CN114818139A - Aircraft structural part design method based on convolutional neural network - Google Patents

Aircraft structural part design method based on convolutional neural network Download PDF

Info

Publication number
CN114818139A
CN114818139A CN202210483693.9A CN202210483693A CN114818139A CN 114818139 A CN114818139 A CN 114818139A CN 202210483693 A CN202210483693 A CN 202210483693A CN 114818139 A CN114818139 A CN 114818139A
Authority
CN
China
Prior art keywords
neural network
convolutional neural
structural part
information
aircraft structural
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
Application number
CN202210483693.9A
Other languages
Chinese (zh)
Inventor
郝博
张鹏
王明阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Northeastern University China
Original Assignee
Northeastern University China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Northeastern University China filed Critical Northeastern University China
Priority to CN202210483693.9A priority Critical patent/CN114818139A/en
Publication of CN114818139A publication Critical patent/CN114818139A/en
Pending legal-status Critical Current

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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Graphics (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses an aircraft structural part design method based on a convolutional neural network, which comprises the following steps: (1) a designer collects two-dimensional design drawings of different airplane structural members, inputs characteristic points of the airplane structural members through a man-machine interaction interface, and builds a convolutional neural network model; (2) reasoning analysis is carried out through a rule reasoning machine to obtain relative spatial position information and curve information among the characteristic points in the characteristic information; (3) the CNN convolutional neural network trains the data set, detects key points and establishes a convolutional neural network training library; (4) and processing the characteristic information, automatically detecting important parts in the nodes, establishing a parameterized three-dimensional model, and storing the example in a knowledge-model library in real time. The invention fully combines the convolutional neural network with the design of the aircraft structural part, and can quickly establish the three-dimensional parameterized model of the aircraft structural part by the two-dimensional design drawing, thereby shortening the design period and the research and development period of the aircraft structural part.

Description

Aircraft structural part design method based on convolutional neural network
Technical Field
The invention relates to the technical field of airplane design, in particular to an airplane structural part design method based on a convolutional neural network.
Background
With the rapid development of advanced manufacturing technology of airplanes, higher requirements are put on the design and manufacture of airplane structural parts. In order to improve the design efficiency of the aircraft and save the economic cost, the united states firstly adopts the digitization technology in the field of aircraft structural part design, and simultaneously modifies and optimizes the design process of the traditional aircraft structural part through the digitization technology. The aircraft structural part is gradually developing towards the integration and large-scale development of the part structure, the complexity degree is higher and higher, the problems of low design efficiency, complex design and modeling process, low knowledge utilization rate and the like exist in the field of aircraft structural part design, and the problems also become important obstacles on realizing the intelligent manufacturing road of the aircraft large-scale structural part.
Patent publications and literature data at the present stage show: 1) the patent (CN201911335707.7) is based on the automatic construction method of the aircraft structural part web processing area of image, and the method is suitable for the aircraft structural part web processing area which contains various complex elements such as broken faces, broken edges, opening and closing angles, clamping bosses and the like in a structural part model, but various types of structures of the aircraft structural part are not realized, and the requirements of various types and diversified designs of the current aircraft structural part cannot be met. 2) According to the system and the method for automatically acquiring the characteristic points of the aircraft structural part, the characteristic points can be automatically acquired after the system and the method are arranged at the reference positions, so that the problem that the errors of the traditional workers in acquiring the characteristic points are large is solved, but the method is only suitable for acquiring the characteristic points, the application range is narrow, and the knowledge utilization rate of the aircraft structural part design is low.
In summary, although the existing research results and methods can realize the intelligent design of the complex aircraft structural member to a certain extent, the problems of high fault tolerance rate and limited design method exist, the aircraft structural member has various types and complex structures, the existing methods have low utilization rate of design knowledge and low design efficiency, and the requirements of high efficiency, high design quality and parametric design in the field of aircraft structural member design in China at present cannot be met.
Disclosure of Invention
The invention aims to solve the technical problems of low utilization rate and low design efficiency of airplane structural part design knowledge based on designers or systems, and provides an airplane structural part design method based on a convolutional neural network.
The invention realizes the purpose through the following technical scheme: a design method of an airplane structural part based on a convolutional neural network is divided into four parts, namely a knowledge acquisition and construction module, a rule-based reasoning and characteristic information integration module, a convolutional neural network model training module and a three-dimensional model building and storing system module, and specifically comprises the following steps:
(1) knowledge acquisition and construction module
The knowledge acquisition and construction module is used for collecting a large number of two-dimensional design drawings of different airplane structural members, designers input characteristic points of the airplane structural members through a man-machine interaction interface and describe characteristic parameters of the airplane structural members to build a convolutional neural network model.
(2) Rule-based reasoning and feature information integration module
The rule-based reasoning and characteristic information integration module carries out reasoning analysis through a rule reasoning machine to obtain relative spatial position information and curve information among characteristic points in the characteristic information.
(3) Convolutional neural network model training module
The convolutional neural network model training module is used for screening and training relative spatial position information and curve information of feature points serving as a data set through a CNN convolutional neural network algorithm, detecting key points, realizing feature information refinement and representativeness of aircraft structural members, and connecting multi-level feature information to enable the convolutional network to have the mapping capacity between input and output pairs, so that a training library of the convolutional neural network model is established.
(4) Three-dimensional model building and storage system module
The three-dimensional model building and storing system module processes characteristic information in a training library of the convolutional neural network model, detects important parts in nodes through OpenCV, processes information modules of the nodes, curves, construction elements and size elements, builds a parameterized three-dimensional model, completes design of an airplane structural part, stores the instance in a knowledge-model library in real time, and continuously updates the knowledge-model library.
Further, the two-dimensional design drawing of the typical aircraft structural part in the knowledge acquisition and construction module comprises a front view, a top view, a directional view and a partial view of the aircraft structural part.
Further, the principle of establishing the feature points in the knowledge acquisition and construction module should include: 1) the selection of the characteristic points can be parameterized and designed each time; 2) the selection of the characteristic points can preliminarily determine the type of a certain airplane structural part.
Further, the relative spatial position information in the rule-based reasoning and feature information integration module is coordinate values under a spatial rectangular coordinate system of x, y and z.
Further, the rule reasoning and characteristic information integration module based on the rule reasoning comprises the related domain knowledge of the structural part characteristics of the airplane, has an IF (condition) THEN (behavior) structure, and triggers the rule when the condition of the rule is met, and THEN executes the behavior.
Further, the rule-based reasoning and feature information integration in the feature information integration module refers to obtaining feature parameters through rule base reasoning based on structural member design requirements, then analyzing the spatial position information and curve information of feature points, primarily determining the feature parameters of the structural member, and finally optimizing and determining a final parameter scheme of the structural member through manual evaluation.
Further, at least three feature points need to be reserved in the relative spatial position information and the curve information in the convolutional neural network model training module.
Further, the characteristic information refinement in the convolutional neural network model training module is realized through a pooling layer in a CNN convolutional network structure, namely, the characteristic information is more, some information has no too much use or repetition for building a three-dimensional model, the pooling layer collects characteristics, and then the characteristics of an image frequency domain are extracted through Fourier transform for sparse processing, so that redundant information is removed, and the most important characteristics are extracted.
Further, the parameterized model in the three-dimensional model establishing and storing system module is used for completing parameter optimization of the aircraft structural part based on CATIA CAA in a man-machine interaction system by utilizing space relative position constraint between nodes and characteristic information of the aircraft structural part to form the three-dimensional model.
Compared with the prior art, the invention has the following beneficial effects:
the aircraft structural part design method based on the convolutional neural network can quickly establish the three-dimensional parameterized model of the aircraft structural part through the two-dimensional design drawing, improves the utilization rate of the design knowledge of the aircraft structural part, improves the design efficiency, and shortens the design period and the research and development period of the aircraft structural part.
Drawings
FIG. 1 is a flow chart of the operation of the present invention;
FIG. 2 is a schematic diagram of a human-computer interaction system of the present invention;
FIG. 3 is a feature information integration flow diagram of the present invention;
FIG. 4 is a schematic diagram of a rule base for rule inference in the present invention;
fig. 5 is a schematic diagram of feature information integration of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.
The invention provides an aircraft structural part design method based on a convolutional neural network, which comprises the following steps:
(1) the knowledge acquisition and construction are to collect a large number of two-dimensional design drawings of different airplane structural members, wherein the two-dimensional design drawings comprise a main view, a top view, an orientation view and a local view of the airplane structural members, then designers input feature points of the airplane structural members through a human-computer interaction interface, feature parameters of the airplane structural members are described to build a convolutional neural network model, and a human-computer interaction system is shown in fig. 2.
(2) The rule-based reasoning and feature information integration is to perform reasoning analysis through a rule reasoning machine, the rule reasoning machine has an IF (condition) THEN (behavior) structure, when the condition of the rule is met, the rule is triggered, THEN the behavior is executed, and further the relative spatial position information and curve information between feature points in the feature information are obtained, and a rule base is shown in FIG. 4.
(3) The convolutional neural network model training is to take the relative spatial position information and curve information of feature points as a data set, screen and train through a CNN convolutional network structure, detect key points, realize the feature information refinement and the representativeness of aircraft structural members, connect multi-level feature information, enable the convolutional network to have the mapping capacity between input and output pairs, and further establish a training library of the convolutional neural network model, wherein the feature information integration step is shown in figure 3.
(4) The three-dimensional model establishing and storing system is characterized in that feature information in a training library of a convolutional neural network model is processed, important parts in nodes are detected through OpenCV, information modules of the nodes, curves, construction elements and size elements are processed, parameter optimization of an aircraft structural part is completed based on CATIA CAA in a man-machine interaction system by utilizing space relative position constraint among the nodes and feature information of the aircraft structural part, a parameterized three-dimensional model is established, design of the aircraft structural part is completed, the instance is stored in a knowledge-model library in real time, and the knowledge-model library is continuously updated.
In conclusion, the convolutional neural network and the aircraft structural part are combined together for product design, the two-dimensional drawing is converted into the three-dimensional parametric modeling model, the design efficiency is greatly improved, the utilization rate of design knowledge is remarkably improved, and the development period of the aircraft structural part can be shortened.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, those skilled in the art can make modifications and equivalents to the specific embodiments of the present invention without departing from the spirit and scope of the present invention, which is set forth in the claims of the present application.

Claims (9)

1. A method for designing an aircraft structural part based on a convolutional neural network is characterized by comprising the following steps: the method comprises the following steps:
(1) the knowledge acquisition and construction module is used for collecting a large number of two-dimensional design drawings of different airplane structural members, and a designer inputs characteristic points of the airplane structural members through a man-machine interaction interface and describes characteristic parameters of the airplane structural members to construct a convolutional neural network model;
(2) the rule-based reasoning and characteristic information integration module carries out reasoning analysis through a rule reasoning machine to obtain relative spatial position information and curve information between characteristic points in the characteristic information;
(3) the convolutional neural network model training module is used for screening and training relative spatial position information and curve information of feature points serving as a data set through a CNN convolutional neural network algorithm, detecting key points, realizing feature information refinement and representativeness of an airplane structural part, and connecting multi-layer feature information to enable the convolutional network to have the mapping capacity between input and output pairs, so that a training library of the convolutional neural network model is established;
(4) the three-dimensional model building and storage system module processes characteristic information in a training library of a convolutional neural network model, detects important parts in nodes through OpenCV, processes information modules of the nodes, curves, construction elements and size elements, builds a parameterized three-dimensional model, completes design of an airplane structural part, stores the instance in a knowledge-model library in real time, and continuously updates the knowledge-model library.
2. The method for designing the aircraft structural part based on the convolutional neural network as claimed in claim 1, wherein: the two-dimensional design drawing of the typical aircraft structural part in the knowledge acquisition and construction module comprises a front view, a top view, a directional view and a partial view of the aircraft structural part.
3. The method for designing the aircraft structural part based on the convolutional neural network as claimed in claim 1, wherein: the principle of establishing the feature points in the knowledge acquisition and construction module includes:
1) the selection of the characteristic points can be parameterized and designed each time;
2) the selection of the characteristic points can preliminarily determine the type of a certain airplane structural part.
4. The method for designing the aircraft structural part based on the convolutional neural network as claimed in claim 1, wherein: and the relative spatial position information in the rule-based reasoning and characteristic information integration module is coordinate values under a spatial rectangular coordinate system of x, y and z.
5. The method for designing the aircraft structural part based on the convolutional neural network as claimed in claim 1, wherein: the rule reasoning in the rule-based reasoning and characteristic information integration module comprises the related domain knowledge of the structural part characteristics of the airplane, has an IF (condition) THEN (behavior) structure, and triggers the rule when the condition of the rule is met, and THEN executes the behavior.
6. The method for designing an aircraft structural member based on a convolutional neural network as claimed in claim 1, wherein: the rule-based reasoning and characteristic information integration in the characteristic information integration module refers to obtaining characteristic parameters through rule base reasoning based on structural part design requirements, then analyzing the spatial position information and curve information of characteristic points, preliminarily determining the characteristic parameters of the structural part, and finally optimizing and determining the final parameter scheme of the structural part through manual evaluation.
7. The method for designing an aircraft structural member based on a convolutional neural network as claimed in claim 1, wherein: at least three feature points need to be reserved in the relative space position information and the curve information in the convolutional neural network model training module.
8. The method for designing an aircraft structural member based on a convolutional neural network as claimed in claim 1, wherein: the characteristic information refinement in the convolutional neural network model training module is realized through a pooling layer in a CNN convolutional network structure, namely, the characteristic information is more, some information has no too much use or repetition for building a three-dimensional model, the pooling layer collects characteristics, and then the characteristics of an image frequency domain are extracted through Fourier transform for sparse processing, so that redundant information is removed, and the most important characteristics are extracted.
9. The method for designing the aircraft structural part based on the convolutional neural network as claimed in claim 1, wherein: the parameterized model in the three-dimensional model establishing and storing system module is used for completing parameter optimization of the aircraft structural part based on CATIA CAA in a man-machine interaction system by utilizing space relative position constraint between nodes and characteristic information of the aircraft structural part to form a three-dimensional model.
CN202210483693.9A 2022-05-05 2022-05-05 Aircraft structural part design method based on convolutional neural network Pending CN114818139A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210483693.9A CN114818139A (en) 2022-05-05 2022-05-05 Aircraft structural part design method based on convolutional neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210483693.9A CN114818139A (en) 2022-05-05 2022-05-05 Aircraft structural part design method based on convolutional neural network

Publications (1)

Publication Number Publication Date
CN114818139A true CN114818139A (en) 2022-07-29

Family

ID=82512073

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210483693.9A Pending CN114818139A (en) 2022-05-05 2022-05-05 Aircraft structural part design method based on convolutional neural network

Country Status (1)

Country Link
CN (1) CN114818139A (en)

Similar Documents

Publication Publication Date Title
CN109446992B (en) Remote sensing image building extraction method and system based on deep learning, storage medium and electronic equipment
CN109299401B (en) Metropolitan area space-time flow prediction method based on mixed deep learning model LSTM-ResNet
CN110703057B (en) Power equipment partial discharge diagnosis method based on data enhancement and neural network
CN111489358A (en) Three-dimensional point cloud semantic segmentation method based on deep learning
WO2015096511A1 (en) Intelligent numerical control machining programming system and method for aircraft structural parts
CN114802296A (en) Vehicle track prediction method based on dynamic interaction graph convolution
CN108734337B (en) Customized bus station generation method based on cluster center correction
CN111091101B (en) High-precision pedestrian detection method, system and device based on one-step method
CN115019510B (en) Traffic data restoration method based on dynamic self-adaptive generation countermeasure network
CN112329973A (en) Space-time load prediction method based on graph neural network and regional gridding
CN110378047A (en) A kind of Longspan Bridge topology ambiguity three-dimensional rebuilding method based on computer vision
CN113642236A (en) Multidisciplinary-oriented digital twin graph network modeling method
CN117217020A (en) Industrial model construction method and system based on digital twin
CN109389170B (en) Gradual change type working condition early warning method based on 3D convolutional neural network
CN114818139A (en) Aircraft structural part design method based on convolutional neural network
CN117557726A (en) Three-dimensional visualization-based power distribution network point cloud model construction system
CN112257202A (en) Neural network-based two-dimensional structure grid automatic decomposition method for multi-inner-hole part
CN110309528A (en) A kind of radar Design Method based on machine learning
CN116976057A (en) Automatic arrangement method for device layout
CN115239779A (en) Three-dimensional point cloud registration method, device, medium and electronic equipment
Xu An intelligent fault detection approach for digital integrated circuits through graph neural networks
CN117911662B (en) Digital twin scene semantic segmentation method and system based on depth hough voting
CN117851778B (en) Apparent recognition method and system based on bridge exposure degree
CN117953164B (en) Method and system for improving drawing measurement quality
CN112330804B (en) Local deformable three-dimensional model contact detection method

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