CN114722491B - Application method of integrated optimization design in fuel cabin shell forming based on proxy model - Google Patents
Application method of integrated optimization design in fuel cabin shell forming based on proxy model Download PDFInfo
- Publication number
- CN114722491B CN114722491B CN202210274817.2A CN202210274817A CN114722491B CN 114722491 B CN114722491 B CN 114722491B CN 202210274817 A CN202210274817 A CN 202210274817A CN 114722491 B CN114722491 B CN 114722491B
- Authority
- CN
- China
- Prior art keywords
- model
- initial
- die
- proxy model
- proxy
- 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
- 238000013461 design Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000005457 optimization Methods 0.000 title claims abstract description 25
- 239000000446 fuel Substances 0.000 title claims abstract description 18
- 238000004088 simulation Methods 0.000 claims abstract description 31
- 239000003795 chemical substances by application Substances 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000003856 thermoforming Methods 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims abstract description 13
- 239000002828 fuel tank Substances 0.000 claims abstract description 11
- 238000005070 sampling Methods 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 7
- 230000004044 response Effects 0.000 claims description 21
- 239000000463 material Substances 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 229910000838 Al alloy Inorganic materials 0.000 claims description 7
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims 2
- 230000006870 function Effects 0.000 description 15
- 230000003993 interaction Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000012805 post-processing Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000465 moulding Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- 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]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/04—Architectural design, interior design
-
- 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
Abstract
The invention discloses an application method of integrated optimization design in fuel cabin shell forming based on a proxy model; the method specifically comprises the following steps: parameterizing to establish a fuel tank shell thermoforming stamping process simulation 3D model, DOE test design and initial sampling, constructing an initial Kriging model, and evaluating agent model precision and optimizing sequence adding points. According to the invention, the agent model is combined with parameterized integrated calculation, so that the automation of the process optimization agent model for constructing the fuel tank shell is realized, the parameterization of the pretreatment and the post-treatment of the finite element simulation is realized, the whole process is constructed conveniently and simply, the operation is only needed to be performed on an optimal design platform constructed based on Matlab, the time and the labor are greatly saved, and the method has good engineering applicability.
Description
Technical Field
The invention belongs to the technical field of engineering design, and particularly relates to an application method of integrated optimization design in fuel cabin shell forming based on a proxy model.
Background
The problem that the performance evaluation function is difficult to acquire is often faced before the complex engineering problem, the problem of high calculation cost is faced when the high-precision simulation model is established for optimizing, the current situation is effectively alleviated by the appearance of the proxy model technology, and students develop and deeply study the optimization method based on the proxy model and widely apply the method in engineering and other fields. At present, the application of the agent model technology at home and abroad has remarkable effects in various fields of aircraft wing optimization, ship sailing performance, turbine blade simulation, aerodynamics, hydrodynamics and the like. In the process of constructing the proxy model, in order to obtain a high-precision proxy model, a large number of sample points are required to be extracted in a design space, which means expensive simulation cost, so that in order to reduce the number of samples, the best-applied adaptive dynamic point adding strategy is studied nowadays, namely, the proxy model is continuously updated while adding points until the precision requirement is met.
Whether initial sampling or self-adaptive addition is carried out, the simulation model needs to be repeatedly called to obtain the real response value of the target performance function, when the hidden function relation between the design variable and the target function is complex or very complex, a large number of sample points are needed to simulate the relation between the design variable and the target function, as the iteration times are increased, the needed sample points are also increased, when the facing engineering object is very complex, perhaps hundreds or thousands of sample points are needed, which means that hundreds or thousands of simulation models need to be called, and if manual call simulation is adopted, huge time and labor are definitely consumed. Therefore, in the invention, the typical hot working process is taken as an example, the Matlab calculation software is used for carrying out pre-post treatment secondary development on the finite element analysis software Abaqus through Python language, so that the data interaction between the Matlab and the Abaqus is realized, and the establishment of a hot forming integrated simulation calculation process parameter optimization platform based on the self-adaptive agent model is completed based on the Matlab.
Abaqus is one of the most universal large nonlinear finite element analysis software internationally at present, the software comprises various rich material libraries and unit libraries, can simulate the linear and nonlinear behaviors of most engineering materials, has strong combination capability between the materials and units, and can realize static and dynamic analysis of complex structures. The Python language is a simple and powerful programming language, has a high-level data structure with high efficiency, can simply and effectively realize object-oriented programming, simple grammar of Python and support for dynamic input, and is an ideal scripting language on most platforms due to the nature of an explanatory language, and is particularly suitable for rapid application program development. There are generally 4 pathways for secondary Abaqus development: (1) Developing a new model through a user subroutine, and controlling an Abaqus calculation process and a calculation result; (2) changing the default settings by the environment initialization file; (3) The preprocessing modeling and the post-processing result analysis and calculation are realized through the kernel script; (4) A new graphical user interface and user interaction is created through the GUI script. The kernel script language of Abaqus is Python, a set of application program interfaces are provided for users to realize operations such as preprocessing, post-processing and the like, and the interface programming is also written by adopting Python grammar, so that the invention adopts the 3 rd method, and controls the Abaqus kernel to realize secondary development of preprocessing and post-processing by writing Python script files.
According to the invention, the self-adaptive agent model optimization is taken as a basic framework, the Matlab is combined with the mathematical calculation software to carry out secondary development on the front and back processing of Abaqus, so that the data interaction between the Matlab and the Abaqus is realized, the automatic joint simulation parameter optimization of the stamping forming simulation of the fuel cabin shell is realized, and the integrated calculation optimization design platform for thermoforming is integrated, and the whole flow is only required to be executed on the optimization design platform, so that the operation is convenient and simple.
Disclosure of Invention
The invention aims at: the agent model technology is widely applied to solve the problem of a black box in actual engineering and greatly reduce huge calculation load caused by complex analysis. However, when aiming at the more complex engineering problem, hundreds or thousands of sample points are needed for obtaining the proxy model meeting the precision requirement, which means hundreds or thousands of times of model simulation calculation analysis, so that in order to solve the problem of a large number of repeated operations of manual call simulation, an automatic parameterized joint simulation parameter optimization design method based on the proxy model is provided and integrated into an intelligent simulation optimization design platform, the operation steps for constructing the engineering proxy model are greatly simplified, and a large amount of time consumption is saved.
The technical scheme of the invention is as follows: the application method of the integrated optimization design in forming the fuel cabin shell based on the agent model is characterized by realizing an automatic flow based on the self-adaptive agent model of stamping forming of the fuel cabin shell, realizing no GUI interface parameterization pre-post treatment of the hot forming stamping process of the fuel cabin shell, realizing the automatic data interaction of Matlab and Abaqus, completing the construction of the agent model of the stamping forming process, optimizing the accuracy of the agent model through self-adaptive addition, and executing the whole built flow only on an integrated simulation platform, and comprises the following steps:
A. parameterized modeling is carried out, a fuel cabin shell thermoforming stamping process simulation 3D model is established, and material parameter attributes, dynamic display analysis steps, contact attributes and boundary conditions are set for the geometric model;
b, DOE test design, determining model design variables, obtaining an initial sample by using Latin hypercube sampling, determining an objective function, and obtaining an objective function response;
C. b, constructing an initial Kriging proxy model by the initial sample points and the corresponding real response values obtained in the step B;
D. using cross verification, adopting Root Mean Square Error (RMSE) as an evaluation index of agent model precision, acquiring an updated sample set through a point adding criterion and an intelligent evolution algorithm, and constructing an agent model meeting the precision requirement;
further, in the step A, a 3D model of the fuel tank shell thermoforming stamping simulation is established, material parameter attributes, dynamic display analysis steps, contact attributes and boundary conditions are set, and the model is established according to relevant dimension parameters through Abaqus software, and specifically the method comprises the following sub-steps:
A1. the forming plate is a 1024mm x 15mm rectangular plate, the material is 5A06 aluminum alloy, the table 1 is mechanical property data of Chinese 5A06 aluminum alloy at room temperature, the forming die is divided into four parts of an upper female die, a lower male die, a left female die and a right female die, and the material properties of the die are defined as rigid bodies;
table 1 chinese 5a06 aluminium alloy room temperature mechanical properties
| Elastic modulus/GPa | Yield strength sigma 0.2 /MPa | Tensile strength/MPa | Elongation at break/% | Shear Strength/MPa |
| 70.35 | 82.37 | 156.5 | 20.2 | 93.7 |
A2. Defining material properties, density 2630kg/m 3 Young's modulus of 70GPa and Poisson's ratio of 0.25, defining a dynamic display analysis step, and defining the contact attribute of a mold and a plate;
A3. setting boundary conditions, applying displacement load of 180mm in +y direction to the upper die, respectively applying displacement load of 285mm in +z and-z directions to the left die and the right die, and applying complete fixing constraint to the lower die;
A4. selecting a corresponding grid type and a corresponding grid size for grid division;
further, the step B is to determine model design variables, obtain initial samples by using Latin hypercube sampling, determine an objective function, and obtain an objective function response, and specifically comprises the following sub-steps:
B1. determining design variables, and acquiring initial samples by using Latin hypercube sampling rules;
B2. writing an external script to realize pretreatment parameterized modeling;
B3. selecting the maximum Mi Saisi stress (Maximum Mises Stress, MMS) after material molding as a performance function, and writing an external script to obtain a real response value of an initial sample;
further, the step C builds an initial Kriging proxy model according to the initial sample points generated in the step B and the corresponding response values, and records an initial Root Mean Square Error (RMSE);
further, the step D is based on the initial agent model established in the step C as a priori model, generates updated sample points meeting the requirements through an intelligent evolution algorithm and a point adding strategy, adds new points to reconstruct the initial agent model, and iterates repeatedly, finally obtains the agent model meeting the precision requirements, and the method specifically comprises the following steps:
D1. according to the step A, B, a geometric model of the fuel tank shell thermoforming stamping simulation is obtained, design variables and a value range affecting a system are determined, a design space is obtained, and an initial proxy model is obtained in the step C;
D2. optimizing the initial proxy model by using an intelligent evolution algorithm through a point adding strategy to obtain updated sample points, and performing parameterized simulation calculation to obtain performance function response values of the updated sample points;
D3. reconstructing a Kriging proxy model based on the D2 newly added point, judging whether the model RMSE meets the precision requirement, and outputting the Kriging model as a high-precision proxy model for hot stamping forming if the model RMSE meets the precision requirement; if the accuracy requirement is not met, returning to the step D2, adding a new sample point, and continuing to remodel the proxy model until the accuracy requirement is met.
The beneficial effects of the invention are as follows: the invention provides application of integrated calculation simulation parameter optimization based on a proxy model in stamping thermoforming of a fuel cabin shell for the first time, and has the key points of realizing data interaction between a Matlab computing platform and simulation software Abaqus, realizing automated modeling of Abaqus pretreatment and automatic extraction of post-treatment results by writing an external script, ensuring that the whole process does not need manual GUI operation, developing an integrated calculation optimization design platform, realizing automation of engineering-oriented parameter optimization design based on the proxy model, greatly reducing manpower consumption, simplifying operation, saving a large amount of time and having better practicability for other engineering problems.
Drawings
Fig. 1 is a technical flow chart of an application method of an integrated optimization design based on a proxy model in aluminum plate forming optimization.
FIG. 2 is a schematic representation of a finite element model of a fuel pod housing thermoforming stamping simulation system in accordance with the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
FIG. 1 is a schematic flow chart of an application method of the integrated optimization design based on the agent model in the fuel tank shell forming. An application method of integrated optimization design in fuel cabin shell forming based on a proxy model comprises the following steps:
A. parameterized modeling is carried out, a fuel cabin shell thermoforming stamping process simulation 3D model is established, and material parameter attributes, dynamic display analysis steps, contact attributes and boundary conditions are set for the geometric model;
b, DOE test design, determining model design variables, obtaining an initial sample by using Latin hypercube sampling, determining an objective function, and obtaining an objective function response;
C. b, constructing an initial Kriging proxy model by the initial sample points and the corresponding real response values obtained in the step B;
D. using cross verification, adopting Root Mean Square Error (RMSE) as an evaluation index of agent model precision, acquiring an updated sample set through a point adding criterion and an intelligent evolution algorithm, and constructing an agent model meeting the precision requirement;
the 3D model for establishing the aluminum alloy plate thermoforming and stamping simulation in the step a is established by using Abaqus software according to relevant dimensional parameters, as shown in fig. 2, which is a finite element model schematic diagram of the fuel tank shell thermoforming and stamping simulation in the invention, and the fuel tank shell forming simulation system is established, and specifically comprises the following sub-steps:
A1. the forming plate is a 1024mm x 15mm rectangular plate, the material is 5A06 aluminum alloy, the forming die is divided into four parts of an upper female die, a lower male die, a left female die and a right female die, and the material properties of the die are defined as rigid bodies;
A2. defining material properties, density 2630kg/m 3 Young's modulus is 70GPa, poisson's ratio is 0.25, initial time of a dynamic display analysis step is defined to be 1s, and initial friction coefficient of contact attribute between a die and a plate is defined to be 0.3;
A3. setting boundary conditions, applying displacement load of 180mm in +y direction to the upper die, respectively applying displacement load of 285mm in +z and-z directions to the left die and the right die, and applying complete fixing constraint to the lower die;
A4. the corresponding grid type and grid size are selected for grid division, the grid cell type of the fuel cabin shell is C3D8R, the global seed size is 5mm, the grid cell type of the mould is R3D4, and the global seed size is 5mm;
further, the step B is to determine model design variables, obtain initial samples by using Latin hypercube sampling, determine an objective function, and obtain an objective function response, and specifically comprises the following sub-steps:
B1. determining design variables, and acquiring initial samples by using Latin hypercube sampling rules; defining the process parameters to be optimized, defining x 1 、x 2 The specific meaning of the basic design variable is as follows:
x 1 : the loading time of the thermoforming stamping system is 0.5-1s;
x 2 : the contact friction coefficient of the hot forming stamping system is in the range of 0.10-0.5;
B2. writing a preprocess script to realize parameterized modeling of the shaping analog preprocessing;
B3. selecting the maximum Mi Saisi stress (Maximum Mises Stress, MMS) after material molding as a performance function, and writing a postprocess.py post-processing parameterized script to obtain a real response value of an initial sample;
further, the step C builds an initial Kriging proxy model by using the initial sample points generated in the step B and the corresponding response values, and records an initial determination coefficient RMSE;
further, the step D is based on the initial agent model established in the step C as a priori model, generates updated sample points meeting the requirements through an intelligent evolution algorithm and a point adding strategy, adds new points to reconstruct the initial agent model, and iterates repeatedly, finally obtains the agent model meeting the precision requirements, and the method specifically comprises the following steps:
D1. according to the step A, B, a geometric model of the fuel tank shell thermoforming stamping simulation is obtained, design variables and a value range affecting a system are determined, a design space is obtained, and an initial proxy model is obtained in the step C;
D2. optimizing an initial proxy model by using a differential evolution algorithm (DE) through a maximum Expected Improvement (EI) point adding strategy to obtain updated sample points, performing parameterized simulation calculation to obtain performance function response values of the updated sample points, wherein the maximum expected improvement function is represented by the following formula:
in the formula (1), phi (·) is a standard normal probability density function, y min Optimally responding to the current sample performance function;
D3. based on the D2 newly added points, adding the obtained updated points into a sample set, reconstructing a Kriging proxy model, judging whether the model RMSE meets the precision requirement, and outputting the Kriging model to be a high-precision proxy model for hot stamping forming of the fuel cabin shell if the model RMSE meets the precision requirement; if the accuracy requirement is not met, returning to the step D2, adding a new sample point, and continuing to remodel the proxy model until the accuracy requirement is met.
The root mean square error RMSE is used herein to evaluate the overall accuracy of constructing the proxy model, and the calculation formula of RMSE is:
in the formula (2), y i As the true response value of the test point,and n is the number of samples of the test point and is the predicted response value of the test point. The accuracy of the proxy model is evaluated by using the Root Mean Square Error (RMSE), the influence of a tested function is small, the solving result is stable, the accuracy of the proxy model can be intuitively expressed, the RMSE value is between 0 and 1, and the closer to 0 is the higher the accuracy of the proxy model.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (3)
1. An application method of integrated optimization design in fuel cabin shell forming based on a proxy model is characterized by comprising the following steps:
A. parameterized modeling is carried out, a 5A06 aluminum alloy rectangular plate fuel cabin shell thermoforming stamping process simulation 3D model is established, material parameter attributes, dynamic display analysis steps, contact attributes and boundary conditions are set for a geometric model, and the model is established through Abaqus software according to relevant size parameters, and the method specifically comprises the following sub-steps:
A1. the forming plate is a 1024mm x 15mm rectangular plate, the material is 5A06 aluminum alloy, the forming die is divided into four parts of an upper female die, a lower male die, a left female die and a right female die, and the material properties of the die are defined as rigid bodies;
A2. defining material properties, density 2630kg/m 3 Young's modulus of 70GPa and Poisson's ratio of 0.25, defining a dynamic display analysis step, and defining the contact attribute of a mold and a plate;
A3. setting boundary conditions, applying displacement load of 180mm in +y direction to the upper die, respectively applying displacement load of 285mm in +z and-z directions to the left die and the right die, and applying complete fixing constraint to the lower die;
A4. selecting a corresponding grid type and a corresponding grid size for grid division;
b, DOE test design, determining model design variables, obtaining an initial sample by using Latin hypercube sampling, determining an objective function, and obtaining an objective function response;
C. b, constructing an initial Kriging proxy model by the initial sample points and the corresponding real response values obtained in the step B;
D. by using cross verification, adopting Root Mean Square Error (RMSE) as an evaluation index for fitting the accuracy of a thermoforming proxy model of the fuel cabin shell, acquiring an updated sample set through a point adding criterion and an intelligent evolution algorithm, and constructing a proxy model meeting the accuracy requirement, wherein the method specifically comprises the following steps of:
D1. according to the step A, B, a geometric model of the fuel tank shell thermoforming stamping simulation is obtained, design variables and a value range affecting a system are determined, a design space is obtained, and an initial proxy model is obtained in the step C;
D2. optimizing the initial proxy model by using an intelligent evolution algorithm through a point adding strategy to obtain updated sample points, and performing parameterized simulation calculation to obtain performance function response values of the updated sample points;
D3. reconstructing a Kriging proxy model based on the D2 newly added point, judging whether the model RMSE meets the precision requirement, and outputting the Kriging model as a high-precision proxy model for hot stamping forming if the model RMSE meets the precision requirement; if the accuracy requirement is not met, returning to the step D2, adding a new sample point, and continuing to remodel the proxy model until the accuracy requirement is met.
2. The method for applying the integrated optimization design based on the proxy model to the formation of the fuel tank shell according to claim 1, wherein the step B is used for determining the model design variables, acquiring an initial sample by using Latin hypercube sampling, determining an objective function and acquiring an objective function response, and specifically comprises the following sub-steps:
B1. determining design variables, and acquiring initial samples by using Latin hypercube sampling rules;
B2. writing an external script to realize pretreatment parameterized modeling;
B3. and selecting the maximum Mi Saisi stress (MaximumMisesStress, MMS) of the molded material as a performance function, and writing an external script to obtain a real response value of the initial sample.
3. The method for applying the integrated optimization design based on the agent model to the formation of the fuel tank shell according to claim 1, wherein the step C is to construct an initial Kriging agent model by using the initial sample points generated in the step B and the corresponding response values, and record an initial Root Mean Square Error (RMSE).
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210069088 | 2022-01-21 | ||
| CN2022100690887 | 2022-01-21 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114722491A CN114722491A (en) | 2022-07-08 |
| CN114722491B true CN114722491B (en) | 2023-10-24 |
Family
ID=82237801
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210274817.2A Active CN114722491B (en) | 2022-01-21 | 2022-03-21 | Application method of integrated optimization design in fuel cabin shell forming based on proxy model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114722491B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005671A (en) * | 2015-07-30 | 2015-10-28 | 中航沈飞民用飞机有限责任公司 | Dynamics simulation analysis method of uniformly distributed load bearing system |
| CN105956342A (en) * | 2016-06-23 | 2016-09-21 | 北京航空航天大学 | Self-locking composite pre-deformation cabin door structure optimization design method |
| CN109977576A (en) * | 2019-04-03 | 2019-07-05 | 北京理工大学 | A kind of constellation system multidisciplinary design optimization based on agent model |
| CN111783278A (en) * | 2020-06-04 | 2020-10-16 | 中国人民解放军军事科学院国防科技创新研究院 | Satellite layout optimization design method based on multi-modal distribution estimation algorithm |
| CN112446110A (en) * | 2020-11-06 | 2021-03-05 | 电子科技大学 | Application method of EOASM algorithm in proxy model construction of robot palletizer driving arm seat |
| CN112784361A (en) * | 2021-01-25 | 2021-05-11 | 武汉理工大学 | Method for optimizing structure of automobile engine compartment heat dissipation system based on proxy model |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7937169B2 (en) * | 2006-08-25 | 2011-05-03 | The Boeing Company | System and method for compartment control |
| FR3038770B1 (en) * | 2015-07-10 | 2021-03-19 | Innov Plus | OPERATOR VIGILANCE MONITORING SYSTEM |
-
2022
- 2022-03-21 CN CN202210274817.2A patent/CN114722491B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005671A (en) * | 2015-07-30 | 2015-10-28 | 中航沈飞民用飞机有限责任公司 | Dynamics simulation analysis method of uniformly distributed load bearing system |
| CN105956342A (en) * | 2016-06-23 | 2016-09-21 | 北京航空航天大学 | Self-locking composite pre-deformation cabin door structure optimization design method |
| CN109977576A (en) * | 2019-04-03 | 2019-07-05 | 北京理工大学 | A kind of constellation system multidisciplinary design optimization based on agent model |
| CN111783278A (en) * | 2020-06-04 | 2020-10-16 | 中国人民解放军军事科学院国防科技创新研究院 | Satellite layout optimization design method based on multi-modal distribution estimation algorithm |
| CN112446110A (en) * | 2020-11-06 | 2021-03-05 | 电子科技大学 | Application method of EOASM algorithm in proxy model construction of robot palletizer driving arm seat |
| CN112784361A (en) * | 2021-01-25 | 2021-05-11 | 武汉理工大学 | Method for optimizing structure of automobile engine compartment heat dissipation system based on proxy model |
Non-Patent Citations (2)
| Title |
|---|
| Design optimization for A Cabin-Skeleton Coupling Structure of Blended-wing-body Underwater Glider;Yijin Zhang等;《2020 3rd International Conference on Unmanned Systems (ICUS)》;第189-194页 * |
| 近炸多姿态弹目对抗下目标毁伤建模研究;朱莉娜等;《国外电子测量技术》;第30-33页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114722491A (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108647370B (en) | Unmanned helicopter aerodynamic shape optimization design method based on double-ring iteration | |
| CN111597631B (en) | Automobile wind resistance coefficient optimization method based on self-adaptive agent model | |
| CN112446110B (en) | Application method of agent model based on EOASM algorithm in robot palletizer driving arm seat | |
| CN107273569B (en) | Aerodynamic configuration drag reduction optimization method based on mesh deformation technique | |
| CN114065662B (en) | Method suitable for rapidly predicting airfoil flow field with variable grid topology | |
| CN112414668B (en) | Wind tunnel test data static bomb correction method, device, equipment and medium | |
| Choe et al. | Uncertainty quantification of stochastic simulation for black-box computer experiments | |
| CN111553025B (en) | Method for controlling gap section difference of automobile engine hood assembly | |
| CN115630438A (en) | Method and device for calculating rigidity of automobile opening and closing member based on CATIA secondary development and storage medium | |
| CN115906303A (en) | Planar microwave filter design method and device based on machine learning | |
| CN114722491B (en) | Application method of integrated optimization design in fuel cabin shell forming based on proxy model | |
| CN115983029A (en) | Method, device and medium for constructing reliability simulation digital twin model of aviation equipment | |
| CN117236111A (en) | Fastener parametric modeling method and device, terminal equipment and storage medium | |
| CN109063402B (en) | Method for simulating wind side of heat dissipation system in complex flow field | |
| CN113392436B (en) | CAE analysis software and office software integrated control method and platform | |
| Li et al. | A geometric feature-based design system of full parametric association modeling of standard cam for automotive stamping dies | |
| CN109710988B (en) | Wing body fusion body aircraft main beam position determining method | |
| CN111027250A (en) | Special-shaped curved surface reinforced shell modeling method based on grid deformation technology | |
| CN111081322B (en) | Modeling method of closed-cell foam wave-absorbing material | |
| CN117077551B (en) | Non-embedded uncertainty quantization method based on gradient enhancement stochastic Co-Kriging model | |
| CN117077298B (en) | Aircraft robust optimization design method based on gradient enhancement random Co-Kriging model | |
| CN117150851A (en) | Structural design analysis optimization integrated method and system based on intelligent interaction | |
| CN116522740B (en) | Method, device, equipment and medium for capturing oil-gas interface of engine nozzle | |
| CN113536448A (en) | Processing method and device for establishing finite element analysis model and upper computer | |
| CN116468074A (en) | Circuit design optimization method and system based on deep learning |
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 |