基于机器学习的双爆炸波耦合作用下靶板变形响应预测模型

初善勇; 刘彦; 徐梓熙; 刘沫言; 黄风雷

doi:10.12382/bgxb.2025.0983

您当前的位置：

首页 >

文章列表页 >

基于机器学习的双爆炸波耦合作用下靶板变形响应预测模型

更新时间：2026-03-09

- 基于机器学习的双爆炸波耦合作用下靶板变形响应预测模型
- Predictive Modeling of Plate Deformation under Double blast waves
- 兵工学报 2026年
- 作者机构：
  
  1. 北京理工大学爆炸科学与安全防护全国重点实验室,北京,100081
  2. 北京理工大学重庆创新中心,重庆,401120
  3. 沈阳理工大学装备工程学,辽宁,沈阳,110158
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目(12202063)
- DOI：10.12382/bgxb.2025.0983
  中图分类号： TJ410.1
- 收稿：2025-11-04，
  
  网络首发：2026-03-09，
- 稿件说明：
移动端阅览
初善勇，刘彦，徐梓熙，等. 基于机器学习的双爆炸波耦合作用下靶板变形响应预测模型[J/OL]. 兵工学报, 2026(2026-03-09). https://doi.org/10.12382/bgxb.2025.0983.

CHU S Y, LIU Y, XU Z X, et al. Predictive modeling of plate deformation under double blast waves[J/OL]. Acta Armamentarii, 2026(2026-03-09). https://doi.org/10.12382/bgxb.2025.0983. (in Chinese)
初善勇，刘彦，徐梓熙，等. 基于机器学习的双爆炸波耦合作用下靶板变形响应预测模型[J/OL]. 兵工学报, 2026(2026-03-09). https://doi.org/10.12382/bgxb.2025.0983. DOI：

CHU S Y, LIU Y, XU Z X, et al. Predictive modeling of plate deformation under double blast waves[J/OL]. Acta Armamentarii, 2026(2026-03-09). https://doi.org/10.12382/bgxb.2025.0983. (in Chinese) DOI：

摘要

为获得双爆源耦合加载下靶板变形预测模型，基于双爆源耦合加载下靶板毁伤效应实验与数值仿真研究进行数据集的获取，结合机器学习构建耦合加载下靶板变形的预测模型。通过双装药协同起爆获得耦合冲击波，实验中改变装药间距调整双爆源载荷强度，以此获得不同载荷强度下靶板变形模式和塑性变形量，并采用有限元软件探究靶板的毁伤模式。基于实验和数值仿真数据，采用决策树回归、随机森林回归、XGBoost和梯度提升回归四种非线性预测模型对靶板变形量进行了回归分析，并通过融合遗传算法与粒子群优化算法优化了模型超参数，优化后的超参数被用于预测模型。通过准确性、鲁棒性、泛化能力和计算效率等方面多维度对比四种非线性预测模型，从而优选出靶板变形响应的最佳预测模型。研究结果表明，梯度提升回归模型在预测精度、鲁棒性和泛化能力等关键指标上表现最优，但计算效率略低于决策树模型。XGBoost模型在部分指标上表现出色，然而其高噪声敏感性限制了实际应用。随机森林回归模型呈现均衡性能，DTR模型虽计算效率最高，但其他关键指标表现不佳。可以认为梯度提升回归模型最适用于双爆源耦合加载下的靶板变形预测。

Abstract

To obtain a predictive modelfor plate deformation under double explosive loading coupling

a model was developed based on experimental and numerical studies of plate damage effects underdoubleexplosive loading coupling. Machine learning was employed to construct a predictive model for plate deformation. By synchronously detonatingdoublecharges

coupled shock waves were generated. The experimental setup involved adjusting the spacing between charges to modify the load intensity of thedoubleexplosions. This enabled the observation of different deformation patterns and plastic deformation amounts of the target plate under varying load intensities. Additionally

the finite element software was utilized to further investigate the damage modes of the plate.Based on the experimental and numerical simulation results

four nonlinear predictive models - Decision Tree Regression (DTR)

Random Forest Regression (RFR)

XGBoost(XGB)

and Gradient Boosting Regression (GBR) - were used to perform regression analysis on the plate deformation. The modelhyperparameterswere optimized using a PSO-GA hybrid optimization algorithm

and the optimized parameters were applied to the predictive model. Through multidimensional comparisons in terms of accuracy

robustness

generalization ability

and computational efficiency

the best predictive model for plate deformation response was selected. The research findings indicate that

despite the slightly lower computational efficiency of the GBR model compared to the DTR model in scenarios with certainnoise in the data

its excellent performance in error statistics

residual analysis

robustness

and generalization capabilities make it the most suitable for predicting plate deformation under dual explosive loading coupling.

关键词

Keywords

references

丁赟.无人机集群作战协同火力决策技术研究[D].南京：南京理工大学,2022.

DING Y. Research on Cooperative fire decision technology of UAV cluster operation[D]. Nanjing ：Nanjing University of Science and Technology,2022. (in Chinese)

吕斯宁,肖川,冯恒振,等.集群协同作战技术现状与战争应用综述[J].探测与控制学报,2025,47(03):1-16.

LU X N，XIAO C，FENG H Z，et al. Overview of Clustered Cooperative Combat Technology: Current Status and Warfare Applications. Journal of Detection and Control[J], 2025,47(03):1-16.(in Chinese)

潘子双，苏析超，韩维，等.基于动态一致性联盟算法的异构无人机集群协同作战联盟组建[J].兵工学报,2024,45(09):3177-3190.

PAN Z C，SU X X，H W，et al. Cooperative Combat Coalition Formation of Heterogeneous UAV Swarm Based on Dynamic Consensus-based Grouping Algorithm[J]. Acta Armamentarii, 2024,45(09):3177-3190. (in Chinese)

JIANG N , YAO W J , ZHANG G G Q .Dynamic Multiprojectile Attack and Killing Effects of Detonation Warheads[J].Shock and vibration, 2022, 2022(Pt.4):1.1-1.13.

RABINOWITZ G I , WILSON F , BJERKE G ,et al.Experimental investigation of cylindrical shock wave interactions[J].Multiscale and Multidisciplinary Modeling, Experiments and Design, 2024, 7(3):2635-2647.DOI:10.1007/s41939-023-00360-9.

KNOCK C , DAVIES N , REEVES T .Predicting Blast Waves from the Axial Direction of a Cylindrical Charge[J]. Propellants Explosives Pyrotechnics, 2015, 40(2):169-179.DOI:10.1002/prep.201300188.

NURICK G. N., MARTIN J. B. Deformation of Thin Plates Subjected to Impulsive Loading—A review: Part I: Theoretical Considerations[J]. International Journal of Impact Engineering, 1989, 8（2）: 159-170.

NURICK G. N., MARTIN J. B. Deformation of Thin Plates Subjected to Impulsive Loading—A review : Part II: Experimental Studies[J]. International Journal of Impact Engineering, 1989, 8（2）: 171-186.

胡宏伟，宋浦，郭炜,等.地面爆炸冲击波的相互作用[J].高压物理学报, 2014, 28(3):5.DOI:10.11858/gywlxb.2014.03.014.

HU H W，SONG P，GUO W, et al. Interaction of shock waves in ground burst[J]. Chinese Journal of High Pressure Physics 2014,28(3):353-357. (in Chinese)

郑监，毛致远，张代鑫，等.不同间距两点空中爆炸威力场特性数值模拟研究[J].兵工学报,2023,44(12):3590-3600.

ZHENG J, MAO Z Y, ZHANG D X, et al. Numerical Research on the Power Field of Two-point Array Explosion with Different Spatial Intervals in Air[J]. Acta Armamentarii, 2023,44(12):3590-3600. (in Chinese)

胡宏伟,王健,冯海云,等. 多点水中阵列爆炸冲击波的传播特性[J]. 含能材料,2021,29(5):370 – 380.

HU H W,WANG J,FENG H Y,et al. The propagation characteristics of shock wave for muticharge underwater array explosion[J]. Chinese Journal of Energetic Materials,2021,29(5):370 - 380. (in Chinese)

翟红波, 李芝绒, 苏健军, 等. 多点同步内爆炸下典型舱室的毁伤特性 [J]. 振动与冲击, 2018, 37(2): 169–174,181. DOI: 10.13465/j.cnki.jvs.2018.02.025

ZHAI H B, LI Z R, SU J J, et al. Damage characteristics of a typical cabin with multi-point simultaneous inner explosion[J]. Journal of Vibration and Shock, 2018, 37(2): 169-174. (in Chinese)

赵伟成,翟红波,毛伯永等.两装药同时起爆时金属靶板的动态响应[J].爆炸与冲击,2023,43(12):3-13.

ZHAO W C，ZHAI H B，MAO B Y，et al. Dynamic response of a metal target plate to simultaneous initiation of two charges[J]. Explosion And Shock Waves, 2023, 43(12): 122201.

YAO S J，ZHANG D, LU F Y. Dimensionless Numbers for Dynamic Response Analysis of Clamped Square Plates Subjected to Blast Loading[J]. Archive of Applied Mechanics, 2015, 85(6):735-744.

CHUNG KIM YUEN S., NURICK G. N., Verster W.et al. Deformation of Mild Steel Plates Subjected to Large-scale Explosions[J]. International Journal of Impact Engineering, 2008, 35(8): 684-703.

JACOB N, NURICK GN, LANGDON GS. The effect of stand-off distance on the failure of fully clamped circular mild steel plates subjected to blast loads. Eng Struct 2007;29(10):2723e36.

ZHANG C , TAN P , YUAN Y .Confined blast loading ofsteel plates with and without pre-formed holes[J].International Journal of Impact Engineering, 2022.DOI:10.1016/j.ijimpeng.2022.104183.

许迎亮，刘彦，闫俊伯，等.双装药同步爆炸钢筋混凝土梁毁伤效应[J].兵工学报,2023,44(12):3719-3732.

XU Y L， LIU Y，YAN J B， BAI Fan,，et al. The Damage Effect of Reinforced Concrete Beams Subjected to Synchronous Explosion of Double Charges[J]. Acta Armamentarii, 2023, 44(12): 3719-3732. (in Chinese)

丰圣林.基于机器学习和GA-PSO算法的烤漆烘房节能应用研究[D].青岛:青岛大学,2023.

FENG S L. Research on energy saving application of paint drying room based on machine learning and GA-PSO algorithm [D]. Qingdao: Qingdao University, 2023. (in Chinese)

陈柳灼,邱羿志,周炎.基于深度神经网络的锈蚀RC梁位移角限值与破坏模式多目标预测方法[J/OL].工程力学,1-16.2024 (2024-10-14)[2026-03-06].https://link.cnki.net/urlid/11.2595.o3.20241014.0945.004.

CHEN L Z，QIU Y Z，ZHOU Y. Deep Neural Network-Aided Multi-Objective Prediction Method for Drift Ratio Limits and Failure Mode of Corroded RC Beam [J/OL]. Engineering Mechanics, 1-16.2024 (2024-10-14)[2026-03-06].https://link.cnki.net/urlid/11.2595.o3.20241014.0945.004. (in Chinese)

李驰运, 缪建明, 沈丙振. 基于改进Stacking集成学习方法的武器装备体系作战效能预测[J]. 兵工学报, 2023, 44(11): 3455-3464.

LI C Y, MIAO J M, SHEN B Z. Operational Effectiveness Prediction of Weapon Equipment System Based on Improved Stacking Ensemble Learning Method[J]. Acta Armamentarii, 2023, 44(11): 3455-3464. (in Chinese)

李萌, 武海军, 董恒, 任光, 张鹏, 黄风雷. 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，el. Machine Learning-based Models for Predicting the Penetration Depth of Concrete[J]. Acta Armamentarii, 2023, 44(12): 3771-3782. (in Chinese)

王雪.钨球穿透叠层靶的弹道极限研究[D].太原：中北大学,2020.

CHEN C , WANG X , HOU H ,et al.Effect of strength matching on failure characteristics of polyurea coated thin metal plates under localized air blast loading: Experiment and numerical analysis[J].Thin-Walled Structures, 2020, 154:106819.DOI:10.1016/j.tws.2020.106819.

WANG X. Study on Ballistic Limit of Tungsten Ball Penetrating Laminated Target[D]. Taiyuan：North University of China.2020.

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

基于量纲约束与符号回归的半无限金属靶板侵彻效率预测模型

基于脑电信号精准识别特种车辆作业人员视听通道工作负荷

硅/钨/聚四氟乙烯反应材料冲击释能特性及机器学习建模预测

空爆冲击波场计算模型研究现状与展望

一种考虑球体变形的钨球侵彻低碳钢深度计算模型