logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Transfer learning-guided generative laminate design framework with limited data availability

delete2025-07-11
delete0
PRE
AI
S
Siyuan Chen
Z
Zhixing Li
J
Jinzhao Huang
T
Tiantian Yang
高
高云鹏 (Yunpeng Gao)
胡笳 封面图
胡笳 (Jia Hu)
杨
杨光 (Guang Yang)
果
果立成 (Licheng Guo)
DOI：10.1016/j.compscitech.2025.111292delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
纤维增强复合材料具有显著的定制潜力，但设计参数众多且需探索新的设计空间，给层合板设计带来了巨大挑战。本文提出了一种基于迁移学习的生成式层合板设计框架（TGLDF），用于在数据有限的情况下高效扩展设计空间。TGLDF中的生成器通过数据缩放方法快速生成在设计范围内取值的设计参数，同时结合基于神经网络且经过小数据集微调的判别器，用于预测新设计空间中的力学性能。引入了定制化的生成损失，以使生成结果达成设计目标，如本文中的期望强度和扭转刚度。通过两个不同新设计空间的实例验证了TGLDF的有效性。这些实例包括单向拉伸下的带缺口层合板和承受耦合内压与轴向压缩的复合材料管，涉及新材料、铺层数量及加载条件的变化。结果表明，仅需少量数据即可在新设计空间中执行逆向设计。与有限元仿真及遗传算法（GAs）的对比分析展示了TGLDF的有效性和优越性，其通过整合随机噪声学习最优解分布，性能优于GAs。此外，将独热编码与连续参数拼接，使TGLDF能够便捷地扩展至其他设计场景。

期刊

Composites Science and Technology 封面图
Composites Science and Technology
IF:
9.8
论文数:
863
被引数:
5.0W

机构

暂无机构信息
引用论文

引用论文

Enforcing Imprecise Constraints on Generative Adversarial Networks for Emulating Physical Systems
errCommunications in Computational Physics
IF0
err2021-01-01
err0
errOAAI
errYang Zeng Yang Zeng; Jin-Long Wu Jin-Long Wu; Heng Xiao Heng Xiao
err分享
err收藏
Layup optimisation of laminated composite tubular structures under thermomechanical loading conditions using PSO使用PSO在热机械载荷条件下对层压复合管结构进行铺层优化
errCOMPOSITE STRUCTURES
IF7.1
err2021-11-01
err12
PREAI
errVeivers, Harry; Bermingham, Michael; Dunn, Mitchell; Veidt, Martin
err分享
err收藏
Optimal design of one-dimensional elastic metamaterials through deep convolutional neural network and genetic algorithm
errSTRUCTURES
IF4.3
err2023-11-01
err7
PREAI
errXiao, Li; Cao, Zhigang; Lu, Haoran; Cai, Yuanqiang; Zhang, Zhicheng
err分享
err收藏
Ply-drop design of non-conventional laminated composites using Bayesian optimization
errCOMPOSITES PART A-APPLIED SCIENCE AND MANUFACTURING
IF8.9
err2020-12-01
err12
PREAI
errYamaguchi, Koshiro; Phenisee, Sean E.; Chen, Zhisong; Salviato, Marco; Yang, Jinkyu
err分享
err收藏
A novel experimental approach for high-velocity ice impact resistance and tolerance investigation of composite laminates一种用于复合材料层合板高速冰撞击抗力与容限研究的新型实验方法
errCOMPOSITES SCIENCE AND TECHNOLOGY
IF9.8
err2025-05-01
err0
PREAI
errYu, Shangyang; Huang, Jinzhao; Hu, Jia; Wang, Yan; Ding, Junfeng; Song, Chenyang; Chen, Zhanguang; Yu, Jikai; Guo, Licheng
err分享
err收藏
Transfer learning based multi-fidelity physics informed deep neural network基于迁移学习的多保真物理通知深度神经网络
errJOURNAL OF COMPUTATIONAL PHYSICS
IF3.8
err2021-02-01
err126
errOAAI
errChakraborty, Souvik
err分享
err收藏
Exploring shear nonlinearity of plain-woven composites at various temperatures based on machine learning
errCOMPOSITE STRUCTURES
IF7.1
err2024-10-01
err0
PREAI
errZhou, Jindi; Huang, Kai; Zheng, Tao; Liu, Xiaodong; Han, Xiaojian; Wang, Zhongyu; Liu, Hongsen; Guo, Licheng
err分享
err收藏
A deep learning-based composite design strategy for efficient selection of material and layup sequences from a given database
errComposites Science and Technology
IF0
err2022-11-01
err0
PREAI
errCheng Qiu; Yuzi Han; Logesh Shanmugam; Ying Zhao; Shaotong Dong; Shanyi Du; Jinglei Yang
err分享
err收藏
Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models
errPolymers
IF0
err2022-08-08
err0
errOAAI
errZhenhao Liao; Cheng Qiu; Jun Yang; Jinglei Yang; Lei Yang
err分享
err收藏
Stacking sequence optimization in composite tubes under internal pressure based on genetic algorithm accounting for progressive damage
errCOMPOSITE STRUCTURES
IF7.1
err2017-10-01
err75
PREAI
errAlmeida, Jose Humberto S., Jr.; Ribeiro, Marcelo L.; Tita, Volnei; Amico, Sandro C.
err分享
err收藏
学者 查看更多内容