross-sectional area of the cold air channel at the outlet of the air film hole; rhooutDensity, P, of gas at the outlet of the gas film holein *Is the total pressure of the gas at the inlet of the gas film hole, PoutStatic pressure of the gas at the exit of the gas film hole.
And 4, training and testing the RBFNN by using the training sample and the testing sample. The radial basis function neural network structure is shown in fig. 4 and comprises three layers: input layer, hidden layer, output layer.
The input value of the ith neuron node center of the hidden layer is expressed as:
Hi=||X-Ci||
in the formula: x ═ X1,x2,…,xk) For the network input vector, k denotes the number of network inputs, xjRepresents the jth network input, j ═ 1,2,3.. k; ci=(c1i,c2i,…,cki) Is the center of the i-th neuron node, cjiA center of an ith neuron node representing a jth network input; | | | represents the euclidean norm.
The output value of the jth neuron node of the hidden layer is expressed as:
in the formula: indicating the RBFNN expansion speed.
The output values for the output layer neurons are expressed as:
in the formula: w ═ w (w)1,w2,…,wn) Is the weight value connecting the hidden layer and the output layer.
RBFNN prediction objective function value F is obtained based on large-range expansion speed by applying trial and error methodobj,preAnd test specimen Fobj.testThe minimum error.
And 6, searching an optimal design point by utilizing a Particle Swarm Optimization (PSO) coupled RBFNN.
The particle swarm algorithm fitness function is expressed as:
max F(α,β,γ)=λ1ηad,av+λ2Cd
in the formula, F (α, gamma) is a fitness function αmin、αmaxThe parameter α corresponds to the maximum value and the minimum value of the variation range βmin、βmaxThe parameter β corresponds to the maximum and minimum values of the variation range, gammamin、γmaxThe parameter gamma corresponds to the maximum and minimum values of the variation range.
Step 6.1, setting maximum iteration times, particle swarm size, inertia weight and learning factors, and initializing particles and particle speed;
the inertia weight adopts a dynamic change method, and the formula is as follows:
w(k)=wstart-(wstart-wend)(k/Nmax)2
in the formula: k is the current iteration algebra, and w (k) is the inertial weight of the current iteration; w is astartIs an initial inertial weight, wstart=0.9;wendIs the inertial weight at the time of iteration to the maximum number, wend=0.4;NmaxIs the maximum iteration algebra.
Step 6.2, detecting the particle fitness;
6.3, searching individual extremum and group extremum;
step 6.4, updating speed and position;
step 6.5, calculating the particle fitness;
6.6, updating the individual extremum and the group extremum;
and 6.7, judging whether the termination condition is met, and if not, returning to the step 6.4.
Step 7, CFD evaluation is carried out on the optimization design point, and if RBFNN predicts the objective function value Fobj,preComputing an objective function with CFDValue Fobj,calIf the error is more than 5%, expanding the training sample database by the optimization design point, and iterating from the step 4 again until the RBFNN forecast FobjAnd CFD FobjAnd (5) the error meets the requirement, and iteration is terminated to obtain a global optimal design point. Wherein RBFNN predicts objective function value Fobj,preAnd CFD calculates the objective function value Fobj,calThe error is expressed as:
the foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (3)
1. A pneumatic-thermal collaborative optimization method for a turbine blade fan-shaped hole air film cooling structure is characterized by comprising the following steps: the method comprises the following steps:
step 1, determining a to-be-optimized design variable of an air film cooling structure and a range of the to-be-optimized design variable; the design variables to be optimized comprise the following parameters: the inclination angle alpha of a fan-shaped hole of the turbine blade, the lateral spread angle beta of the fan-shaped hole and the forward spread angle gamma of the fan-shaped hole are respectively 25-55 degrees, 10-20 degrees and 3-15 degrees;
step 2, designing a data sample of the radial basis function neural network agent model; the step of designing the data sample comprises:
step 2.1, designing 25 groups of data as training samples by adopting a Latin hypercube design method, wherein the parameters to be optimized are the inclination angle alpha of a fan-shaped hole of the turbine blade, the lateral spread angle beta of the fan-shaped hole and the forward spread angle gamma of the fan-shaped hole;
2.2, randomly combining the inclination angle alpha of a fan-shaped hole, the lateral expansion angle beta of the fan-shaped hole and the forward expansion angle gamma of the fan-shaped hole of the turbine blade to be optimized, and designing 8 groups of data to be used as a test sample;
step 2.3, normalization processing is carried out on the parameters to be optimized, and the method comprises the following steps:
in the formula:for the normalized data, x is the actual value of the parameter to be optimized, xmaxFor the maximum value of the parameter to be optimized, xminIs the minimum value of the parameter to be optimized;
step 3, establishing a CFD model for the data sample, and calculating an objective function value Fobj,cal(ii) a The objective function is expressed as:
F(α,β,γ)=λ1ηad,av+λ2Cd
in the formula: lambda [ alpha ]1η is the average cooling efficiency weight ratio of the turbine blade facead,avAverage cooling efficiency for turbine blade faces; lambda [ alpha ]2The weight ratio of the flow coefficient of the fan-shaped hole is used; cdIs a fan-shaped hole flow coefficient;
step 4, training and testing the radial basis function neural network by utilizing the training sample and the testing sample;
step 5, outputting a radial basis function neural network prediction objective function value Fobj,preAnd the test sample objective function value Fobj.testExpansion speed at minimum error;
step 6, searching an optimal design point by utilizing a particle swarm algorithm coupled with a radial basis function neural network;
step 7, CFD evaluation is carried out on the optimization design point, and if the radial basis function value F is predicted by the radial basis function neural networkobj,preAnd CFD calculates the objective function value Fobj,calIf the error is more than 5%, the optimization design point is expanded to a training sample database, and iteration is started from the step 4 again until the radial basis function value F is predicted by the radial basis function neural networkobj,preAnd CFD calculates the objective function value Fobj,calThe iteration is terminated when the error is within a preset range, and a global optimal design point is obtained;
step 5, predicting the target function by the radial basis function neural networkValue Fobj,preAnd test specimen Fobj.testThe error is expressed as:
obtaining a radial basis function value F predicted by a radial basis function neural network based on a large-range expansion speed by applying a trial-and-error methodobj,preAnd test specimen Fobj.testThe minimum error;
the particle group algorithm optimization problem in step 6 is expressed as:
maxF(α,β,γ)=λ1ηad,av+λ2Cd
wherein F (α, gamma) is fitness function, αmin、αmaxThe parameter α corresponds to the maximum value and the minimum value of the variation range βmin、βmaxThe parameter β corresponds to the maximum and minimum values of the variation range, gammamin、γmaxThe parameter gamma corresponds to the maximum value and the minimum value of the variation range;
step 6.1, setting maximum iteration times, particle swarm size, inertia weight and learning factors, and initializing particles and particle speed;
step 6.2, detecting the particle fitness;
6.3, searching individual extremum and group extremum;
step 6.4, updating speed and position;
step 6.5, calculating the particle fitness;
6.6, updating the individual extremum and the group extremum;
step 6.7, judging whether the termination condition is met, if not, returning to the step 6.4;
in step 6.1, the inertia weight adopts a dynamic change method, and the formula is as follows:
w(k)=wstart-(wstart-wend)(k/Nmax)2
in the formula: k is the current iteration algebra, and w (k) is the inertial weight of the current iteration; w is astartIs an initial inertial weight, wstart=0.9;wendIs the inertial weight at the time of iteration to the maximum number, wend=0.4;NmaxIs the maximum iteration algebra.
2. The method for the aerodynamic-thermal collaborative optimization of the turbine blade fan hole film cooling structure according to claim 1, wherein the method comprises the following steps: step 4, the radial basis function neural network is expressed as follows:
the radial basis function neural network is divided into three layers: an input layer, a hidden layer, an output layer,
the input value of the ith neuron node center of the hidden layer is expressed as:
Hi=||X-Ci||
in the formula: x ═ X1,x2,…,xk) For the network input vector, k denotes the number of network inputs, xjRepresents the jth network input, j ═ 1,2,3.. k; ci=(c1i,c2i,…,cki) Is the center of the i-th neuron node, cjiA center of an ith neuron node representing a jth network input; | | represents the euclidean norm;
the output value of the jth neuron node of the hidden layer is expressed as:
in the formula: representing the expansion speed of the radial basis function neural network;
the output values for the output layer neurons are expressed as:
in the formula: w is aj=(w1,w2,…,wn) N represents the number of hidden layers for the weight connecting the hidden layers and the output layers.
3. The method for the aerodynamic-thermal collaborative optimization of the turbine blade fan hole film cooling structure according to claim 1, wherein the method comprises the following steps: step 1, predicting an objective function value F by using a radial basis function neural networkobj,preAnd CFD calculates the objective function value Fobj,calThe error is expressed as:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710464122.XA CN107194118B (en) | 2017-06-19 | 2017-06-19 | Pneumatic-thermal collaborative optimization method for turbine blade fan-shaped hole air film cooling structure |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710464122.XA CN107194118B (en) | 2017-06-19 | 2017-06-19 | Pneumatic-thermal collaborative optimization method for turbine blade fan-shaped hole air film cooling structure |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107194118A CN107194118A (en) | 2017-09-22 |
CN107194118B true CN107194118B (en) | 2020-09-18 |
Family
ID=59879286
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710464122.XA Active CN107194118B (en) | 2017-06-19 | 2017-06-19 | Pneumatic-thermal collaborative optimization method for turbine blade fan-shaped hole air film cooling structure |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107194118B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109611268B (en) * | 2018-11-01 | 2020-11-06 | 协鑫能源科技有限公司 | Design optimization method for double-impeller horizontal shaft wind turbine |
CN111814272B (en) * | 2020-07-07 | 2024-04-19 | 中国科学院工程热物理研究所 | Turbine pneumatic-dynamic response intelligent optimization design method based on machine learning |
CN111914461A (en) * | 2020-09-08 | 2020-11-10 | 北京航空航天大学 | Intelligent assessment method for one-dimensional cold efficiency of turbine guide vane |
CN112084597B (en) * | 2020-09-08 | 2021-06-15 | 北京航空航天大学 | Single-exhaust-film cooling efficiency two-dimensional distribution AI prediction method based on bell-shaped curve |
CN112084596B (en) * | 2020-09-08 | 2021-06-15 | 北京航空航天大学 | Intelligent recommendation system and recommendation method for structural parameters of floor |
CN116756882B (en) * | 2023-08-23 | 2023-10-31 | 中国航发四川燃气涡轮研究院 | Turbine blade cooling structure design method based on geometric parameter sensitivity analysis |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573282A (en) * | 2015-01-29 | 2015-04-29 | 河海大学 | Aerodynamic optimum design method of airfoil profile of vertical axis wind turbine |
CN106777642A (en) * | 2016-12-08 | 2017-05-31 | 南京航空航天大学 | A kind of Forecasting Methodology of film cooling structure discharge coefficient |
-
2017
- 2017-06-19 CN CN201710464122.XA patent/CN107194118B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573282A (en) * | 2015-01-29 | 2015-04-29 | 河海大学 | Aerodynamic optimum design method of airfoil profile of vertical axis wind turbine |
CN106777642A (en) * | 2016-12-08 | 2017-05-31 | 南京航空航天大学 | A kind of Forecasting Methodology of film cooling structure discharge coefficient |
Non-Patent Citations (3)
Title |
---|
Optimization of a fan-shaped hole to improve film cooling performance by RBF neural network and genetic algorithm;ChunhuaWang, JingzhouZhang, JunhuiZhou;《AerospaceScienceandTechnology》;20160805;第58卷;18-25 * |
Shape optimization of a fan-shaped hole to enhance film-cooling effectiveness;Ki-Don Lee, Kwang-Yong Kim;《International Journal of Heat and Mass Transfer》;20100731;第53卷;2996-3005 * |
基于BP神经网络的多参数气膜冷却效率研究;秦晏旻;《工程热物理学报》;20110731;第32卷(第7期);1127-1130 * |
Also Published As
Publication number | Publication date |
---|---|
CN107194118A (en) | 2017-09-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107194118B (en) | Pneumatic-thermal collaborative optimization method for turbine blade fan-shaped hole air film cooling structure | |
Aulich et al. | High-dimensional constrained multiobjective optimization of a fan stage | |
Goulos et al. | Design optimisation of separate-jet exhausts for the next generation of civil aero-engines | |
Tejero et al. | Impact of droop and scarf on the aerodynamic performance of compact aero-engine nacelles | |
Wang et al. | Integrated optimization for design and operation of turbomachinery in a solar-based Brayton cycle based on deep learning techniques | |
Song et al. | Aerodynamic and structural multidisciplinary optimization design method of fan rotors based on blade curvature constraints | |
Lv et al. | Mode transition path optimization for turbine-based combined-cycle ramjet stage under uncertainty propagation of integrated airframe-propulsion system | |
Yu et al. | Inverse design of nozzle using convolutional neural network | |
Zhu et al. | Artificial neural network-based predictive model for supersonic ejector in refrigeration system | |
Wang et al. | Rapid performance prediction model of axial turbine with coupling one-dimensional inverse design and direct analysis | |
CN111079920B (en) | Prediction method for flow non-uniformity coefficient of turbine gas collection cavity outlet | |
Semlitsch et al. | Shape Optimisation of Turbomachinery Components | |
Cao et al. | DNN-based surrogate modeling-based feasible performance reliability design methodology for aircraft engine | |
Wang et al. | An efficient quantification method based on feature selection for high-dimensional uncertainties of multistage compressors | |
CN111125971B (en) | Method for determining thrust uncertainty of air-breathing hypersonic aircraft | |
CN114519299A (en) | Multi-objective optimization method for double-wall structure of integrated support plate flame stabilizer | |
Wang et al. | Data mining optimization of laidback fan-shaped hole to improve film cooling performance | |
Rosa Taddei | Analytical closure of the inviscid blade force model | |
Jin et al. | Design Optimization and Analysis of Exit Rotor with Diffuser Passage based on Neural Network Surrogate Model and Entropy Generation Method | |
Chen et al. | Optimisation design of turbofan engine using infrared stealth technology | |
Xu et al. | Comprehensive Flow Path Design Method for the Adaptive Cycle Engine Considering the Coupling Relation of Multiple Components | |
Wu et al. | Automated design optimization and experimental validation for intermediate casing duct of aeroengine | |
Leylek et al. | Global Three-Dimensional Surrogate Modeling of Gas Turbine Aerodynamic Performance | |
Rossetti et al. | An optimum design procedure for an aerodynamic radial diffuser with incompressible flow at different Reynolds numbers | |
Zhang et al. | Prediction of multi-physics field distribution on gas turbine endwall using an optimized surrogate model with various deep learning frames |
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 |