Machine Learning-based Prediction of Impact Response in Kevlar<sup>®</sup> Yarn with 3D Visualization

HU Yiting; LIU Wanli; YUAN Zishun; GU Bingfei; XU Wang

doi:10.12382/bgxb.2025.0492

您当前的位置：

首页 >

文章列表页 >

Machine Learning-based Prediction of Impact Response in Kevlar^® Yarn with 3D Visualization

更新时间：2026-04-24

- Machine Learning-based Prediction of Impact Response in Kevlar^® Yarn with 3D Visualization
- Acta Armamentarii Vol. 47, Issue 3, Pages: 250492(2026)
- 作者机构：
  
  浙江理工大学服装学院，浙江杭州 310018
  浙江理工大学浙江省服装工程技术研究中心，浙江杭州 310018
  浙江理工大学丝绸文化传承与产品设计数字化技术文化和旅游部重点实验室，浙江杭州 310018
  北卡罗来纳州立大学威尔逊纺织学院，美国北卡罗来纳州罗利 27695
- 作者简介：
- 基金信息：
- DOI：10.12382/bgxb.2025.0492
  CLC： TH145.2;TP181
- Received：12 June 2025，
  
  Online First：25 December 2025，
  
  Published：2026-03
- 稿件说明：
移动端阅览
HU Yiting, LIU Wanli, YUAN Zishun, et al. Machine Learning-based Prediction of Impact Response in Kevlar^® Yarn with 3D Visualization[J]. Acta Armamentarii, 2026, 47(3): 250492.
DOI：

HU Yiting, LIU Wanli, YUAN Zishun, et al. Machine Learning-based Prediction of Impact Response in Kevlar^® Yarn with 3D Visualization[J]. Acta Armamentarii, 2026, 47(3): 250492. DOI： 10.12382/bgxb.2025.0492.

摘要

有限元方法在微观和介观尺度下预测高速冲击中高性能纱线的力学响应时，网格尺寸小、单元数量多，计算过程耗时长，且现有机器学习方法在三维结构响应的直接预测方面仍存在局限。为解决上述问题，提出基于前馈神经网络（Feedforward Neural Network，FNN）的机器学习预测与三维可视化方法。以凯夫拉纱线为研究对象，构建基于有限元数据驱动的FNN模型，将材料参数与冲击时间点作为输入，预测出纱线节点坐标和单元von Mises应力。并结合三维可视化技术，实现对纱线冲击响应的直观呈现。对比分析结果表明：所提方法生成的纱线三维模型在形变与应力分布方面与有限元仿真结果高度相似，且从参数输入到结果输出的全过程耗时约3s，计算效率较FEM提升近10倍；该方法为高性能防护材料的冲击响应预测提供了一种高效手段。

Abstract

The finite element method（FEM）incurs a substantial computational cost due to small mesh sizes and large element counts when predicting the mechanical response of high-performance yarn under high-velocity impact at micro-scales and meso-scales. Meanwhile

the existing machine-learning methods still have limitations in the direct prediction of three-dimensional structural response. To address these issues

a FNN-based machine-learning prediction and three-dimensional visualization method is proposed. A FEM-data-driven FNN model is constructed for Kevlar

yarn

which takes the material parameters and impact time points as inputs to predict the coordinates of yarn node and the von Mises stress of elements. Coupled with three-dimensional visualization

the method provides an intuitive depiction of the impact response. Comparative analysis shows that the three-dimensional yarn mod

el generated by the proposed method is highly similar to FEM simulation results in terms of deformation and stress distribution

and the end-to-end runtime from parameter input to result output is approximately 3 seconds

yielding nearly a tenfold improvement in computational efficiency over FEM. The proposed method offers an efficient means for predicting the impact response of high-performance protective materials.

关键词

Keywords

references

YANG Y F,LIU Y C,XUE S N,et al. Multi-scale finite element modeling of ballistic impact onto woven fabric involving fiber bundles[J]. Composite Structures,2021,267:113856.

唱忠良,张志俊,吴晨晨,等.平纹机织可展收层合壳弹道冲击特性研究[J].机械强度,2024,46(4):853-858.

CHANG Z L,ZHANG Z J,WU C C,et al. Study on ballistic impact characteristics of bistable laminated shells of plain weaved composites[J].Journal of Mechanical Strength,2024,46(4):853-858. (in Chinese)

王晓东,徐永杰,董方栋,等.凯夫拉与陶瓷复合结构抗侵彻性能数值仿真[J].兵工学报,2022,43(9):2360-2366.

WANG X D,XU Y J,DONG F D,et al. Numerical simulation of penetration resistance of Kevlar and ceramic composite structures[J]. Acta Armamentarii,2022,43(9):2360-2366. (in Chinese)

ZOCHOWSKI P, BAJKOWSKI M, GRYGORUK R, et al. Finite element modeling of ballistic inserts containing aramid fabrics under projectile impact conditions-comparison of methods[J]. Composite Structures,2022,294:115752.

PHAM Q H,HA-MINH C,CHU T L,et al. Numerical investigation of fibre failure mechanisms of one single Kevlar yarn under ballistic impact[J]. International Journal of Solids and Structures,2022, 239-240:111436.

SMITH J C, MCCRACKIN F L, SCHIEFER H F. Stress-strain relationships in yarns subjected to rapid impact loading[J]. Textile Research Journal,1958,28(4):288-302.

JEGADEESAN K,DATTA S. Design of laminated composite plate for optimum ballistic impact resistance:a finite element approach[J]. Materials Today:Proceedings,2022,68:2493-2497.

陈斌,汪送,刘星雨,等.面向钝性弹道冲击损伤评估的头部有限元模型[J].兵工学报,2025,46 (8):241022.

CHEN B,WANG S,LIU X Y,et al. Head finite element model for blunt ballistic impact injury assessment[J]. Acta Armamentarii, 2025,46(8):241022. (in Chinese)

甄泓,肖李军,杜成鑫,等.在弹道冲击条件下超高分子量聚乙烯纤维复合材料板破坏模式[J].兵工学报, 2025, 46(7):240725.

ZHEN H,XIAO L J,DU C X,et al. Damage modes of ultra-high molecular weight polyethylene fiber composite plates under ballistic impact conditions[J]. Acta Armamentarii,2025,46(7):240725. (in Chinese)

杨守怀,黄江流,陈志华,等.基于Transformer-LSTM混合神经网络的迫弹外弹道及落点预测方法[J].兵工学报,2025, 46(11):250123.

YANG S H,HUANG J L,CHEN Z H,et al. Prediction of exterior ballistics and impact point of mortar based on Transformer-LSTM hybrid neural network[J]. Acta Armamentarii,2025,46(11):250123. (in Chinese)

韩若寒,付小龙,蔚红建,等复合固体推进剂细观力学性能模拟研究进展[J].兵器装备工程学报,2024,45(8):290-300.

HAN R H,FU X L,WEI H J,et al. Progress on the simulation of mesomechanics properties of composite solid propellants[J]. Journal of Ordnance Equipment Engineering,2024,45(8):290-300. (in Chinese)

NIE Z G, JIANG H L, KARA L B. Stress field prediction in cantilevered structures using convolutional neural networks:arXiv:1808.08914[R/OL]. Ithaca,NY,US:Cornell University, 2018:1808.08914. https:∥arxiv. org/abs/1808.08914.

SUN Y X, HANHAN I, SANGID M D, et al. Predicting mechanical properties from microstructure images in fiber-reinforced polymers using convolutional neural networks[J]. Journal of Composites Science,2024,8(10):387.

YANG Z Z,YU C H,BUEHLER M J. Deep learning model to predict complex stress and strain fields in hierarchical composites[J]. Science Advances,2021,7(15):eabd7416.

BALDERAS L, LASTRA M, BENÍTEZ J M. Optimizing dense feed-forward neural networks[J]. Neural Networks,2024,171:229-241.

YUAN Z S,CHEN X G,ZENG H X,et al. Identification of the elastic constant values for numerical simulation of high velocity impact on dyneema ® woven fabrics using orthogonal experiments[J ] . Composite Structures,2018,204:178-191.

YUAN Z S,HE J,YANG Y R,et al. Estimating shear modulus of yarn on impact by lazy learning[J]. International Journal of Mechanical Sciences,2024,270:109074.

YUAN Z S, ZENG H X, XU W, et al. Reverse engineering for estimation of shear modulus for yarn models in finite element modelling for ballistic impact[J]. Composite Structures,2021, 274:114371.

YUAN Z S,WANG K C,QIU J W,et al. A numerical study on the mechanisms of Dyneema ® quasi-isotropic woven panels under ballistic impact[J ] . Composite Structures,2020,236:111855.

WANG K Y, ZHOU X, REN W K, et al. The impact of the coupling relationship between projectile size and yarn dimension on the ballistic performance of plain weave fabric[J]. Defence Technology,2025,43:288-303.

DUAN Y, KEEFE M, BOGETTI T A, et al. Finite element modeling of transverse impact on a ballistic fabric[J]. International Journal of Mechanical Sciences, 2006, 48 (1):33-43.

RAO M P, NILAKANTAN G, KEEFE M, et al. Global/Local modeling of ballistic impact onto woven fabrics[J]. Journal of Composite Materials,2009,43:445-467.

CHOCRON S, FIGUEROA E, KING N, et al. Modeling and validation of full fabric targets under ballistic impact[J]. Composites Science and Technology,2010,70(13):2012-2022.

KUMAR S,MURTHY S V S S N V G K,KUMAR B V R, et al. Thermo-magnetic radiative flow in porous enclosure with deep-learning parameter estimation[J]. International Journal of Mechanical Sciences,2024,276:109366.

孙凯,张成,詹天,等.融合注意力机制和多层动态形变卷积的多视图立体视觉重建方法[J].兵工学报,2024,45(10):3631-3641.

SUN K, ZHANG C, ZHAN T, et al. Multi-view stereo vision reconstruction network with fusion attention mechanism and multi-layer dynamic deformable convolution[J]. Acta Armamentarii, 2024,45(10):3631-3641. (in Chinese)

李萌,武海军,董恒,等.基于机器学习的混凝土侵彻深度预测模型[J].兵工学报,2023,44(12):3771-3782.

LI M,WU H J,DONG H,et al. Machine learning-based models for predicting the penetration depth of concrete[J]. Acta Armamentarii,2023,44(12):3771-3782. (in Chinese)

JOSHI A,MISHRA A,SAXENA V K. Impact response and energy absorption mechanisms of UHMWPE fabric and composites in ballistic applications: a comprehensive review[J]. Composites Part A:Applied Science and Manufacturing,2024,185:108314.

ZHANG J,ZHOU Y,LU Z Q,et al. Ballistic behavior of three-dimensional orthotropic woven fabric using virtual-fiber model[J]. International Journal of Mechanical Sciences, 2025, 286:109896.

PANDYA K S,KULKARNI M D,WARMAN A,et al. Simulation of stress wave attenuation in plain weave fabric composites during in-plane ballistic impact[J]. Composite Structures, 2017, 160:748-757.

ZHU Y H,WU W,SONG Y,et al. Ballistic impact wave and back bulge propagation mechanism and blunt trauma assessment of ceramic/UHMWPE composite body armor[J]. Journal of Materials Research and Technology,2024,31:1483-1506.

ZHU Y H, SONG Y, WU W, et al. Ballistic impact wave and bulge profile propagation characteristics and blunt injury assessment of UHMWPE laminate composite[J]. Journal of Materials Research and Technology,2024,31:3760-3780.

Views

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on the Application of Shear-stiffening Gel Modified Foam Materials in Ballistic Helmets

Application and Selection of Different Clustering Algorithms in the Processing of Impact-resistant Finite Element Simulation Results

A Predictive Model for Penetration Efficiency of Semi-Infinite Metallic Targets Based on Dimensional Constraints and Symbolic Regression

Identification of Auditory and Visual Channel Workloads of Special Vehicle Operators Based on EEG Indicators

Related Author

HU Yiting

LIU Wanli

YUAN Zishun

GU Bingfei

XU Wang

Junlong WANG

Zhenwei MIAO

Yue KANG

Related Institution

Apparel Engineering Research Center of Zhejiang Province

Wilson College of Textiles, North Carolina State University

Zhejiang Provincial Engineering Laboratory of Clothing Digital Technology

Postal code：100089
Tel：010-68963060/68962718 Fax：010-68963025 Email：bgxb@cos.org.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05059581号-4 京公网安备11010802024360号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：117952 Visits Today：266

⁰

Machine Learning-based Prediction of Impact Response in Kevlar® Yarn with 3D Visualization

DOI：10.12382/bgxb.2025.0492

摘要

Abstract

关键词

Keywords

references

Machine Learning-based Prediction of Impact Response in Kevlar^® Yarn with 3D Visualization