基于代理模型的人体钝击响应特征快速预测方法

徐侗桐; 宋阳; 桂冰琪; 朱一辉; 樊壮卿; 赵丽玲; 夏旻; 温垚柯

doi:10.12382/bgxb.2025.0590

您当前的位置：

首页 >

文章列表页 >

基于代理模型的人体钝击响应特征快速预测方法

更新时间：2026-05-06

- 基于代理模型的人体钝击响应特征快速预测方法
- Fast Prediction of Human Blunt Impact Response Characteristics Based on Surrogate Model
- 兵工学报 2026年47卷第4期页码：250590
- 作者机构：
  
  南京信息工程大学自动化学院，江苏南京 210044
  陆军军医大学大坪医院，重庆 400042
  创伤与化学中毒国家重点实验室，重庆 400042
  南京理工大学机械工程学院，江苏南京 210094
- 作者简介：
  
  通信作者邮箱：fanzhuangqing@163.com
- 基金信息：
  
  国家自然科学基金项目(12402477;12202210);中国博士后科学基金项目(2024M751481)
- DOI：10.12382/bgxb.2025.0590
  中图分类号： TJ012.4
- 收稿：2025-07-01，
  
  网络首发：2025-12-25，
  
  纸质出版：2026-04
- 稿件说明：
移动端阅览
徐侗桐, 宋阳, 桂冰琪, 等. 基于代理模型的人体钝击响应特征快速预测方法[J]. 兵工学报, 2026,47(4):250590.

XU Tongtong, SONG Yang, GUI Binqi, et al. Fast Prediction of Human Blunt Impact Response Characteristics Based on Surrogate Model[J]. Acta Armamentarii, 2026, 47(4): 250590.
徐侗桐, 宋阳, 桂冰琪, 等. 基于代理模型的人体钝击响应特征快速预测方法[J]. 兵工学报, 2026,47(4):250590. DOI： 10.12382/bgxb.2025.0590.

XU Tongtong, SONG Yang, GUI Binqi, et al. Fast Prediction of Human Blunt Impact Response Characteristics Based on Surrogate Model[J]. Acta Armamentarii, 2026, 47(4): 250590. DOI： 10.12382/bgxb.2025.0590.

摘要

非穿透性弹道冲击引起的钝性损伤对个体防护效果和伤情评估提出了高时效性的响应预测需求。传统有限元法虽然具有高精度，但计算成本高、响应滞后，难以适应快速决策场景。为此提出一种多物理场区域感知的代理建模方法，用于快速预测人体上躯干在软防护条件下的钝击响应特征。通过构建人体上躯干有限元模型，模拟9mm手枪铅芯弹以340m/s初速度冲击软防护下人体上躯干的过程，并提取关键部位的等效应力与位移数据构建训练集。该模型采用区域特化结构和物理约束，显著增强了对复杂组织响应模式的建模能力。实验结果表明，该模型在多区域、多指标预测中均达到相关指数

≥0.96的高精度，可实现快速响应预测。所得成果为钝击损伤的高效建模、个性化防护装备设计与突发伤情智能评估提供了可推广、可部署的技术路径。

Abstract

The blunt trauma caused by non-penetrative ballistic impact poses a demand for high-efficiency response prediction in individual protection effectiveness and injury assessment. Although the traditional finite elementmethod

offers high accuracy

it suffers from high computational cost and delayed response

making it difficult to adapt to fast decision-making scenarios. This paper proposes a surrogatemodelingmethod based onmulti-physical domain awareness

which is used to rapidly predict the blunt impact response characteristics of human torso under soft protection conditions. A finite elementmodel of human torso is established to simulate the process of a 9mm handgun fullmetal jacketed bullet impacting the human torso at an initial velocity of 340m/s under soft protection. The equivalent stress and displacement data of key parts of human body

are extracted to construct a training dataset. Themodel adopts a regionspecific structure and physical constraints

significantly enhancing themodeling capability for complex tissue response patterns. The experimental results indicate that themodel achieves high accuracy with

≥0.96 inmulti-region andmulti-metric predictions. This study provides a scalable and deployable technical approach for efficient blunt traumamodeling

personalized protective equipment design

and intelligent assessment of sudden injuries.

关键词

Keywords

references

BELLAMY R F. The causes of death in conventional land warfare:implications for combat casualty care research [J]. Military Medicine, 1984, 149 (2): 55-62.

王正国，蒋建新.爆炸冲击伤原理与实践[M].北京：人民卫生出版社，2020.

WANG Z G, JIANG J X.Principles and practice of explosive blast injury[M]Beijing: People's Medical Publishing House, 2020. (in Chinese)

王振保，王子健，徐新喜，等.急救机器人关键技术及装备发展现状[J].医疗卫生装备，2025，46（3）：96-114.

WANG Z B, WANG Z J, XU X X, et al. Key technology and equipment development status of first-aid robotics [J]. Chinese Medical Equipment Journal, 2025, 46 (3): 96-114. (in Chinese)

赵雪婷，汪送.人体胸部有限元模型的构建与军事应用[J].火力与指挥控制，2024，49（9）：40-51.

ZHAO X T, WANG S.Review on the construction and military applications of a finite element model of the human chest [J]. Fire Control & Command Control, 2024, 49 (9): 40-51. (in Chinese)

郭泽荣，唐帆，袁梦琦，等.手枪弹钝性冲击下人体躯干的力学响应[J].安全与环境学报，2020，20（3）：884-891.

GUO Z R, TANG F, YUAN M Q, et al. Mechanical response of human trunk under blunt impact of pistol bullets [J]. Journal of Safety and Environment, 2020, 20 (3): 884-891. (in Chinese)

HAMPTON C E, KLEINBERGER M. Material models for the human torso finite element model:ARL-TR-8297[R]. Aberdeen Proving Ground, MD, US:US Army Research Laboratory, 2018.

汪萌，温垚珂，徐诚，等.步枪弹侵彻背部穿硬防护人体靶标钝击效应研究[J].兵器装备工程学报，2024，45（4）：119-127.

WANG M, WEN Y K, XU C, et al. Study on the blunt impact effects of rifle bullet penetrating the back through human torso targets wear ballistic insert plate [J]. Journal of Ordnance Equipment Engineering, 2024, 45 (4): 119-127. (in Chinese)

EATON M A K, MCMAHON J A, SALZAR R S. Evaluating the limits in the biomechanics of blunt lung injury [J]. Journal of Biomechanical Engineering, 2022, 144 (9): 090801.

RUAN J, EI-JAWAHRI R, CHAI L, et al. Prediction and analysis of human thoracic impact responses and injuries in cadaver impacts using a full human body finite element model [R]. Warrendale, PA, US:SAE Technical Paper, 2003.

沈周宇，温垚珂，闫文敏，等.手枪弹撞击戴防弹头盔人体头颈部靶标的钝击效应[J].兵工学报，2022，43（9）：2101-2112.

SHEN Z Y, WEN Y K, YAN W M, et al. Behind-helmet blunt trauma of a pistol bullet striking ballistic helmet-covered human head and neck target [J]. Acta Armamentarii, 2022, 43 (9): 2101-2112. (in Chinese)

罗小豪.枪弹对戴防弹头盔人体头颈部靶标钝击效应研究[D].南京：南京理工大学，2021.

LUO X H.Study on blunt impact effect of gunshot on human head and neck target wearing bulletproof helmet [D]. Nanjing: Nanjing University of Science and Technology, 2021. (in Chinese)

TAGHIZADEH M, NABIAN M A, ALEMAZKOOR N. Multifidelity graph neural networks for efficient and accurate mesh-based partial differential equations surrogate modeling [J]. Computer-Aided Civil and Infrastructure Engineering, 2024, 40 (7): 841-858.

冯岳，蔡大星，何嘉俊，等.机器学习在复合材料力学领域的应用研究进展[J].复合材料学报，2025，42（9）：4885-4902.

FENG Y, CAI D X, HE J J, et al. Research progress in the application of machine learning in the mechanics of composite materials [J]. Acta Materiae Compositae Sinica, 2025, 42 (9): 4885-4902. (in Chinese)

SAMADIAN D, MUHIT I B, DAWOOD N. Application of datadriven surrogate models in structural engineering: a literature review [J]. Archives of Computational Methods in Engineering, 2024, 32:735-784.

GANTI H, KHARE P. Data-driven surrogate modeling of multiphase flows using machine learning techniques [J]. Computers & Fluids, 2020, 211:104626.

JIANG P, ZHOU Q, SHAO X Y. Surrogate-model-based design and optimization[M].Singapore:Springer, 2019:135-236.

MISENER R, BIEGLER L. Formulating data-driven surrogate models for process optimization [J]. Computers & Chemical Engineering, 2023, 179:108411.

冯易鑫，彭辉，罗威.聚类分析-神经网络-贝叶斯优化联合识别复合材料参数研究[J].力学学报，2024，56（11）：3333-3350.

FENG Y X, PENG H, LUO W.Research on parameter identification of composite materials by combination of selfconsistent cluster analysis, neural network and Bayesian optimization [J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56 (11): 3333-3350. (in Chinese)

ZHU Z H, KONG X S, ZHOU H, et al. A hybrid data-driven machine learning framework for predicting the impact resistance of composite armor [J]. International Journal of Impact Engineering, 2025, 195:105125.

XU Y J, WENG H B, JU X Z, et al. A method for predicting mechanical properties of composite microstructure with reduced dataset based on transfer learning [J]. Composite Structures, 2021, 275:114444.

YE S, LI B, LI Q Y, et al. Deep neural network method for predicting the mechanical properties of composites [J]. Applied Physics Letters, 2019, 115 (16): 161901.

PATHAN M V, PONNUSAMI S A, PATHAN J, et al. Predictions of the mechanical properties of unidirectional fibre composites by supervised machine learning [J]. Scientific Reports, 2019, 9 (1): 13964.

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.

PAI A, KINI C R, SHENOY S. Development of materials and structures for shielding applications against blast and ballistic impact:a detailed review [J]. Thin-Walled Structures, 2022, 179:109664.

SHEN X Y, HU Q R, ZHU D F, et al. Dynamic mechanical response prediction model of honeycomb structure based on machine learning method and finite element method [J]. International Journal of Impact Engineering, 2024, 184:104825.

何明洋，傅广，靳尚坤，等.基于机器学习的多孔材料力学性能预测研究进展[J].复合材料学报，2025，42（8）：4311-4338.

HE M Y, FU G, JIN S K, et al. Research progress in prediction of mechanical properties of porous materials based on machine learning [J]. Acta Materiae Compositae Sinica, 2025, 42 (8): 4311-4338. (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)

王锋，汪衡，刘宗伟，等.基于机器学习的侵彻弹安全性量化分级方法初探[J].北京理工大学学报，2025，45（1）：67-76.

WANG F, WANG H, LIU Z W, et al. Preliminary study on quantitative classification method of penetrating projectile safety based on machine learning [J]. Transactions of Beijing Institute of Technology, 2025, 45 (1): 67-76. (in Chinese)

YANG Z H, RONG J L, ZHAO Z T. Study on the prediction and inverse prediction of detonation properties based on deep learning [J]. Defence Technology, 2023, 24:18-30.

FANG X, LI H, ZHANG S R, et al. A combined finite element and deep learning network for structural dynamic response estimation on concrete gravity dam subjected to blast loads [J]. Defence Technology, 2023, 24:298-313.

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 Z, 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)

张云阳.有限监督条件下的物理场深度学习代理模型构建方法研究[D].北京：军事科学院，2024.

ZHANG Y Y.Research on construction method of deep learning proxy model for physical fields under limited supervision [D]. Beijing: Academy of Military Sciences, 2024. (in Chinese)

秦帅，刘浩，陈力，等.融合先验知识的混凝土侵彻深度试验数据异常点检测算法[J].爆炸与冲击，2024，44（3）：031406.

QIN S, LIU H, CHEN L, et al. Outlier detection algorithms for penetration depth data of concrete targets combined with prior knowledge [J]. Explosion and Shock Waves, 2024, 44 (3): 031406. (in Chinese)

樊壮卿，张双博，卢芳云，等.人员易损性分析研究进展及应用综述[J].兵工学报，2024，45（9）：2888-2905.

FAN Z Z, ZHANG S B, LU F Y, et al. A review of research advances in personnel vulnerability analysis and application [J]. Acta Armamentarii, 2024, 45 (9): 2888-2905. (in Chinese)

唐刘建，温垚珂，徐诚，等.手枪弹侵彻软防护人体胸部靶标的数值模拟[J].兵器装备工程学报，2018，39（1）：106-110，117.

TANG L J, WEN Y K, XU C, et al. Numerical simulation of pistol bullets penetrating into soft bulletproof vest covered human chest target [J]. Journal of Ordnance Equipment Engineering, 2018, 39 (1): 106-110, 117. (in Chinese)

唐刘建，温垚珂，薛本源，等.手枪弹侵彻有防护仿生人体躯干靶标试验研究[J].振动与冲击，2019，38（4）：245-249.

TANG L J, WEN Y K, XUE B Y, et al. Pistol bullet impact soft body armor covered bionic human torso [J]. Journal of Vibration and Shock, 2019, 38 (4): 245-249. (in Chinese)

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

叠层式复合装甲结构抗弹性能分析与优化设计

基于Transformer-LSTM混合神经网络的迫弹外弹道及落点预测方法

基于多尺度双重注意力网络的雷达信号调制识别方法

暗环境下红外目标检测跟踪方法研究