基于深度神经网络的四折痕锥形折纸结构设计

doi:10.3901/JME.2023.21.167

机械工程学报 ›› 2023, Vol. 59 ›› Issue (21): 167-176.doi: 10.3901/JME.2023.21.167

扫码分享

基于深度神经网络的四折痕锥形折纸结构设计

陆晨浩^1,2, 陈耀^1,2, 何若琪¹, 范维莹¹, 冯健^1,2

1. 东南大学混凝土及预应力混凝土结构教育部重点实验室南京 211189;
2. 东南大学国家预应力工程技术研究中心南京 211189

收稿日期:2022-12-22 修回日期:2023-04-04 出版日期:2023-11-05 发布日期:2024-01-15
通讯作者: 陈耀(通信作者)，男，1986年出生，博士，教授，博士研究生导师。主要研究方向为新型可展结构、高效计算分析方法、复杂结构设计与分析等。E-mail：chenyao@seu.edu.cn
作者简介:陆晨浩，男，1995年出生，博士研究生。主要研究方向为新型可展结构、结构数字化设计等。E-mail：chenhao_lu@seu.edu.cn；何若琪，男，2000年出生，博士研究生。主要研究方向为折纸、剪纸结构等。E-mail：434849181@qq.com；范维莹，女，1996年出生，硕士。主要研究方向为机器学习在土木工程结构、新型可展结构中的应用。E-mail：17801000603@163.com；冯健，男，1963年出生，博士，教授，博士研究生导师。主要研究方向为预应力结构基本理论和设计方法、预制装配结构设计方法、结构抗连续倒塌、复杂结构分析与试验等。E-mail：fengjian@seu.edu.cn
基金资助:
国家自然科学基金资助项目(51978150,52050410334)。

Developing Four-fold Conical Origami Structures Using Deep Neural Network

LU Chenhao^1,2, CHEN Yao^1,2, HE Ruoqi¹, FAN Weiying¹, FENG Jian^1,2

1. Key Laboratory of Concrete and Prestressed Concrete Structures of Ministry of Education, Southeast University, Nanjing 211189;
2. National Prestress Engineering Research Center, Southeast University, Nanjing 211189

Received:2022-12-22 Revised:2023-04-04 Online:2023-11-05 Published:2024-01-15

摘要/Abstract

摘要： 锥形折纸结构不仅具有高强轻质、形态可变、刚度可控等特点，而且有效改善了传统薄壁折纸结构面外刚度薄弱问题，在伸展臂、可展天线、吸能耗能构件等领域具备良好的应用前景。然而，目前锥形折纸设计难以从工程需求出发、实现特定几何尺寸的结构设计。因此，通过解析几何，推导折痕参数间的关系，并基于深度神经网络(DNN)，将折痕参数与几何参数进行拟合，构建一种四折痕锥形折纸结构的逆向设计方法，实现从三维结构到二维折痕图的逆向设计。计算分析表明，所设计的锥形结构与解析解吻合良好。此外，折纸实物模型不仅验证了所设计结构的可平折性，还利用搭接、镜像等操作丰富了结构的外立面。该设计方法适用于更广义的锥形结构设计，可为基于数据驱动的折纸结构创新发挥积极作用。

关键词: 四折痕, 折纸结构, 深度神经网络, 参数化设计, 逆向设计

Abstract: A conical origami structure generally has the characteristics of high strength, light weight, transformable configuration, and tunable stiffness. Furthermore, it significantly improves the weak out-of-plane stiffness of traditional and thin-walled origami structures, and thus has bright application prospects for extendable arms, deployable antennas, and energy-absorbing components. However, the current design of conical origami cannot fully consider engineering needs, or develop complex origami structures with specific geometries. Therefore, this work deduces the relationship between the four-fold creases through analytic geometry. Subsequently, based on the deep neural network, the origami creases are predicted and fitted with the geometric parameters. We establish an inverse design framework for four-fold conical origami structures, and realize the inverse design process from a given 3D structure to the 2D origami crease pattern. Computational analysis shows that all the designed conical origami structures are in good agreements with the analytical solutions. In addition, the physical origami model not only verifies the flat-foldability of the designed structure, but also enriches the possible structural configurations by certain operations, such as overlapping and mirroring. This design method is suitable for developing generalized conical origami, and can play a positive role in data-driven origami design.

Key words: four-fold, origami structure, deep neural network, parametric design, inverse design

中图分类号:

TH112
TU357

陆晨浩, 陈耀, 何若琪, 范维莹, 冯健. 基于深度神经网络的四折痕锥形折纸结构设计[J]. 机械工程学报, 2023, 59(21): 167-176.

LU Chenhao, CHEN Yao, HE Ruoqi, FAN Weiying, FENG Jian. Developing Four-fold Conical Origami Structures Using Deep Neural Network[J]. Journal of Mechanical Engineering, 2023, 59(21): 167-176.

参考文献

[1] 李明,蒋延达,崔琦峰,等. 折纸衍生空间可展结构研究回顾与展望刍议[J]. 机械工程学报, 2021, 57(23):53-65. LI Ming, JIANG Yanda, CUI Qifeng, et al. Immature state-of-the-art review on origami-inspired spaceborne deployable structures[J]. Journal of Mechanical Engineering, 2021, 57(23):53-65.
[2] ZHANG Zhiwei, LUCE B, MA Chunping, et al. Programmable origami-inspired cellular architected building blocks for flow-regulating adaptive weir[J]. Extreme Mechanics Letters, 2020, 40:100974.
[3] 林秋红,张骞,贾文文,等. 大型空间薄膜遮阳罩折展构型设计与分析[J]. 机械工程学报, 2020, 56(5):13-20. LIN Qiuhong, ZHANG Qian, JIA Wenwen, et al. Deployable configuration design and analysis of large space membrane sunshield structures[J]. Journal of Mechanical Engineering, 2020, 56(5):13-20.
[4] 刘荣强,史创,郭宏伟,等. 空间可展开天线机构研究与展望[J]. 机械工程学报, 2020, 56(5):1-12. LIU Rongqiang, SHI Chuang, GUO Hongwei, et al. Review of space deployable antenna mechanisms[J]. Journal of Mechanical Engineering, 2020, 56(5):13-20.
[5] SILVERBERG J L, EVANS A A, MCLEOD L, et al. Using origami design principles to fold reprogrammable mechanical metamaterials[J]. Science, 2014, 345(6197):647-650.
[6] SAREH P, CHERMPRAYONG P, EMMANUELLI M, et al. Rotorigami:A rotary origami protective system for robotic rotorcraft[J]. Science Robotics, 2018, 3(22):eaah5228.
[7] 陈焱. 基于机构运动的大变形超材料[J]. 机械工程学报, 2020, 56(19):2-13. CHEN Yan. Review on kinematic metamaterials[J]. Journal of Mechanical Engineering, 2020, 56(19):2-13.
[8] 杨名远,马家耀,李建民,等. 基于厚板折纸理论的微创手术钳[J]. 机械工程学报, 2018, 54(17):36-45. YANG Mingyuan, MA Jiayao, LI Jianmin, et al. Thick-panel origami inspired forceps for minimally invasive surgery[J]. Journal of Mechanical Engineering, 2018, 54(17):36-45.
[9] 胡楠,陈花玲. 折纸结构驱动技术的研究进展[J]. 机械工程学报. 2020, 56(15):118-128. HU Nan, CHEN Hualing. Progress in actuating technology of origami structure[J]. Journal of Mechanical Engineering, 2020, 56(15):118-128.
[10] LANG R J. The complete book of origami:Step-by-step instructions in over 1000 diagrams:37 original models[M]. North Chelmsfood:Courier Corporation, 1988.
[11] WANG Fei, GONG Haoran, CHEN Xi, et al. Folding to curved surfaces:A generalized design method and mechanics of origami-based cylindrical structures[J]. Scientific Reports, 2016, 6(1):33312.
[12] HU Yucai, LIANG Haiyi, DUAN Huiling. Design of cylindrical and axisymmetric origami structures based on generalized Miura-ori cell[J]. Journal of Mechanisms and Robotics-Transactions of the ASME, 2019, 11(5):051004.
[13] DU Yuntong, KELLER T, SONG Changping, et al. Design and foldability of Miura-based cylindrical origami structures[J]. Thin-Walled Structures, 2021, 159:107311.
[14] CHEN Yao, SAREH P, YAN Jiayi, et al. An integrated geometric-graph-theoretic approach to representing origami structures and their corresponding truss frameworks[J]. Journal of Mechanical Design-Transactions of the ASME, 2019, 141(9):091402.
[15] CHEN Yao, YAN Jiayi, FENG Jian, et al. Particle swarm optimization-based metaheuristic design generation of non-trivial flat-foldable origami tessellations with degree-4 vertices[J]. Journal of Mechanical Design-Transactions of the ASME, 2021, 143(1):011703.
[16] CHEN Yao, LU Chenhao, YAN Jiayi, et al. Intelligent computational design of scalene-faceted flat-foldable tessellations[J]. Journal of Computational Design and Engineering, 2022, 9(5):1765-1774.
[17] CHEN Yao, FAN Linzi, BAI Yongtao, et al. Assigning mountain-valley fold lines of flat-foldable origami patterns based on graph theory and mixed-integer linear programming[J]. Computers & Structures, 2020, 239:106328.
[18] DANG Xiangxin, FENG Fan, PLUCINSKY P, et al. Inverse design of deployable origami structures that approximate a general surface[J]. International Journal of Solids and Structures, 2022, 234-235:111224.
[19] CALLENS S J P, ZADPOOR A A. From flat sheets to curved geometries:Origami and kirigami approaches[J]. Materials Today, 2018, 21(3):241-264.
[20] SHARMA H, UPADHYAY S H. Folding pattern design and deformation behavior of origami based conical structures[J]. Advances in Space Research, 2021, 67(7):2058-2076.
[21] SHARMA H, UPADHYAY S H. Geometric design and deployment behavior of origami inspired conical structures[J]. Mechanics Based Design of Structures and Machines, 2020:1-25.
[22] LU Lu, DANG Xiangxin, FENG Fan, et al. Conical Kresling origami and its applications to curvature and energy programming[J]. Proceedings of the Royal Society A:Mathematical, Physical and Engineering Sciences, 2022, 478(2257):1-20.
[23] LIU Ke, PAULINO G H. Nonlinear mechanics of non-rigid origami:An efficient computational approach[J]. Proceedings of the Royal Society A:Mathematical, Physical and Engineering Sciences, 2017, 473(2206):1-28.
[24] RAO Ziyuan, TUNG Poyen, XIE Ruiwen, et al. Machine learning-enabled high-entropy alloy discovery[J]. Science, 2022, 378(6615):78-85.
[25] FAN Weiying, CHEN Yao, LI Jiaqiang, et al. Machine learning applied to the design and inspection of reinforced concrete bridges:Resilient methods and emerging applications[J]. Structures, 2021, 33(10):3954-3963.
[26] ZHANG Pei, FAN Weiying, CHEN Yao, et al. Structural symmetry recognition in planar structures using convolutional neural networks[J]. Engineering Structures, 2022, 260:114227.

基于深度神经网络的四折痕锥形折纸结构设计

Developing Four-fold Conical Origami Structures Using Deep Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	邓栋轩, 李纪辉, 朱志韦, 邓子辰. 基于折纸结构的收纳式软体抓手设计与试验[J]. 机械工程学报, 2024, 60(5): 51-58.
[2]	常建涛, 乔子萱, 孔宪光, 杨胜康, 罗才文. 多维非线性特征重构与融合的复杂产品工期预测方法[J]. 机械工程学报, 2023, 59(6): 295-309.
[3]	纪小刚, 方创, 王炜. 目标参数驱动的点阵支架逆向设计方法研究[J]. 机械工程学报, 2023, 59(23): 221-228.
[4]	林京, 焦金阳. 可解释机械智能诊断技术的研究进展与挑战[J]. 机械工程学报, 2023, 59(20): 215-224.
[5]	黄澜, 于兆玮, 丁亮, 杨怀广, 高海波, 邓宗全, 杨辰光. 面向熔岩管探测的星球子车及其参数化设计方法研究[J]. 机械工程学报, 2023, 59(1): 19-34.
[6]	张立, 陈江涛, 熊芬芬, 任成坤, 李超. 基于元学习的多可信度深度神经网络代理模型[J]. 机械工程学报, 2022, 58(1): 190-200.
[7]	邓云蛟, 段艳宾, 李建军, 窦玉超, 曾达幸, 侯雨雷. 基于工作空间的混联式极化天线机构参数化设计及其力学分析[J]. 机械工程学报, 2021, 57(5): 81-89.
[8]	陈妮, 闫博, 袁媛, 李亮, 何宁. 微铣刀参数化设计系统研究[J]. 机械工程学报, 2020, 56(23): 185-192.
[9]	喻曦, 赵欢, 李祥飞, 丁汉. 基于双深度神经网络的轮廓误差补偿策略研究[J]. 机械工程学报, 2019, 55(3): 130-137.
[10]	侯文擎, 叶鸣, 李巍华. 基于改进堆叠降噪自编码的滚动轴承故障分类[J]. 机械工程学报, 2018, 54(7): 87-96.
[11]	何恕预, 刘斌. 特征尺寸驱动的鞋楦参数化设计[J]. 机械工程学报, 2017, 53(21): 118-127.
[12]	孙文珺, 邵思羽, 严如强. 基于稀疏自动编码深度神经网络的感应电动机故障诊断[J]. 机械工程学报, 2016, 52(9): 65-71.
[13]	史亮, 颜培刚, 韩万金, 谢鸣. 管网耦合计算在涡轮气冷叶片优化中的应用^*[J]. 机械工程学报, 2016, 52(18): 140-152.
[14]	周欣;周海波;王桂莲;马旭. 基于多目标模糊优化的非H封闭式周转轮系参数化计算机辅助设计[J]. , 2007, 43(7): 32-38.
[15]	高卫国;徐燕申;陈永亮;章青. 广义模块化设计原理及方法[J]. , 2007, 43(6): 48-54.