Rapid structure design method based on carbon fiber composite database

Abstract

The invention provides a rapid structure design method based on a carbon fiber composite material database, which comprises the following steps: disassembling an imported composite material structure model into a basic joint structure and a basic connection structure through an image recognition technology, matching the basic joint structure and the basic connection structure with a composite material basic structure database to obtain composition information of the composite material structure model, the method comprises the following steps: manually inputting a user demand, calling a composite material layering performance library by a system, and matching material performance and a layering structure to a basic joint structure and a basic connection structure of a composite material structure model; and by taking the model structure composition information, the material performance and the layering structure parameters as input ends of machine learning, and taking the user demand as an index of machine learning, a composite material type and a layering structure which meet the user demand are optimized through a machine learning method. According to the method, image recognition, a database and machine learning are integrated, the design process can be simplified, and the design threshold is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of carbon fiber composite material structure design, and in particular to a rapid structure design method based on a carbon fiber composite material database. Background Art

[0002] With the growing demand for high-performance, lightweight materials in the aerospace, automotive, sports equipment and energy sectors, carbon fiber composites (CFRP) have become key materials in these fields due to their excellent specific strength, specific modulus, good corrosion resistance and fatigue resistance. However, the structural design process of carbon fiber composites is complex and time-consuming, involving multiple links such as material selection, layer design, mechanical analysis, etc., and requires highly specialized knowledge and experience.

[0003] The structural design of carbon fiber composite materials is flexible. Different material selection and layer structure often lead to different overall performance. This is a major feature that distinguishes composite materials from metal materials. Composite materials that meet special needs can be freely combined and designed. However, due to the flexibility of material selection and layer structure, slight changes in these parameters may have a significant impact on the overall performance of the structure. Therefore, in the process of structural design, it is necessary to fully and accurately grasp the performance data of various carbon fiber composite materials in order to make reasonable choices. However, the database of performance parameters of carbon fiber composite materials on the market is difficult to meet actual design needs, and mechanical performance tests are often required to provide data for structural design.

[0004] Traditional carbon fiber composite material structural design methods often rely on engineers' experience and a large number of trial and error experiments, which not only increases design costs and time, but also makes it difficult to ensure the optimality of the design results. In addition, with the increasing number of carbon fiber composite materials and the increasing diversification of application scenarios, how to quickly and accurately complete structural design to meet the performance requirements under different working conditions has become an urgent problem to be solved.

[0005] In summary, in the field of carbon fiber composite material structure design, the existing technology mainly has the following shortcomings: 1. Traditional designs often lack a carbon fiber composite material database, which requires references or mechanical property tests during the design process.

[0006] 2. Existing structural optimization methods often require manual calculations, and the optimization software used often has a certain usage threshold, and there are problems such as low calculation efficiency, unsatisfactory optimization effects, and non-reusability.

[0007] 3. The traditional design process is cumbersome and often requires cooperation among multiple parties, which is not conducive to quickly responding to market demand Summary of the invention

[0008] In order to solve the technical problems existing in the above-mentioned background technology, the present invention proposes a rapid structural design method based on a carbon fiber composite material database, aiming to provide an efficient and accurate solution for carbon fiber composite material structure design through a comprehensive database, machine learning algorithm and convenient design process.

[0009] Specifically, the present invention provides a rapid structural design method based on a carbon fiber composite material database, comprising the following steps: S1: disassemble the imported composite material structure model into a basic joint structure and a basic connection structure by using image recognition technology, match the disassembled basic joint structure and basic connection structure with a composite material basic structure library, and obtain the composition information of the composite material structure model; S2: By manually inputting user requirements, the system calls the composite material ply performance library and matches the material properties and ply structure to the basic joint structure and basic connection structure of the composite material structure model; S3: The model structure composition information obtained in step S1 and the material properties and layer structure parameters obtained in step 2 are used as the input of machine learning, and the user needs are used as the indicators of machine learning. Through the machine learning method, the composite material type and layer structure that meet the user needs are selected.

[0010] As a further illustration of the present invention, in step S1, the imported composite material structure model is disassembled into a basic joint structure and a basic connection structure by using image recognition technology, specifically including: Write 3D models of composite materials based on external imports; Perform image recognition on the imported 3D model and automatically split it into basic joint structure and basic connection structure.

[0011] As a further illustration of the present invention, the composite material basic structure library includes: a basic joint structure and a basic connection structure; wherein the basic joint structure includes a three-way joint type, a four-way joint type, a five-way joint type, and a six-way joint type, and each type of joint includes a branch joint in addition to a main joint; the basic connection structure includes connecting pipes of different specifications and sizes.

[0012] As a further explanation of the present invention, in step S2, the user requirements include: performance requirements, cost requirements and weight requirements of the structure; the user fills in one or more according to actual needs.

[0013] As a further illustration of the present invention, the composite material ply performance library includes basic mechanical performance parameters of different types of carbon fiber composite materials and ply structure parameters of basic structures.

[0014] As a further illustration of the present invention, the basic mechanical performance parameters include density, strength, modulus, and Poisson's ratio parameters; the ply structure parameters include single layer thickness, number of plies and ply sequence, as well as the strength, price, and weight corresponding to the structure.

[0015] As a further explanation of the present invention, in step S3, during the machine learning process, a machine learning model is used to automatically select material types and layup structure solutions that meet the requirements through model training. The model includes material type, layup structure type, structural strength, price, and weight. The model uses a combination of finite element and experimental methods in training, and ultimately obtains the best matching solution of material type-layup structure-strength-price-weight.

[0016] Compared with the prior art, the present invention has the following beneficial technical effects: 1. The existing composite material structure design has a long design cycle, and the time cost spent in multiple links such as finite element modeling calculation, mechanical property testing, and sample trial production is relatively high. The present invention can quickly design a structural design solution that meets the needs, reduce process design costs, and improve efficiency.

[0017] 2. The existing composite material structure design models have low universality. The present invention adopts a composite material basic structure database and a composite material ply performance library containing various specifications and sizes. The model has high universality and can be reused, which can reduce design time and improve production efficiency.

[0018] 3. In the existing composite material structure design process, it is often necessary to use a variety of modeling software, finite element software and optimization algorithms. The process is often complicated and the solutions are different. The present invention integrates image recognition, database and machine learning into one, which can simplify the design process and lower the design threshold.

[0019] Other features and advantages of the technical solution will be described in the subsequent description, and partly become apparent from the description, or understood by implementing the technical solution. The purpose and other advantages of the technical solution can be achieved and obtained through the structures specifically pointed out in the written description and the drawings.

[0020] The technical solution of the present technical solution is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the technical solution and constitute a part of the specification. Together with the embodiments of the technical solution, they are used to explain the technical solution and do not constitute a limitation of the technical solution. In the accompanying drawings: Figure 1 It is a schematic diagram of disassembling a structural model by using image recognition technology in an embodiment of the present invention.

[0022] Figure 2 The figure is a flow chart of a rapid structural design method based on a carbon fiber composite material database in an embodiment of the present invention.

[0023] Figure 3 It is the optimal result of the material type and ply structure that meet the indicators output by the machine learning model in the embodiment of the present invention. DETAILED DESCRIPTION

[0024] The preferred embodiments of the present technical solution are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present technical solution, and are not used to limit the present technical solution.

[0025] like Figure 2 As shown, an embodiment of the present invention provides a rapid structural design method based on a carbon fiber composite material database, comprising the following steps: S1: The imported composite material structure model is disassembled into a basic joint structure and a basic connection structure through image recognition technology, and the disassembled basic joint structure and basic connection structure are matched with the composite material basic structure library to obtain the composition information of the composite material structure model.

[0026] Specifically, the above-mentioned image recognition process includes: writing a three-dimensional model of a composite material based on external import; performing image recognition on the imported three-dimensional model, and automatically splitting it into a basic joint structure and a basic connection structure.

[0027] Among them, the composite material basic structure library includes: basic joint structure and basic connection structure; among them, the basic joint structure includes three-way joints, four-way joints, five-way joints, and six-way joints. Each type of joint includes branch joints in addition to the main joint; the basic connection structure includes connecting pipes of different specifications and sizes.

[0028] like Figure 1 As shown, for example, after importing a three-dimensional model of a composite material, the three-dimensional model can be split into 4 three-way two-branch joints, 4 three-way zero-branch joints, 12 connecting pipes 01, and 4 connecting pipes 02 through image recognition technology, and then matched with the joints and connection structures in the composite material basic structure library to obtain the composition information of the composite material structure model.

[0029] S2: By manually inputting user requirements, the system calls the composite material ply performance library and matches the material properties and ply structure to the basic joint structure and basic connection structure of the composite material structure model.

[0030] Among them, user requirements include: structural performance requirements, cost requirements and weight requirements, performance requirements include strength requirements; users fill in one or more according to actual needs. When entering requirements, users can enter requirements as follows: performance requirements: strength not less than 30MPa, price requirements: price not more than 300 yuan; weight requirements: weight not more than 1Kg.

[0031] The composite material ply performance library contains the basic mechanical performance parameters of different types of carbon fiber composite materials and the ply structure parameters of the basic structure. The basic mechanical performance parameters include density, strength, modulus, and Poisson's ratio parameters; the ply structure parameters include single layer thickness, number of plies and ply sequence, as well as the strength, price, and weight of the structure.

[0032] S3: Use the model structure composition information obtained in step S1 and the material properties and layer structure parameters obtained in step 2 as the input of machine learning, use user needs as the indicator of machine learning, and use machine learning methods to select the composite material type and layer structure that meet user needs.

[0033] During the machine learning process, a machine learning model is used to automatically select material types and layup structure solutions that meet the requirements through model training. The model includes material type, layup structure type, structural strength, price, and weight. The model uses a combination of finite element and experimental methods in training, and ultimately obtains the best matching solution of material type-layup structure-strength-price-weight.

[0034] The machine learning model can output a combination of material types and layup results that meet the indicators, and select the optimal material type-layup structure-strength-price-weight combination based on the lowest price, such as Figure 3 As shown in Table 1, it is the optimal result of each component structure of the composite material.

[0035] Table 1 Optimal results of each component structure of the composite material

[0036] In summary, the present invention first uses image recognition technology to perform image recognition on the imported three-dimensional model and split it into a basic joint structure and a basic connection structure. Then, a method combining computer simulation and experimental data is used to train a machine learning model that automatically selects material types and layer structure schemes that meet the requirements. Finally, image recognition is performed using the input performance requirements to split the complex structure into a basic structure. Combined with the database and using a machine learning algorithm, a structural design scheme that meets user needs is selected.

[0037] Obviously, those skilled in the art can make various changes and modifications to the technical solution without departing from the spirit and scope of the technical solution. Thus, if these modifications and variations of the technical solution fall within the scope of the claims of the technical solution and their equivalents, the technical solution is also intended to include these modifications and variations.

Claims

1. A rapid structural design method based on a carbon fiber composite material database, characterized in that: The steps include: S1: disassemble the imported composite material structure model into a basic joint structure and a basic connection structure by using image recognition technology, match the disassembled basic joint structure and basic connection structure with a composite material basic structure library, and obtain the composition information of the composite material structure model; S2: By manually inputting user requirements, the system calls the composite material ply performance library and matches the material properties and ply structure to the basic joint structure and basic connection structure of the composite material structure model; S3: The model structure composition information obtained in step S1 and the material properties and layer structure parameters obtained in step 2 are used as the input of machine learning, and the user needs are used as the indicators of machine learning. Through the machine learning method, the composite material type and layer structure that meet the user needs are selected.

2. The rapid structural design method based on carbon fiber composite material database according to claim 1, characterized in that: In step S1, the imported composite material structure model is disassembled into a basic joint structure and a basic connection structure by using image recognition technology, specifically including: Write 3D models of composite materials based on external imports; Perform image recognition on the imported 3D model and automatically split it into basic joint structure and basic connection structure.

3. The rapid structural design method based on carbon fiber composite material database according to claim 1, characterized in that: The composite material basic structure library includes: basic joint structures and basic connection structures; wherein the basic joint structures include three-way joints, four-way joints, five-way joints, and six-way joints, and each type of joint includes branch joints in addition to the main joint; the basic connection structure includes connection pipes of different specifications and sizes.

4. The rapid structural design method based on carbon fiber composite material database according to claim 1, characterized in that: In step S2, the user requirements include: structural performance requirements, cost requirements and weight requirements; the user fills in one or more according to actual needs.

5. The rapid structural design method based on carbon fiber composite material database according to claim 1, characterized in that: The composite material ply performance library includes basic mechanical performance parameters of different types of carbon fiber composite materials and ply structure parameters of basic structures.

6. The rapid structural design method based on carbon fiber composite material database according to claim 5, characterized in that: The basic mechanical performance parameters include density, strength, modulus, and Poisson's ratio parameters; the ply structure parameters include single layer thickness, number of plies and ply sequence, as well as the strength, price, and weight corresponding to the structure.

7. The rapid structural design method based on carbon fiber composite material database according to claim 1, characterized in that: In step S3, during the machine learning process, a machine learning model is used to automatically select the material type and layup structure solution that meet the requirements through model training. The model includes material type, layup structure type, structural strength, price, and weight. The model uses a combination of finite element and experimental methods in training, and ultimately obtains the best matching solution of material type-layup structure-strength-price-weight.

Images