CN114547993A - Intelligent prediction method for aerodynamic performance of automobile - Google Patents
Intelligent prediction method for aerodynamic performance of automobile Download PDFInfo
- Publication number
- CN114547993A CN114547993A CN202210146539.2A CN202210146539A CN114547993A CN 114547993 A CN114547993 A CN 114547993A CN 202210146539 A CN202210146539 A CN 202210146539A CN 114547993 A CN114547993 A CN 114547993A
- Authority
- CN
- China
- Prior art keywords
- data
- automobile
- aerodynamic performance
- aerodynamic
- flow field
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—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
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- 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
-
- 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)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Mathematical Optimization (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Computation (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Automation & Control Theory (AREA)
- Algebra (AREA)
- Computing Systems (AREA)
- Fluid Mechanics (AREA)
- Mathematical Physics (AREA)
- Aerodynamic Tests, Hydrodynamic Tests, Wind Tunnels, And Water Tanks (AREA)
Abstract
The invention provides an intelligent prediction method for aerodynamic performance of an automobile, which comprises the following steps: obtaining vehicle appearance structure parameterization data, flow field simulation data and flow field test data, and building a data system; carrying out filtering and denoising on data in the database, extracting characteristic data related to strong pneumatic performance, and carrying out data analysis and fusion; the intelligent prediction of aerodynamic performance parameters is realized; and updating the automobile aerodynamic prediction function to realize the automobile aerodynamic performance prediction. By building an aerodynamic digital development application scene in the field of automobile research and development, the method has wide industrial application value in the aspects of reducing development cost, improving development efficiency and quality and the like. The technology shows that a high-efficiency, low-cost and high-quality digital solution can be provided for automobile enterprises by means of machine learning and digitization in a full development process, and has a certain industry demonstration effect.
Description
Technical Field
The invention belongs to the technical field of automobile research and development, and particularly relates to an intelligent prediction method for aerodynamic performance of an automobile.
Background
Under the background of a double-carbon target, the aerodynamic development of automobiles becomes an important technology for automobile enterprises to meet new challenges of energy conservation and emission reduction. By building an aerodynamic target-driven digital development platform, an aerodynamic technology is fused with an automobile model design, the influence mechanism and rule of an automobile body flow field on automobile aerodynamics are disclosed, a research and development mode mainly based on human is converted into a data-driven research and development mode, and a systematic aerodynamic digital solution is formed.
The traditional development process of the aerodynamic performance of the automobile mainly adopts manual iteration, in the automobile design stage, an aerodynamic team, a modeling team and an engineering design team coordinate and iterate design mutually, the design period is long, the design cost is high, the optimization process is in the middle and later stages of automobile type development, early development means and tools are lacked, and on the premise of lacking effective data support, a method or means capable of rapidly and efficiently predicting the aerodynamic performance is absent, so that the development difficulty is high, and the target realization is influenced.
At present, the aerodynamic performance development is mainly based on the experience of engineers, analysis and optimization are carried out based on limited flow field information, certain wind tunnel testing capacity is achieved, the excavating and intelligent processing capacity of the flow field information is lacked, data accumulation is few, accumulation is slow, development capacity is limited, the difficulty in improving the quality of a development project is high, and innovation and expansion of aerodynamic directional business are hindered.
With the development of digital technology, automobile research and development face significant technical change, vehicle aerodynamic development is realized by means of machine learning and digitization, and the method is a key common problem faced by aerodynamics. No aerodynamic digital development platform exists in China, but the requirement of the industry for aerodynamic research and development of digital transformation is urgent.
Disclosure of Invention
In view of the above, the invention aims to provide an intelligent prediction method for aerodynamic performance of an automobile, so as to quantitatively evaluate the influence of structural parameters of the automobile on the aerodynamic performance, and has important significance for guiding vehicle design and improving the efficiency of aerodynamic performance development.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
an intelligent prediction method for automobile aerodynamic performance comprises the following steps:
s1, obtaining shape structure parameterization data, flow field simulation data and flow field test data of the vehicle;
s2, building a data system according to the data acquired in the step S1;
s3, carrying out filtering and denoising on data in the database by adopting an integrated Kalman filtering method, extracting characteristic data strongly related to aerodynamic performance, and carrying out data analysis and fusion;
s4, establishing a functional relation between an aerodynamic performance target function and each variable of vehicle structure parameters, flow field pressure and flow field speed by utilizing a nonlinear fitting or artificial neural network method, and realizing the intelligent prediction of the aerodynamic performance parameters;
and S5, analyzing the difference between the prediction result and the actual measurement result by adopting a root mean square error, and calibrating and optimizing the automobile aerodynamic prediction model according to the analysis result, so that the automobile aerodynamic prediction function is updated, and the automobile aerodynamic performance prediction is realized.
Further, in step S1, vehicle exterior structure parameterization data is obtained through an automatic identification algorithm, vehicle flow field simulation data is obtained through a digital wind tunnel method, and vehicle flow field test data is obtained through a pneumatic acoustic wind tunnel method.
Further, the shape structure parameters in step S1 include angle data and height data of each part of the automobile, and angle data and distance data between parts.
Further, in step S2, the database system obtains vehicle aerodynamic performance parameters through a wind tunnel test, a road test, and a CFD simulation;
the aerodynamic performance parameters of the vehicle comprise aerodynamic force, wind speed around the automobile and pressure distribution.
Further, in step S3, the data fusion is performed by using a gaussian regression method to fuse the data obtained by the simulation and the test.
Further, the functional relationship formula in step S4 is as follows:
Cd＝k*f(Xn,Pn,Vn) Wherein, CdIs the wind resistance coefficient; xn ═ x1,x2,...xn) Geometrically structuring parameters for the automobile model; p ═ P (P)1,p2,...pn) Is the pressure in the flow field; v ═ V (V)1,v2,...vn) Is the velocity in the flow field.
Further, in the step S4, in the intelligent prediction process of the aerodynamic performance parameters, an adaptive spatial transformation is used to scale the known parameters.
Compared with the prior art, the intelligent prediction method for the aerodynamic performance of the automobile has the following advantages:
(1) the intelligent prediction method for the aerodynamic performance of the automobile, provided by the invention, has a wide industrial application value in the aspects of reducing the development cost, improving the development efficiency and quality and the like by building an aerodynamic digital development application scene in the field of automobile research and development.
(2) The intelligent automobile aerodynamic performance prediction method disclosed by the invention shows that a high-efficiency, low-cost and high-quality digital solution can be provided for automobile enterprises by means of machine learning and digitization in a full development process, and has a certain industry demonstration effect.
(3) The intelligent automobile aerodynamic performance prediction method changes the traditional performance development mode mainly based on human into the intelligent development mode, reuses the model and data and precipitates knowledge, so that the development efficiency and quality of aerodynamic performance are greatly improved, and the method has better innovation value.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation of the invention. In the drawings:
FIG. 1 is a functional schematic diagram of an aerodynamic performance prediction of an automobile according to an embodiment of the present invention;
FIG. 2 is a first schematic view of parameters of a structural portion of an automobile according to an embodiment of the present invention;
fig. 3 is a second schematic parameter diagram of the automobile structure according to the embodiment of the invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
An intelligent prediction method for automobile aerodynamic performance comprises the following steps:
step 1: data acquisition and collection, vehicle external shape structure parameterized data (x1, x 2.. xn), flow field simulation data (pressure (p1, p 2.. pn), speed (v1, v 2.. vn), drag coefficient Cd, lift coefficient Cl, lateral force coefficient Cs..), flow field test data (pressure (p1, p 2.. pn), speed (v1, v 2.. vn), drag coefficient Cd, lift coefficient Cl, lateral force coefficient Cs..) are respectively obtained through technical means such as an automatic identification algorithm, a digital wind tunnel, a vehicle and wind tunnel laboratory digitalized model are established in the digital wind tunnel, obtaining simulation data of a flow field around the vehicle by utilizing a computational fluid dynamics algorithm, wherein the simulation data comprises pressure, speed, aerodynamic coefficient and the like; the method comprises the following steps that a pneumatic acoustic wind tunnel obtains flow field test data including pressure, speed, aerodynamic coefficient and the like by using a wind tunnel test technology;
the digital wind tunnel comprises a simplified wind tunnel resident chamber geometric model, a road surface simulation equipment model and a vehicle model to be tested;
step 2, building a database system through the collected vehicle appearance structure parameterization data, flow field simulation data and test data;
the database system obtains vehicle aerodynamic performance parameters including aerodynamic force, wind speed around the vehicle, pressure distribution and the like through wind tunnel tests, road tests, CFD simulation and the like.
Step 3, carrying out filtering and denoising on the data in the database by adopting an integrated Kalman filtering method, extracting characteristic data relevant to strong pneumatic performance, and carrying out data analysis and fusion;
the data fusion adopts a Gaussian regression method to fuse the data obtained by simulation and test;
establishing a functional relation between an aerodynamic performance target function and variables such as vehicle structure parameters, flow field pressure, flow field speed and the like by using methods such as nonlinear fitting or artificial neural networks and the like, wherein Cd is k f (Xn, Pn and Vn), and realizing the intelligent prediction of aerodynamic performance parameters;
wherein Cd is a wind resistance coefficient; xn ═ (x1, x 2.. Xn) is the automotive build geometry parameters; p ═ P1, P2.. pn) is the pressure in the flow field; v ═ V1, V2.. vn) is the velocity in the flow field;
in the intelligent prediction process of the aerodynamic performance parameters, the known parameters are scaled by adopting self-adaptive spatial transformation;
and 5: and analyzing the difference between the prediction result and the actual measurement result by adopting a root mean square error, and calibrating and optimizing the automobile aerodynamic prediction model according to the analysis result, so that an automobile aerodynamic prediction function is updated, and the automobile aerodynamic performance prediction is realized.
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, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. An intelligent prediction method for automobile aerodynamic performance is characterized by comprising the following steps:
s1, obtaining shape structure parameterization data, flow field simulation data and flow field test data of the vehicle;
s2, building a data system according to the data acquired in the step S1;
s3, carrying out filtering and denoising on data in the database by adopting an integrated Kalman filtering method, extracting characteristic data strongly related to aerodynamic performance, and carrying out data analysis and fusion;
s4, establishing a functional relation between an aerodynamic performance target function and each variable of vehicle structure parameters, flow field pressure and flow field speed by utilizing a nonlinear fitting or artificial neural network method, and realizing the intelligent prediction of the aerodynamic performance parameters;
and S5, analyzing the difference between the prediction result and the actual measurement result by adopting a root mean square error, and calibrating and optimizing the automobile aerodynamic prediction model according to the analysis result, so that the automobile aerodynamic prediction function is updated, and the automobile aerodynamic performance prediction is realized.
2. The intelligent automobile aerodynamic performance prediction method according to claim 1, wherein in step S1, vehicle shape structure parameterization data is obtained through an automatic recognition algorithm, vehicle flow field simulation data is obtained through a digital wind tunnel method, and vehicle flow field test data is obtained through a pneumatic acoustic wind tunnel method.
3. The intelligent automobile aerodynamic performance prediction method of claim 1, wherein the configuration parameters in step S1 include angle data, height data, and angle data and distance data between components of the automobile.
4. The intelligent automobile aerodynamic performance prediction method according to claim 1, characterized in that in step S2, the database system obtains the parameters of the aerodynamic performance of the automobile through a wind tunnel test, a road test and a CFD simulation;
the aerodynamic performance parameters of the vehicle comprise aerodynamic force, wind speed around the automobile and pressure distribution.
5. The intelligent automobile aerodynamic performance prediction method according to claim 1, wherein in step S3, the data fusion is performed by using a gaussian regression method to fuse the data obtained by simulation and test.
6. The intelligent automobile aerodynamic performance prediction method according to claim 1, wherein the functional relation formula in step S4 is as follows:
Cd＝k*f(Xn,Pn,Vn) Wherein, CdIs the wind resistance coefficient; xn ═ x1,x2,...xn) Geometrically structuring parameters for the automobile model; p ═ P (P)1,p2,...pn) Is the pressure in the flow field; v ═ V (V)1,v2,...vn) Is the velocity in the flow field.
7. The intelligent prediction method for the aerodynamic performance of an automobile according to claim 1, wherein in the intelligent prediction process for the aerodynamic performance parameters in step S4, adaptive spatial transformation is used to scale the known parameters.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210146539.2A CN114547993A (en) | 2022-02-17 | 2022-02-17 | Intelligent prediction method for aerodynamic performance of automobile |
| PCT/CN2022/115981 WO2023155414A1 (en) | 2022-02-17 | 2022-08-30 | Intelligent prediction method for automobile aerodynamic performance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210146539.2A CN114547993A (en) | 2022-02-17 | 2022-02-17 | Intelligent prediction method for aerodynamic performance of automobile |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114547993A true CN114547993A (en) | 2022-05-27 |
Family
ID=81676456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210146539.2A Pending CN114547993A (en) | 2022-02-17 | 2022-02-17 | Intelligent prediction method for aerodynamic performance of automobile |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114547993A (en) |
| WO (1) | WO2023155414A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023155414A1 (en) * | 2022-02-17 | 2023-08-24 | 中汽研（天津）汽车工程研究院有限公司 | Intelligent prediction method for automobile aerodynamic performance |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664721A (en) * | 2018-05-03 | 2018-10-16 | 中南大学 | High-speed train head shape collaborative design method based on multi-subject design |
| CN109455236B (en) * | 2018-10-30 | 2021-02-02 | 重庆理工大学 | Automobile tail wing structure and design method thereof |
| CN110096844B (en) * | 2019-05-22 | 2022-11-22 | 湖北汽车工业学院 | Aerodynamic characteristic optimization design method of non-smooth vehicle surface automobile |
| US20210216688A1 (en) * | 2020-01-13 | 2021-07-15 | Microsoft Technology Licensing, Llc | Configuring aerodynamic simulation of a virtual object |
| CN111597631B (en) * | 2020-05-07 | 2022-05-13 | 中汽研汽车检验中心（天津）有限公司 | Automobile wind resistance coefficient optimization method based on self-adaptive agent model |
| CN113032902B (en) * | 2021-03-18 | 2022-06-17 | 中南大学 | High-speed train pneumatic head shape design method based on machine learning optimization |
| CN113505440B (en) * | 2021-07-28 | 2024-05-14 | 大连理工大学 | Real-time prediction method for aerodynamic performance parameters of automobile based on three-dimensional deep learning |
| CN114547993A (en) * | 2022-02-17 | 2022-05-27 | 中汽研（天津）汽车工程研究院有限公司 | Intelligent prediction method for aerodynamic performance of automobile |
-
2022
- 2022-02-17 CN CN202210146539.2A patent/CN114547993A/en active Pending
- 2022-08-30 WO PCT/CN2022/115981 patent/WO2023155414A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023155414A1 (en) * | 2022-02-17 | 2023-08-24 | 中汽研（天津）汽车工程研究院有限公司 | Intelligent prediction method for automobile aerodynamic performance |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023155414A1 (en) | 2023-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113609596B (en) | Aircraft aerodynamic characteristic prediction method based on neural network | |
| CN110909762B (en) | Robot posture recognition method and device based on multi-sensor fusion | |
| WO2021013190A1 (en) | Meteorological parameter-based high-speed train positioning method and system in navigation blind zone | |
| CN114547993A (en) | Intelligent prediction method for aerodynamic performance of automobile | |
| CN111400811B (en) | Reliability analysis method for mixed uncertainty structure | |
| CN110766222A (en) | Particle swarm parameter optimization and random forest based PM2.5 concentration prediction method | |
| CN112597702B (en) | Pneumatic modeling generation type confrontation network model training method based on radial basis function | |
| CN113987705A (en) | Automobile covering part rebound prediction method based on deep learning | |
| CN111191186B (en) | Multi-cell filtering method for positioning position of mobile robot in production workshop | |
| CN113221278B (en) | Light weight method for vehicle-mounted photoelectric platform calibration frame | |
| CN112749508B (en) | Road feel simulation method based on GMM and BP neural network | |
| CN106227984B (en) | The method and its system of BIM entrance model quick-assembling | |
| CN114474004B (en) | Error compensation planning control strategy for multi-factor coupling vehicle-mounted building robot | |
| CN113139241B (en) | Automatic modeling method for conceptual model of vehicle body structure based on image | |
| CN101950317A (en) | Method for identifying fixed-order parameter model of aircraft based on modal segmentation and genetic algorithm | |
| CN111753414B (en) | Seepage characteristic simulation method for rock progressive destruction process based on non-Darcy law | |
| EP2442279A1 (en) | Evolvable control point grid layouts for the design optimization of physical bodies | |
| CN113591371A (en) | Bridge cluster structure damage positioning method based on space-time correlation model | |
| CN114756980B (en) | Info-GAN-based multi-design space coupling pneumatic shape optimization method and system | |
| CN117349462B (en) | Remote sensing intelligent interpretation sample data set generation method | |
| CN114818139A (en) | Aircraft structural part design method based on convolutional neural network | |
| CN112560311A (en) | Method for quickly and automatically extracting structure information and analyzing and optimizing structure | |
| CN116227062A (en) | Data-driven non-invasive shape-topology collaborative optimization method and system | |
| CN115035066A (en) | Chain deformation measurement method based on deep learning | |
| CN106096108A (en) | The optimization method of semi-mounted truck side wind stability based on agent model |
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 |