CN109684666B - Aircraft index parameter sensitivity optimization method based on genetic algorithm - Google Patents
Aircraft index parameter sensitivity optimization method based on genetic algorithm Download PDFInfo
- Publication number
- CN109684666B CN109684666B CN201811409820.0A CN201811409820A CN109684666B CN 109684666 B CN109684666 B CN 109684666B CN 201811409820 A CN201811409820 A CN 201811409820A CN 109684666 B CN109684666 B CN 109684666B
- Authority
- CN
- China
- Prior art keywords
- aircraft
- sensitivity
- index
- genetic algorithm
- optimization
- 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
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- 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
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- 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)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Feedback Control In General (AREA)
Abstract
The application provides an aircraft index parameter sensitivity optimization method based on a genetic algorithm, which comprises the following steps: analyzing single parameter sensitivity; determining decision variables and constraint conditions affecting index parameters based on the analysis result of the single parameter sensitivity; performing large sample optimization on the aircraft index parameter value to obtain an aircraft index parameter value optimization solution space; the sensitivity of the aircraft index parameters is optimized with an optimized solution space.
Description
Technical Field
The application relates to the technical field of aircrafts, and particularly provides an aircraft index parameter sensitivity optimization method based on a genetic algorithm.
Background
The parameter sensitivity optimization refers to analyzing the sensitivity degree of specific input parameters to output in a system, so as to determine the influence factors of different input parameters to output, provide a basis for judging the importance of each input parameter, and research the stability of the optimal solution when the original data is inaccurate or changed by sensitivity analysis.
At present, the sensitivity optimization of the fighter aircraft index parameters only can provide a carpet map, the theoretical depth is insufficient, the model is simple and coarse, the sensitivity analysis method adopted in each project type task is inconsistent, no rule exists, the provided result is often one-sided, the scientificity is insufficient, the method is immature, and the system is not available.
Disclosure of Invention
In order to solve at least one of the above technical problems, the present application provides a method for optimizing sensitivity of aircraft index parameters based on genetic algorithm, including: analyzing single parameter sensitivity; determining decision variables and constraint conditions affecting index parameters based on the analysis result of the single parameter sensitivity; and carrying out large sample optimization on the aircraft index parameter value to obtain an aircraft index parameter value optimization solution space so as to optimize the index parameter sensitivity of the aircraft by the optimization solution space.
According to at least one embodiment of the present application, analyzing single parameter sensitivity includes finding a sensitivity point selection index parameter; carrying out transformation of a sensitivity interval on the sensitive points; calculating index parameters of the aircraft; searching a change rule of aircraft index parameters; and carrying out sensitivity degree analysis to obtain a conclusion of single-parameter sensitivity analysis.
According to at least one embodiment of the present application, the sensitivity coefficient is calculated according to the following formula:
wherein E is the sensitivity coefficient of the evaluation index A to the factor F, deltaF is the change rate of the uncertainty factor F, deltaA is the change rate of the evaluation index A when the uncertainty factor F changes.
According to at least one embodiment of the present application, performing large sample optimization on aircraft index parameter values includes: based on an improved genetic algorithm, carrying out large-sample optimization on more than two decision variables at a time, and setting an optimization target according to the overall design index of the aircraft; wherein the improved genetic algorithm is: and adopting an optimal preservation strategy, and adopting the optimal preservation strategy when selecting the optimizing target.
According to at least one embodiment of the present application, obtaining an aircraft index parameter value optimization solution space includes: setting a variation range value of a decision variable as a simulation input; three genetic operators of design selection, hybridization and mutation are used as search tools; and taking the optimized solution space as a design criterion of index parameters.
According to at least one embodiment of the present application, the index parameters include a rate of climb of the aircraft and a range of the aircraft.
According to at least one embodiment of the present application, the decision variable is an influencing factor that determines the basic performance of the aircraft, wherein the influencing factor includes weight, engine thrust, and aerodynamic force.
According to at least one embodiment of the present application, the constraint is that the decision variable varies from 5% to 25%.
Compared with the prior art, the aircraft index parameter sensitivity optimization method based on the genetic algorithm has the advantages that the provided result is comprehensive and scientific, and the genetic algorithm can efficiently search a very wide problem space, so that many potential and important parameter optimization designs which are possibly not considered by a designer can be investigated and mined by the genetic algorithm.
Drawings
FIG. 1 is a schematic diagram of the results of a single parameter sensitivity analysis method according to an embodiment of the present application;
FIG. 2 is a graph of the trend of the optimal values of the multi-parameter sensitivity optimization method according to the embodiment of the present application;
fig. 3 is an optimal solution space diagram of a multi-parameter sensitivity optimization method according to an embodiment of the present application.
Detailed Description
The present application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and not limiting of the application. It should be further noted that, for convenience of description, only the portions relevant to the present application are shown in the drawings.
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
The aircraft index parameter sensitivity optimization method based on the genetic algorithm provided by the embodiment of the application comprises the following steps:
and step 1, analyzing single parameter sensitivity.
In this embodiment, the single parameter sensitivity analysis method may use a one-time-of-flight (OAT) method to obtain local sensitivity, specifically, the analysis but parameter sensitivity includes the following steps:
searching a sensitive point selection index parameter;
carrying out transformation of a sensitivity interval on the sensitive points;
calculating index parameters of the aircraft;
searching a change rule of aircraft index parameters;
and carrying out sensitivity degree analysis to obtain a conclusion of single-parameter sensitivity analysis.
The sensitivity coefficient is an index reflecting the sensitivity degree to the factors, and the higher the sensitivity coefficient is, the higher the sensitivity degree is, and the calculation can be performed by the following formula:
wherein E is the sensitivity coefficient of the evaluation index A to the factor F, deltaF is the change rate of the uncertainty factor F, deltaA is the change rate of the evaluation index A when the uncertainty factor F changes.
Fig. 1 shows the analysis results of the single parameter sensitivity analysis method.
And step 2, determining decision variables and constraint conditions affecting index parameters based on the analysis result of the single parameter sensitivity.
The index parameters comprise the climbing rate of the aircraft and the range of the aircraft, the decision variables are influencing factors for determining the basic performance of the aircraft, the influencing factors comprise weight, engine thrust and aerodynamic force, and the constraint conditions are that the variation range of the decision variables is between 5% and 25%.
In an example, the performance index parameters of the aircraft are analyzed, sensitive factors are determined and selected as decision variables, other parameters are kept at neutral values unchanged during analysis, parameters to be analyzed are adjusted each time, the parameters to be analyzed are increased or decreased according to a certain percentage (for example, constraint transformation is performed according to 5% -20%), and objective functions are the performance index parameters facing the aircraft, including standard atmosphere and pressure altitude, lift and drag characteristics of the aircraft, thrust and oil consumption characteristics of the engine, overall parameters of an engine body platform, weight of the aircraft, lift and brake characteristics and the like.
And step 3, carrying out large-sample optimization on the aircraft index parameter value to obtain an aircraft index parameter value optimization solution space.
In this embodiment, the large-sample optimization of the aircraft index parameter value may be performed on the basis of an improved genetic algorithm, and the large-sample optimization may be performed on two or more decision variables at a time, and an optimization target may be set according to the overall design index of the aircraft.
Wherein the improved genetic algorithm is as follows: and adopting an optimal preservation strategy, and adopting the optimal preservation strategy when selecting the optimizing target.
The problem of premature convergence of a genetic algorithm is one of the more prominent problems in the current genetic algorithm, the premature convergence refers to the phenomenon that super individuals appear in a population in the early stage of the genetic algorithm, and the adaptive value of the individuals greatly exceeds the average individual adaptive value of the current population, so that the individuals quickly occupy absolute proportion in the population, the diversity of the population is quickly reduced, and the evolution capability of the population is basically lost, so that the algorithm is converged to a local optimal solution earlier.
The most conditional preservation strategy, i.e. conditional delivery of the best individual directly to the next generation or at least equivalent to the previous generation, is adopted in this embodiment, which effectively prevents premature convergence.
The optimal preservation strategy is that the individuals with highest fitness in the current population do not participate in crossover operation and mutation operation, but replace the individuals with low fitness generated by crossover, mutation and other genetic operations in the current population.
The specific operation process of the optimal preservation strategy evolution model is as follows:
finding out the individual with the highest fitness and the individual with the lowest fitness in the current group;
if the fitness of the best individual in the current group is higher than the fitness value of the total best individual so far, the best individual in the current group is used as the new best individual so far;
the worst individual in the current population is replaced with the best individual so far.
In some embodiments, obtaining the aircraft index parameter value optimization solution space includes the steps of:
setting a variation range value of a decision variable as a simulation input;
three genetic operators of design selection, hybridization and mutation are used as search tools;
and taking the optimized solution space as a design criterion of index parameters.
The specific method for taking three genetic operators of design selection, hybridization and mutation as search tools comprises the following steps: determining a coding method; determining a decoding method; determining a fitness conversion rule; designing a genetic factor; an operating parameter is determined.
Fig. 2 shows a multi-parameter sensitivity optimization method optimal value change trend graph, and fig. 3 shows a multi-parameter sensitivity optimization method optimal solution space.
And 4, optimizing the sensitivity of the index parameters of the aircraft by using the optimized solution space.
According to the method, an fitness function is used as a function for detecting individual fitness, in a specific design, design balance is carried out according to the range requirement of specific index parameters of the aircraft design, and the aircraft design balance and coordination are carried out with related professional comprehensive design balance and coordination of weight, engines, aerodynamic force and the like, and the aircraft design constraint conditions such as weight increasing and decreasing scheme, engine cost, aerodynamic layout requirement and the like are selected and replaced according to the specific design.
Thus far, the technical solution of the present application has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present application is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present application, and such modifications and substitutions will be within the scope of the present application.
Claims (5)
1. An aircraft index parameter sensitivity optimization method based on a genetic algorithm is characterized by comprising the following steps:
analyzing single parameter sensitivity;
determining decision variables and constraint conditions affecting index parameters based on the analysis result of the single parameter sensitivity;
performing large sample optimization on the aircraft index parameter value to obtain an aircraft index parameter value optimization solution space;
optimizing the sensitivity of the index parameters of the aircraft by using an optimized solution space;
analyzing single parameter sensitivity, including
Searching a sensitive point selection index parameter;
carrying out transformation of a sensitivity interval on the sensitive points;
calculating index parameters of the aircraft;
searching a change rule of aircraft index parameters;
carrying out sensitivity degree analysis to obtain a conclusion of single-parameter sensitivity analysis;
performing large sample optimization on aircraft index parameter values, including:
based on an improved genetic algorithm, carrying out large-sample optimization on more than two decision variables at a time, and setting an optimization target according to the overall design index of the aircraft;
wherein the improved genetic algorithm is: adopting an optimal preservation strategy, and adopting the optimal preservation strategy when selecting an optimal target;
obtaining an aircraft index parameter value optimization solution space, comprising:
setting a variation range value of a decision variable as a simulation input;
three genetic operators of design selection, hybridization and mutation are used as search tools;
and taking the optimized solution space as a design criterion of index parameters.
2. The aircraft index parameter sensitivity optimization method based on genetic algorithm according to claim 1, wherein the sensitivity coefficient is calculated according to the following formula:
E＝△A
△F
wherein E is the sensitivity coefficient of the evaluation index A to the factor F, deltaF is the change rate of the uncertainty factor F, deltaA is the change rate of the evaluation index A when the uncertainty factor F changes.
3. The method for optimizing sensitivity of aircraft index parameters based on genetic algorithm according to claim 1, wherein the index parameters include a climb rate of an aircraft and a range of the aircraft.
4. The method for optimizing sensitivity of aircraft index parameters based on genetic algorithm according to claim 1, wherein the decision variable is an influencing factor determining basic performance of the aircraft, wherein the influencing factor includes weight, engine thrust, and aerodynamic force.
5. The genetic algorithm-based aircraft index parameter sensitivity optimization method according to claim 4, wherein the constraint condition is that the variation range of the decision variable is between 5% and 25%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811409820.0A CN109684666B (en) | 2018-11-23 | 2018-11-23 | Aircraft index parameter sensitivity optimization method based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811409820.0A CN109684666B (en) | 2018-11-23 | 2018-11-23 | Aircraft index parameter sensitivity optimization method based on genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109684666A CN109684666A (en) | 2019-04-26 |
| CN109684666B true CN109684666B (en) | 2023-05-23 |
Family
ID=66185753
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811409820.0A Active CN109684666B (en) | 2018-11-23 | 2018-11-23 | Aircraft index parameter sensitivity optimization method based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109684666B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110376892A (en) * | 2019-07-16 | 2019-10-25 | 东华大学 | A kind of aircraft automatic calibrating method |
| CN118821619B (en) * | 2024-09-14 | 2024-11-22 | 天目山实验室 | Sensitivity analysis-based high-speed aircraft maneuvering countermeasure design method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101226606A (en) * | 2007-11-16 | 2008-07-23 | 燕山大学 | Optimizing method of process parameters for mechanical diameter expansion of tubular parts |
| CN102194025A (en) * | 2010-03-08 | 2011-09-21 | 利弗莫尔软件技术公司 | Improved method and system in engineering design optimization based on multi-objective evolutionary algorithm |
| CN103293962A (en) * | 2013-06-18 | 2013-09-11 | 北京理工大学 | Planet gravity-assist low-thrust trajectory optimization method based on decomposition and coordination strategy |
| CN104598687A (en) * | 2015-01-26 | 2015-05-06 | 北京工商大学 | Optimized construction method for photovoltaic storage battery power supply system of small buoy power source for water quality monitoring |
| CN105183927A (en) * | 2015-05-11 | 2015-12-23 | 上海宇航系统工程研究所 | Multi-satellite separation parameter optimization method |
| CN105550434A (en) * | 2015-12-10 | 2016-05-04 | 南车株洲电力机车有限公司 | Locomotive body light weight optimization method |
| CN105975712A (en) * | 2016-05-20 | 2016-09-28 | 南京航空航天大学 | Design optimization method for spacecraft passive thermal control parameters |
| CN105975658A (en) * | 2016-04-27 | 2016-09-28 | 北京空间飞行器总体设计部 | A Modeling Method for Takeoff Stability |
| CN106548000A (en) * | 2016-12-16 | 2017-03-29 | 中国航空工业集团公司沈阳飞机设计研究所 | A kind of aircraft efficiency sensitivity analysis method |
| CN106599411A (en) * | 2016-11-30 | 2017-04-26 | 中国航空工业集团公司沈阳飞机设计研究所 | Redundancy configuration optimization method for aircraft system |
| CN108509722A (en) * | 2018-04-02 | 2018-09-07 | 西北工业大学 | Aircraft sensibility based on support vector machines weighs optimization method |
-
2018
- 2018-11-23 CN CN201811409820.0A patent/CN109684666B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101226606A (en) * | 2007-11-16 | 2008-07-23 | 燕山大学 | Optimizing method of process parameters for mechanical diameter expansion of tubular parts |
| CN102194025A (en) * | 2010-03-08 | 2011-09-21 | 利弗莫尔软件技术公司 | Improved method and system in engineering design optimization based on multi-objective evolutionary algorithm |
| CN103293962A (en) * | 2013-06-18 | 2013-09-11 | 北京理工大学 | Planet gravity-assist low-thrust trajectory optimization method based on decomposition and coordination strategy |
| CN104598687A (en) * | 2015-01-26 | 2015-05-06 | 北京工商大学 | Optimized construction method for photovoltaic storage battery power supply system of small buoy power source for water quality monitoring |
| CN105183927A (en) * | 2015-05-11 | 2015-12-23 | 上海宇航系统工程研究所 | Multi-satellite separation parameter optimization method |
| CN105550434A (en) * | 2015-12-10 | 2016-05-04 | 南车株洲电力机车有限公司 | Locomotive body light weight optimization method |
| CN105975658A (en) * | 2016-04-27 | 2016-09-28 | 北京空间飞行器总体设计部 | A Modeling Method for Takeoff Stability |
| CN105975712A (en) * | 2016-05-20 | 2016-09-28 | 南京航空航天大学 | Design optimization method for spacecraft passive thermal control parameters |
| CN106599411A (en) * | 2016-11-30 | 2017-04-26 | 中国航空工业集团公司沈阳飞机设计研究所 | Redundancy configuration optimization method for aircraft system |
| CN106548000A (en) * | 2016-12-16 | 2017-03-29 | 中国航空工业集团公司沈阳飞机设计研究所 | A kind of aircraft efficiency sensitivity analysis method |
| CN108509722A (en) * | 2018-04-02 | 2018-09-07 | 西北工业大学 | Aircraft sensibility based on support vector machines weighs optimization method |
Non-Patent Citations (2)
| Title |
|---|
| 基于遗传算法的复合材料圆柱壳屈曲多目标优化设计;刘钢等;《强度与环境》;20080415(第02期);全文 * |
| 飞机总体设计中的一种多目标鲁棒优化方法;周盛强等;《工程设计学报》;20061230(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109684666A (en) | 2019-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111176807B (en) | Multi-star collaborative task planning method | |
| CN109684666B (en) | Aircraft index parameter sensitivity optimization method based on genetic algorithm | |
| CN112580228B (en) | Fan blade structural design optimization method for mixed structure of turbofan engine | |
| CN113935132B (en) | Parameter optimization method of viscous damper based on improved multi-objective particle swarm optimization algorithm | |
| CN113434401B (en) | Software defect prediction method based on sample distribution characteristics and SPY algorithm | |
| CN114970115B (en) | A calculation method for fuel consumption and efficiency of excavator | |
| CN114564787A (en) | Bayesian optimization method, device and storage medium for target-related airfoil design | |
| CN112651533A (en) | Integrated moving average autoregression-back propagation neural network prediction method | |
| Łapa | Meta-optimization of multi-objective population-based algorithms using multi-objective performance metrics | |
| CN114282320A (en) | Method for optimizing engineering parameters by using Bayesian optimization algorithm | |
| CN109583480A (en) | One kind being used for aero-engine anti-asthma control system bathtub curve estimation method | |
| CN113868960B (en) | Soil heavy metal characteristic selection method and system based on typical related forests | |
| WO2017073445A1 (en) | Device, method, and program for selecting explanatory variable | |
| CN111222738B (en) | A method for wind power cluster power prediction and parameter optimization | |
| CN119066983A (en) | A machine learning-guided dynamic population optimization design method | |
| CN114861800A (en) | Model training method, probability determination method, device, equipment, medium and product | |
| CN118944064A (en) | A line backup constant value tuning method based on improved particle swarm optimization algorithm | |
| CN114326404B (en) | Aeroengine overrun protection control law design method based on low-selection-high-selection architecture | |
| CN112213090B (en) | Simplified spectrum compilation method for damage tolerance of helicopter maneuvering component | |
| CN112347153A (en) | Blast furnace wall internal type judging method, terminal equipment and storage medium | |
| Arsenyev et al. | Surrogate-based Robust Shape Optimization for Vane Clusters | |
| CN118395636B (en) | Performance evaluation optimization method and system for aviation gas turbine shaft engine | |
| CN111144623A (en) | Fixed value tuning method based on self-adaptive learning factor particle swarm | |
| Machado et al. | Probabilistic Scores of Classifiers, Calibration is not Enough | |
| CN120407208A (en) | Intelligent resource scheduling method and system based on dynamic data lineage graph |
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 |