A data-driven approach to identify the optimal sub-laminates for homogeneity design under the concept of double-double composites

IF 8.1 2区材料科学 Q1 ENGINEERING, MANUFACTURING

Composites Part A: Applied Science and Manufacturing Pub Date : 2025-04-11 DOI:10.1016/j.compositesa.2025.108897

Cheng Qiu , Hongwei Song , Jinglei Yang

{"title":"A data-driven approach to identify the optimal sub-laminates for homogeneity design under the concept of double-double composites","authors":"Cheng Qiu , Hongwei Song , Jinglei Yang","doi":"10.1016/j.compositesa.2025.108897","DOIUrl":null,"url":null,"abstract":"<div><div>This paper presents the design of the sub-laminate under the concept of the double-double composite using the data-driven method. As the key advantage of the double-double composites is the reduced repeat number of sub-laminates necessary to achieve homogeneity, it is therefore crucial to determine the best pattern of sub-laminates which ensures the optimal lightweight design with the minimum thickness. In the data-driven framework, first, a generative neural network model was built for generating the sub-laminates fitting in the scope of the homogeneous criterion. Then, a symbolic regression model was built for quantitatively finding the hidden layup patterns in the dataset of these sub-laminates. It is found that the form of double-double and triple-double stands out in the vast design space of all the possible layup sequences. The 4-layer sub-laminate of <span><math><mrow><mo>[</mo><mi>θ</mi><mo>/</mo><mo>−</mo><mi>β</mi><mo>/</mo><mi>β</mi><mo>/</mo><mo>−</mo><mi>θ</mi><mo>]</mo></mrow></math></span> and 6-layer sub-laminate of <span><math><mrow><mo>[</mo><mi>θ</mi><mo>/</mo><mo>−</mo><mi>β</mi><mo>/</mo><mo>−</mo><mi>γ</mi><mo>/</mo><mo>+</mo><mi>γ</mi><mo>/</mo><mo>+</mo><mi>β</mi><mo>/</mo><mo>−</mo><mi>θ</mi><mo>]</mo></mrow></math></span> are most recommended as they meet the homogeneous criterion with less thickness and offer larger design space of mechanical properties. The established data-driven framework can be extended to other scenarios especially in finding the common design rules of laminates.</div></div>","PeriodicalId":282,"journal":{"name":"Composites Part A: Applied Science and Manufacturing","volume":"195 ","pages":"Article 108897"},"PeriodicalIF":8.1000,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Composites Part A: Applied Science and Manufacturing","FirstCategoryId":"1","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1359835X25001915","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MANUFACTURING","Score":null,"Total":0}

引用次数: 0

Abstract

This paper presents the design of the sub-laminate under the concept of the double-double composite using the data-driven method. As the key advantage of the double-double composites is the reduced repeat number of sub-laminates necessary to achieve homogeneity, it is therefore crucial to determine the best pattern of sub-laminates which ensures the optimal lightweight design with the minimum thickness. In the data-driven framework, first, a generative neural network model was built for generating the sub-laminates fitting in the scope of the homogeneous criterion. Then, a symbolic regression model was built for quantitatively finding the hidden layup patterns in the dataset of these sub-laminates. It is found that the form of double-double and triple-double stands out in the vast design space of all the possible layup sequences. The 4-layer sub-laminate of

[θ / - β / β / - θ]

and 6-layer sub-laminate of

[θ / - β / - γ / + γ / + β / - θ]

are most recommended as they meet the homogeneous criterion with less thickness and offer larger design space of mechanical properties. The established data-driven framework can be extended to other scenarios especially in finding the common design rules of laminates.

Abstract Image

查看原文本刊更多论文

基于数据驱动的双双复合材料均匀性设计最佳子层压板识别方法

本文采用数据驱动的方法，在双双复合材料的概念下设计了亚层压板。由于双双复合材料的主要优势是减少了实现均匀性所需的次层压板的重复数量，因此确定最佳的次层压板模式是至关重要的，从而确保以最小的厚度实现最佳的轻量化设计。在数据驱动框架下，首先建立了生成式神经网络模型，生成在齐次准则范围内拟合的子层压板；然后，建立符号回归模型，定量地发现这些子层叠数据集中隐藏的层叠模式。研究发现，在所有可能的上篮序列的广阔设计空间中，双双和三双的形式显得尤为突出。推荐采用4层[θ/−β/β/−θ]和6层[θ/−β/−γ/+γ/+β/−θ]的亚层压板，因为它们满足均匀性要求，厚度小，力学性能设计空间大。所建立的数据驱动框架可以扩展到其他场景，特别是在寻找层合板的通用设计规则方面。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Composites Part A: Applied Science and Manufacturing 工程技术-材料科学：复合

CiteScore

15.20

自引率

5.70%

发文量

492

审稿时长

30 days

期刊介绍： Composites Part A: Applied Science and Manufacturing is a comprehensive journal that publishes original research papers, review articles, case studies, short communications, and letters covering various aspects of composite materials science and technology. This includes fibrous and particulate reinforcements in polymeric, metallic, and ceramic matrices, as well as 'natural' composites like wood and biological materials. The journal addresses topics such as properties, design, and manufacture of reinforcing fibers and particles, novel architectures and concepts, multifunctional composites, advancements in fabrication and processing, manufacturing science, process modeling, experimental mechanics, microstructural characterization, interfaces, prediction and measurement of mechanical, physical, and chemical behavior, and performance in service. Additionally, articles on economic and commercial aspects, design, and case studies are welcomed. All submissions undergo rigorous peer review to ensure they contribute significantly and innovatively, maintaining high standards for content and presentation. The editorial team aims to expedite the review process for prompt publication.