CN114297807A - Method for optimizing parameters of flute-shaped tube structure of anti-icing system - Google Patents
Method for optimizing parameters of flute-shaped tube structure of anti-icing system Download PDFInfo
- Publication number
- CN114297807A CN114297807A CN202210221884.8A CN202210221884A CN114297807A CN 114297807 A CN114297807 A CN 114297807A CN 202210221884 A CN202210221884 A CN 202210221884A CN 114297807 A CN114297807 A CN 114297807A
- Authority
- CN
- China
- Prior art keywords
- hot gas
- mass flow
- gas mass
- structural parameters
- icing
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of anti-icing and deicing, and particularly relates to a flute-shaped pipe structure parameter optimization method of an anti-icing system. The method is characterized in that the minimum hot gas mass flow is taken as a target, the surface non-icing of an anti-icing system is taken as a limiting condition, a plurality of structural parameters, the maximum icing thickness and the minimum temperature are taken as input layers of a neural network, the hot gas mass flow is taken as an output layer of the neural network, neural network training is carried out to obtain a proxy model type, and the simulated annealing algorithm is adopted to carry out optimization design on the hot gas mass flow and the structural parameters of the flute-shaped pipe. According to the method, numerical simulation sample points required for establishing the proxy model are reduced by adopting a Latin hypercube method for sampling, the hot gas mass flow is quickly obtained by establishing the proxy model, the global optimization of the hot gas mass flow and structural parameters is realized by adopting a simulated annealing algorithm, and the whole optimization design method has the advantages of quickness and high efficiency.
Description
Technical Field
The invention belongs to the technical field of anti-icing and deicing, and particularly relates to a flute-shaped pipe structure parameter optimization method of an anti-icing system.
Background
When the aircraft passes through the cloud layer containing the supercooled water drops, ice accumulation can occur on the windward surface of the aircraft, and the ice accumulation can cause great harm to the safety of the aircraft. Therefore, a corresponding anti-icing system needs to be designed on the windward surface of the aircraft, such as the front edge of the wing, the lip of an engine inlet and the like.
Hot gas anti-icing is one of the anti-icing means commonly used on the windward surfaces of the wing leading edge, the engine and the like at present. The method comprises the steps of leading out high-temperature and high-pressure gas from a high-pressure compressor of an engine, leading the gas to a position needing protection through a hot gas pipeline, and heating the inner part of a wall surface needing protection through a certain jet impact form, so that the temperature of supercooled water on the surface is increased, and the phenomenon of ice accumulation on the wall surface is prevented.
The hot gas anti-icing system of flute pipe jet impact has been widely applied to the front edge of an airfoil and the lip of an engine inlet. A large number of researches show that the structural parameters of the flute pipe are as follows: the aperture, the number of holes, the hole distance, the impact distance and the like have important influences on the working performance of the anti-icing system, so that the structural parameters of the flute-shaped pipe need to be optimally designed in the design process of the anti-icing system.
The traditional method is to carry out preliminary design according to the design experience of engineering personnel and carry out comparison optimization through a limited amount of numerical calculation so as to obtain a better design scheme. The final result obtained by the method is only a local optimal result and is not a global optimal solution, the requirement on the design experience of designers is high, meanwhile, a large amount of numerical simulation calculation needs to be carried out, the iteration speed is low, and the efficiency is low.
Disclosure of Invention
The invention provides a flute-shaped pipe structure parameter optimization method of an anti-icing system, which is used for improving the anti-icing performance of the anti-icing system by optimizing flute-shaped pipe structure parameters.
The invention is realized by the following technical scheme:
the invention provides a flute-shaped tube structure parameter optimization method of an anti-icing system, which comprises the following steps:
s100: determining a plurality of structural parameters and hot gas mass flow of the flute-shaped pipe, and simultaneously determining a plurality of structural parameters and a value interval of the hot gas mass flow of the flute-shaped pipe;
s200: sampling the structural parameters and the hot gas mass flow in the value interval to obtain a sample matrix, wherein the sample matrix comprises N groups of structural parameters and hot gas mass flow, and N is a natural number;
s300: calculating the maximum icing thickness of the surface of the airplane and the minimum temperature of the surface of the airplane acted by an anti-icing system corresponding to each group of structural parameters and hot gas mass flow in the sample matrix, and obtaining a mapping relation matrix between the structural parameters, the hot gas mass flow and the maximum icing thickness and the minimum temperature;
s400: taking the structural parameters, the maximum icing thickness and the minimum temperature as input layers of the neural network, and taking the hot gas mass flow as an output layer of the neural network to carry out neural network training to obtain a proxy model;
s500: and (3) optimizing the structural parameters of the flute-shaped pipe by combining the proxy model and adopting a simulated annealing algorithm by taking the minimum mass flow of hot gas as a target and the non-icing condition of the surface of the anti-icing system as a limiting condition.
Further, the structural parameters in S100 include at least one of the following parameters: pore diameterNumber of holesHole pitch h.
Further, the obtaining process of the sample matrix in S200 is as follows:
s210: determining the number of samples to be N;
s220: sampling the structural parameters and the hot gas mass flow by adopting a Latin hypercube method to obtain a sample matrix:
the value intervals of the structural parameters and the hot gas mass flow are evenly divided into N layers, and one structural parameter is randomly extracted from each layerAnd mass flow of hot gasThe following sample matrix is obtained:
wherein:is indicative of at least one structural parameter,obtained for samplingThe parameters of the group structure are set up,for the nth hot gas mass flow sampled,。
further, in step S300, each set of structural parameters of the sample matrix is calculatedAnd mass flow of hot gasMaximum thickness of icing of the corresponding aircraft surfaceAircraft surface minimum temperature acting with anti-icing systemAnd obtaining a mapping relation matrix:
further, the obtaining process of the proxy model in S400 is as follows:
s410: establishing a new mapping matrix based on the mapping relation matrix:
s420: based on the new mapping matrix, the structure parameterMaximum thickness of ice formationMinimum temperature ofIs the input layer of the neural network, and has hot gas mass flowAnd carrying out neural network training for the output layer to obtain the proxy model.
Further, a layer is arranged in the middle layer of the neural network training, and the number of neurons in the middle layer is,;
further, the optimization design of the mass flow and the structural parameters of the hot gas of the flute-shaped pipe by adopting the simulated annealing algorithm in the step S500 comprises the following steps:
s510: setting the maximum thickness of ice to zero, i.e.(ii) a Minimum temperatureAt least the minimum non-icing temperature, and randomly generating a group of structural parameters in a value rangeAnd obtaining a parameter combination:inputting the parameter combination into the proxy model to obtain the corresponding hot gas mass flow;
S520: obtaining a second parameter combination by adopting the method of the step S510:and corresponding hot gas mass flow;
(2)Time, probability(ii) a When in useRetention ofKicking and removing device(ii) a When in useRetention ofKicking and removing device;
s540: repeating steps S520-S530 until remainingOrAre retained for M consecutive times, thenOrThe optimal hot gas mass flow is achieved; optimum hot gas mass flowThe corresponding structural parameters are the optimal structural parameters.
by adopting the technical scheme, the invention has the following advantages:
according to the method, numerical simulation sample points required for establishing the proxy model are reduced by adopting a Latin hypercube method for sampling, the hot gas mass flow is quickly obtained by establishing the proxy model, the global optimization of the hot gas mass flow and structural parameters is realized by adopting a simulated annealing algorithm, and the whole optimization design method has the advantages of quickness and high efficiency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention or the prior art will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for optimizing parameters of a flute-shaped tube structure of an anti-icing system according to the present invention;
FIG. 2 is a neural network proxy model of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments.
As shown in fig. 1, the present embodiment provides a method for optimizing parameters of a flute-shaped tube structure of an anti-icing system, including the following steps:
s100: determining a plurality of structural parameters and hot gas mass flow of the flute-shaped pipe, and simultaneously determining a plurality of structural parameters and a value interval of the hot gas mass flow of the flute-shaped pipe; the structural parameters of the flute-shaped pipe comprise aperture, number of holes, pitch of holes, impact distance and the like, and a plurality of structural parameters represent that 1 or more structural parameters can be selected; of course, specific structural parameters of the flute tube include, but are not limited to, the above list.
S200: sampling structural parameters and hot gas mass flow in a value interval to obtain a sample matrix, wherein the sample matrix comprises N groups of structural parameters and hot gas mass flow, each group of structural parameters and hot gas mass flow comprises a plurality of structural parameters and hot gas mass flow, and N is a natural number.
Further, sampling a value interval of sampling a plurality of structural parameters and a value interval of hot gas mass flow by adopting a Latin hypercube method to obtain a sample matrix.
S210: determining the number of samples to be N;
s220: sampling the structural parameters and the hot gas mass flow by adopting a Latin hypercube method to obtain a sample matrix:
the value intervals of the structural parameters and the hot gas mass flow are evenly divided into N layers, and one structural parameter is randomly extracted from each layerAnd mass flow of hot gasThe following sample matrix is obtained:
wherein:is indicative of at least one structural parameter,obtained for samplingThe parameters of the group structure are set up,for the nth hot gas mass flow sampled,。
the N groups of structural parameters and the hot gas mass flow are specifically as follows:,,...,,。
it should be noted that the latin hypercube method is known in the art, and the specific sampling process will not be described in detail here.
In certain embodiments, further, the structural parameters are selected: pore diameterNumber of holes,The structural parameter aperture is expressedNumber of holesThe sampled sample matrix is:(ii) a If the number of samples is determined to be 40, the sample matrix is:。
further, the apertureThe value interval is as follows:number of holesThe value interval is as follows:(ii) a Mass flow of hot gasThe value interval is as follows:。
s300: calculating each set of structural parameters of the sample matrixAnd mass flow of hot gasMaximum thickness of icing of the corresponding aircraft surfaceAircraft surface minimum temperature acting with anti-icing systemAnd obtaining a mapping relation matrix between the structural parameters, the mass flow of hot gas and the maximum thickness and the minimum temperature of the ice:
for those skilled in the art, the calculation of the maximum thickness and the minimum temperature of the ice is prior art and will not be described herein.
S400: taking the structural parameters, the maximum icing thickness and the minimum temperature as input layers of the neural network, and taking the hot gas mass flow as an output layer of the neural network to carry out neural network training to obtain a proxy model;
further, the obtaining process of the proxy model in S400 is as follows:
s410: establishing a new mapping matrix based on the mapping relation matrix:
s420: based on the new mapping matrix, the structure parameterMaximum thickness of ice formationMinimum temperature ofIs the input layer of the neural network, and has hot gas mass flowAnd carrying out neural network training for the output layer to obtain the proxy model.
Further, a layer is arranged in the middle layer of the neural network training, and the number of neurons in the middle layer is,。
as shown in fig. 2, in some embodiments, is an apertureNumber of holesMaximum thickness of ice formationMinimum temperature ofIs the input layer of the neural network, and has hot gas mass flowA proxy model obtained by training a neural network for an output layer, wherein。
S500: and (3) optimizing the structural parameters of the flute-shaped pipe by combining the proxy model and adopting a simulated annealing algorithm by taking the minimum mass flow of hot gas as a target and the non-icing condition of the surface of the anti-icing system as a limiting condition.
Further, the structural parameters are selected: pore diameterNumber of holesFor example, the optimization design of the hot gas mass flow and the structural parameters of the flute-shaped pipe by adopting a simulated annealing algorithm comprises the following steps:
randomly generating a set of combinations of parameters of pore diameter, pore number, maximum thickness of ice formation and minimum temperature:obtaining hot gas mass flow by using parameter combination and adopting the proxy model(ii) a At this time, no iteration is performed, the number of iterations is 0,the parameter combination is。
Wherein:the value interval is as follows:,the value interval is as follows:;,(ii) a The minimum freezing-free temperature is 273.15K,ensure thatAnd designing a margin.
Randomly generating a group of parameter combinations II of aperture, number of holes, icing maximum thickness and minimum temperature around the parameter combination I:using said proxy model to obtain hot gas mass flow for parameter combination two(ii) a At this time, no iteration is performed, the number of iterations is 0,the parameter combination is;
(2)Time, probability(ii) a When in useRetention ofKicking and removing device(ii) a When in useRetention ofKicking and removing device。
if it is reservedRandomly generating a group of parameter sets of aperture, number of holes, icing maximum thickness and minimum temperature around the second parameter combinationCombining three:obtaining the mass flow of hot gas by using the proxy model by using the parameter combination III(ii) a In this case 1 iteration, the number of iterations is 1,the parameter combination III is。
(2)Time, probability(ii) a When in useRetention ofKicking and removing device(ii) a When in useRetention ofKicking and removing device。
if the reservation is stillAnd randomly generating a group of parameter combinations IV of aperture, number of holes, maximum thickness of ice and minimum temperature around the parameter combination III:obtaining the mass flow of hot gas by using the proxy model by using the parameter combination III(ii) a In this case 1 iteration, the number of iterations is 2,the parameter combination is four(ii) a According to the method described aboveAndand (6) comparing.
If the reservation is stillObtaining the parameter combination again according to the method, and comparing again untilContinuously retaining for 11 times, thenFor the purpose of an optimum hot gas mass flow,corresponding toThen the optimum aperture is obtained for the desired aperture,corresponding toThe optimal number of holes is obtained; in this case, the value of M is 11, and it should be noted that the value of M includes, but is not limited to, 11.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. A flute-shaped tube structure parameter optimization method for an anti-icing system is characterized by comprising the following steps: the method comprises the following steps:
s100: determining a plurality of structural parameters and hot gas mass flow of the flute-shaped pipe, and simultaneously determining a plurality of structural parameters and a value interval of the hot gas mass flow of the flute-shaped pipe;
s200: sampling the structural parameters and the hot gas mass flow in the value interval to obtain a sample matrix, wherein the sample matrix comprises N groups of structural parameters and hot gas mass flow, and N is a natural number;
s300: calculating the maximum icing thickness of the surface of the airplane and the minimum temperature of the surface of the airplane acted by an anti-icing system corresponding to each group of structural parameters and hot gas mass flow in the sample matrix, and obtaining a mapping relation matrix between the structural parameters, the hot gas mass flow and the maximum icing thickness and the minimum temperature;
s400: taking the structural parameters, the maximum icing thickness and the minimum temperature as input layers of the neural network, and taking the hot gas mass flow as an output layer of the neural network to carry out neural network training to obtain a proxy model;
s500: and (3) optimizing the structural parameters of the flute-shaped pipe by combining the proxy model and adopting a simulated annealing algorithm by taking the minimum mass flow of hot gas as a target and the non-icing condition of the surface of the anti-icing system as a limiting condition.
3. The method for optimizing the parameters of the flute structure of the anti-icing system according to claim 1, wherein the method comprises the following steps: the obtaining process of the sample matrix in the S200 is as follows:
s210: determining the number of samples to be N;
s220: sampling the structural parameters and the hot gas mass flow by adopting a Latin hypercube method to obtain a sample matrix:
the value intervals of the structural parameters and the hot gas mass flow are evenly divided into N layers, and one structural parameter is randomly extracted from each layerAnd mass flow of hot gasThe following sample matrix is obtained:
4. a method as claimed in claim 3, wherein the method comprises the following steps: in step S300, each set of structural parameters of the sample matrix is calculatedAnd mass flow of hot gasMaximum thickness of icing of the corresponding aircraft surfaceAircraft surface minimum temperature acting with anti-icing systemAnd obtaining a mapping relation matrix:
5. the method for optimizing the parameters of the flute structure of the anti-icing system according to claim 4, wherein the method comprises the following steps: the process of obtaining the proxy model in S400 is as follows:
s410: establishing a new mapping matrix based on the mapping relation matrix:
6. The method for optimizing the parameters of the flute structure of the anti-icing system according to claim 5, wherein the method comprises the following steps: the middle layer of the neural network training is provided with a layer, and the number of neurons in the middle layer is,;
7. the method for optimizing the parameters of the flute structure of the anti-icing system according to claim 5, wherein the method comprises the following steps: s500, the optimization design of the mass flow and the structural parameters of the hot gas of the flute-shaped pipe by adopting a simulated annealing algorithm comprises the following steps:
s510: setting the maximum thickness of ice to zero, i.e.(ii) a Minimum temperatureAt least the minimum non-icing temperature, and randomly generating a group of structural parameters in a value rangeAnd obtaining a parameter combination:inputting the parameter combination into the proxy model to obtain the corresponding hot gas mass flow;
S520: obtaining a second parameter combination by adopting the method of the step S510:and corresponding hot gas mass flow;
(2)Time, probability(ii) a When in useRetention ofKicking and removing device(ii) a When in useRetention ofKicking and removing device;
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210221884.8A CN114297807B (en) | 2022-03-09 | 2022-03-09 | Method for optimizing parameters of flute-shaped tube structure of anti-icing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210221884.8A CN114297807B (en) | 2022-03-09 | 2022-03-09 | Method for optimizing parameters of flute-shaped tube structure of anti-icing system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114297807A true CN114297807A (en) | 2022-04-08 |
CN114297807B CN114297807B (en) | 2022-06-03 |
Family
ID=80978682
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210221884.8A Active CN114297807B (en) | 2022-03-09 | 2022-03-09 | Method for optimizing parameters of flute-shaped tube structure of anti-icing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114297807B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114757109A (en) * | 2022-06-14 | 2022-07-15 | 中国空气动力研究与发展中心低速空气动力研究所 | Method and system for testing relation of parameters of icing inside and outside air inlet channel and application |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101982765A (en) * | 2010-09-21 | 2011-03-02 | 南京航空航天大学 | Method and device for on-line detecting iced and damaged transmission line based on elastic wave |
CN105139274A (en) * | 2015-08-16 | 2015-12-09 | 东北石油大学 | Power transmission line icing prediction method based on quantum particle swarm and wavelet nerve network |
CN106867455A (en) * | 2017-04-06 | 2017-06-20 | 中国民用航空总局第二研究所 | The quick preparation system of pipeline and method of civil aviaton's ice-removing and ice-preventing liquid |
CN109117951A (en) * | 2018-01-15 | 2019-01-01 | 重庆大学 | Probabilistic Load Flow on-line calculation method based on BP neural network |
CN111738481A (en) * | 2020-04-01 | 2020-10-02 | 南京航空航天大学 | Airplane icing meteorological parameter MVD prediction method based on BP neural network |
US20200391871A1 (en) * | 2019-06-14 | 2020-12-17 | Rosemount Aerospace Inc. | Health monitoring of an electrical heater of an air data probe |
-
2022
- 2022-03-09 CN CN202210221884.8A patent/CN114297807B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101982765A (en) * | 2010-09-21 | 2011-03-02 | 南京航空航天大学 | Method and device for on-line detecting iced and damaged transmission line based on elastic wave |
CN105139274A (en) * | 2015-08-16 | 2015-12-09 | 东北石油大学 | Power transmission line icing prediction method based on quantum particle swarm and wavelet nerve network |
CN106867455A (en) * | 2017-04-06 | 2017-06-20 | 中国民用航空总局第二研究所 | The quick preparation system of pipeline and method of civil aviaton's ice-removing and ice-preventing liquid |
CN109117951A (en) * | 2018-01-15 | 2019-01-01 | 重庆大学 | Probabilistic Load Flow on-line calculation method based on BP neural network |
US20200391871A1 (en) * | 2019-06-14 | 2020-12-17 | Rosemount Aerospace Inc. | Health monitoring of an electrical heater of an air data probe |
CN111738481A (en) * | 2020-04-01 | 2020-10-02 | 南京航空航天大学 | Airplane icing meteorological parameter MVD prediction method based on BP neural network |
Non-Patent Citations (10)
Title |
---|
YI XIAN等: "Investigation on heat transfer characteristics of aircraft icing including runback water", 《INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER》 * |
YI XIAN等: "Investigation on heat transfer characteristics of aircraft icing including runback water", 《INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER》, vol. 53, no. 19, 30 September 2010 (2010-09-30), pages 3702 - 3707 * |
张镇等: "基于神经网络的主动式红外结冰分类方法研究", 《自动化与仪表》 * |
张镇等: "基于神经网络的主动式红外结冰分类方法研究", 《自动化与仪表》, no. 02, 15 February 2010 (2010-02-15), pages 1 - 4 * |
易贤等: "民用航空发动机进气道防冰系统设计方法研究", 《航空工程进展》 * |
易贤等: "民用航空发动机进气道防冰系统设计方法研究", 《航空工程进展》, vol. 8, no. 3, 28 August 2017 (2017-08-28), pages 335 - 341 * |
朱永峰等: "某型飞机发动机短舱防冰系统设计计算", 《航空动力学报 》 * |
朱永峰等: "某型飞机发动机短舱防冰系统设计计算", 《航空动力学报 》, vol. 27, no. 6, 15 June 2012 (2012-06-15), pages 1326 - 1331 * |
肖晓阳: "基于RBF神经网络的波音737NG飞机引气系统故障诊断模型", 《航空维修与工程》 * |
肖晓阳: "基于RBF神经网络的波音737NG飞机引气系统故障诊断模型", 《航空维修与工程》, no. 07, 20 July 2020 (2020-07-20), pages 81 - 84 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114757109A (en) * | 2022-06-14 | 2022-07-15 | 中国空气动力研究与发展中心低速空气动力研究所 | Method and system for testing relation of parameters of icing inside and outside air inlet channel and application |
CN114757109B (en) * | 2022-06-14 | 2022-08-23 | 中国空气动力研究与发展中心低速空气动力研究所 | Method and system for testing relation between internal and external icing parameters of air inlet channel |
Also Published As
Publication number | Publication date |
---|---|
CN114297807B (en) | 2022-06-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114297807B (en) | Method for optimizing parameters of flute-shaped tube structure of anti-icing system | |
CN106919731B (en) | Method for determining wake flow of wind turbine generator for different wind direction angles | |
CN107194118B (en) | Pneumatic-thermal collaborative optimization method for turbine blade fan-shaped hole air film cooling structure | |
Jeong et al. | Optimization of thick wind turbine airfoils using a genetic algorithm | |
CA2430823A1 (en) | Morphogenetic modelling of in-flight icing | |
CN105069221B (en) | For the critical Calculation Methods for Performance of Supersonic Inlet optimal design | |
CN113777931B (en) | Icing wing type pneumatic model construction method, device, equipment and medium | |
CN104346499A (en) | Multi-fan turbine engine design method based on computer platform | |
CN110633522A (en) | Supersonic thrust nozzle reverse design method based on maximum thrust theory | |
CN114254460B (en) | Turbomachine pneumatic robustness optimization method based on graph convolution neural network | |
CN116167300A (en) | Quick evaluation numerical simulation method for ice-type characteristics of airfoil | |
CN111079920B (en) | Prediction method for flow non-uniformity coefficient of turbine gas collection cavity outlet | |
CN115048748B (en) | Method, system and processing terminal for obtaining compressor pressure prediction model | |
Lengyel-Kampmann et al. | Generalized optimization of counter-rotating and single-rotating fans | |
CN112163691B (en) | Air film cooling two-dimensional effectiveness prediction method and system based on scalar transport equation | |
Lee et al. | Simulation of icing on a cascade of stator blades | |
CN115358167B (en) | Flying and launching integrated pneumatic accompanying optimization design method considering engine parameters | |
CN112632728B (en) | Turbine mechanical blade profile design and performance prediction method based on deep learning | |
Kuzmenko et al. | Optimization of the gas turbine engine parts using methods of numerical simulation | |
Tang et al. | Multi-objective optimization of aerodynamic performance for a small single-stage turbine | |
Leylek et al. | Global Three-Dimensional Surrogate Modeling of Gas Turbine Aerodynamic Performance | |
Liu et al. | Optimization for Hot-film Anti-icing Structure by BPNN and GA | |
Jirasek et al. | Computational design of S-duct intakes for the NATO AVT-251 multi-disciplinary configuration | |
Tahsini | Preliminary Design Optimization of a Gas Turbine Multi-Stage Compressor | |
Liu et al. | Aero-Engine Inlet Vane Structure Optimization for Anti-Icing with Hot Air Film Using Neural Network and Genetic Algorithm |
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 |