基于粒子群神经网络的黑索今基混合炸药大隔板试验冲击波感度预测

doi:10.3969/j.issn.1000-1093.2014.02.008

摘要/Abstract

摘要： 应用粒子群神经网络模型对黑索今（RDX）基混合炸药冲击波感度的大隔板厚度值进行预测以减少试验量，节约试验成本。选取具有不同密度、空隙率、装药方式、RDX含量等特征的41组 RDX基混合炸药，考察炸药实际密度、空隙率、RDX和附加物含量影响因素，通过分析它们与大隔板厚度值的非线性关系，建立大隔板厚度值与上述4个变量之间的粒子群算法优化神经网络模型，采用100进化次数，40种群规模进行计算。计算与试验结果表明：4个变量与大隔板厚度值之间的映射模型良好；模型预测值与试验值吻合良好，相对误差在10%以内。该粒子群神经网络模型预测值对RDX基混合炸药大隔板试验具有一定参考价值。

关键词: 兵器科学与技术, 混合炸药, 冲击波感度, 大隔板试验, 神经网络

Abstract: The large-scale gap thickness value of RDX-based composite explosive shock sensitivity is predicted by particle swarm neural network for reducing the number of tests and saving the test cost. 41 groups of RDX-based composite explosives with different densities, void ratios, charge structures and RDX contents are selected for test. The practical density of explosive, void ratio, RDX and additives content are taken into account as main influence factors. The nonlinear relationship among three influence factors and large scale gap thickness value is analyzed. The neural network model optimized by particle swarm algorithm is established for the above four variables and gap thickness value. The calculation results show that there is a good mapping model between the four variables and large scale gap thickness value; the predicted values are in good agreement with the experimental results, and the relative error is within 10%. The predicted value of the particle sarwm neural network can provide reference for the large-scale gap test of RDX-based composite explosive.

Key words: ordnance science and technology, composite explosive, shock sensitivity, large-scale gap test, neural network

中图分类号:

TJ55

袁俊明，刘玉存，王建华，常双君，于雁武. 基于粒子群神经网络的黑索今基混合炸药大隔板试验冲击波感度预测[J]. 兵工学报, 2014, 35(2): 188-193.

YUAN Jun-ming, LIU Yu-cun, WANG Jian-hua, CHANG Shuang-jun, YU Yan-wu. Prediction of Shock Sensitivity of RDX-based Composite Explosive by Particle Swarm Neural Network in Large-scale Gap Test[J]. Acta Armamentarii, 2014, 35(2): 188-193.

参考文献

［1］李玉斌,黄辉,李金山,等.一种含LLM-105的HMX基低感高能PBX炸药[J].火炸药学报, 2008, 31(5):1-4.
LI Yu-bin, HUANG Hui, LI Jin-shan, et al. A new HMX-based low-sensitive high energy PBX explosive containing LLM-105[J]. Chinese Journal of Explosives & Propellants, 2008, 31(5):1-4. (in Chinese)
[2］何中其,陈网桦,彭金华,等.基于水中小隔板法测试炸药冲击波感度的初步尝试[J].兵工学报, 2012, 33(8):1004-1008.
HE Zhong-qi，CHEN Wang-hua，PENG Jin-hua, et al. Preliminary experiments for shock sensivity test of explosives based on underwater small cardboard method[J]. Acta Armamentarii, 2012, 33(8): 1004-1008. (in Chinese)
[3］曾代朋,谭多里,李尚斌.含铝炸药冲击波感度的实验和数值计算研究[J].含能材料, 2010, 18(2):148-151.
ZENG Dai-peng, TAN Duo-li, LI Shang-bin. Experimental and numerical calculation study on shock sensitivity of aluminum explosive[J].Chinese Journal of Energetic Materials, 2010, 18(2):148-151. (in Chinese)
[4］ Nefati H, Diawara B, Legendre J J. Predicting the impact sensitivity of explosive molecules using neuromimetic networks[J]. SAR and QSAR in Environmental Research, 1993, 1(2/3):131- 136.
[5］ Nefati H, Cense J M, Legendre J J. Prediction of the impact sensitivity by neural networks[J]. Journal of Chemical Information and Computer Sciences, 1996, 36(4):804-810.
[6］ SooGyeong C, Kyoung T, EunMee G, et al. Optimization of neural networks architecture for impact sensitivity of energetic molecules[J]. Bulletin of the Korean Chemical Society, 2005, 26(3): 399-408.
[7］ Mohammad H K, Mohammad J. Investigation of the various structure parameters for predicting impact sensitivity of energetic molecules via artificial neural network[J]. Propellants, Explosives, Pyrotechnics, 2006, 31(3):216-224.
[8］ Wang R, Jiang J C, Pan Y, et al. Prediction of impact sensitivity of nitro energetic compounds by neural network based on electrotopological-state indices[J]. Journal of Hazardous Materials, 2009, 166(1): 155-186.
[9］刘欢,姜峰,于国强,等.遗传-神经网络方法在炸药撞击感度预测中的应用研究[J].火工品, 2010(6):42-45.
LIU Huan, JIANG Feng, YU Guo-qiang, et al. Application research of genetic-neural network method in the prediction of explosives’ impact sensitivity[J]. Initiators & Pyrotechnics, 2010(6): 42-45.(in Chinese)
[10］ WANG Rui, JIANG Jun-cheng, PAN Yong. Prediction of impact sensitivity of nonheterocyclic nitroenergetic compounds using genetic algorithm and artificial neural network[J]. Journal of Energetic Materials, 2012, 30(2):135-155.
[11］赵俊,何碧,程新路,等.多硝基炸药撞击感度与分子特征量关联度的BP神经网络方法研究[J].四川大学学报, 2006, 43(3):627-631.
ZHAO Jun, HE Bi, CHENG Xin-lu,et al. Back propagation neural networks study on the correlation between impact sensitivity of polynitro-explosives and molecular structure[J]. Journal of Sichuan University, 2006, 43(3):627-631.(in Chinese)
[12］王国栋,刘玉存. 应用神经网络预测炸药撞击感度[J].含能材料, 2008, 16(2):167-171.
WANG Guo-dong, LIU Yu-cun. Predicting the impact sensitivity of explosives by artificial neural network[J]. Journal of Energetic Materials, 2008, 16(2):167-171.(in Chinese)
[13］袁俊明,刘玉存. 基于灰色神经网络模型的混合炸药特性落高预测[J].兵工学报,2012,33(增刊1):195-199.
YUAN Jun-ming, LIU Yu-cun. Predicting of characteristic fall height of composite explosive based on grey neural network model[J]. Acta Armamentarii, 2012, 33(S1):195-199.(in Chinese)
[14］ Mohammad H K, Hamid R P, Masoud K T, et al. Predicting shock sensitivity of energetic compounds[J]. Asian Journal of Chemistry, 2008, 20(2):1025-1028.
[15］袁俊明,刘玉存,常双君,等.HMX基混合炸药大隔板厚度的计算[J].火炸药学报, 2013, 36(2):33-47.
YUAN Jun-ming, LIU Yu-cun,CHANG Shuang-jun,et al. Numerical calculation on large scale gap thickness of HMX-based composite explosive[J].Chinese Journal of Explosives & Propellants, 2013, 36(2):33-47.(in Chinese)
[16］张世杰. 炸药的冲击波感度测定—隔板试验法[J].煤矿爆破, 1994, 26(3):22-25.
ZHANG Shi-jie. Explosive shock sensitivity test-gap test method[J].Coal Mine Blasting, 1994, 26(3):22-25.(in Chinese)
[17］ Gibbs T G, Popolato A. LASL explosive property data [M].California:University of California Press, 1980:72-99.
[18] Dobratz B M, Crawford C. LLNL explosives handbook [M].California: University of California Livermore Press, 1985:280-288.
[19］钟一鹏,胡雅达,江宏志.国外炸药性能手册[M].北京：兵器工业出版社, 1990:112-185.
ZHONG Yi-peng, HU Ya-da, JIANG Hong-zhi. Handbook of foreign explosive property[M]. Beijing: the Publishing House of Ordnance Industry, 1990:112-185.(in Chinese)
[20］史峰,王小川,郁磊,等.Matlab 神经网络30个案例分析[M].北京:北京航空航天大学出版社,2011.
SHI Feng, WANG Xiao-chuan, YU Lei, et al. 30 neural network examples analysis with Matlab[M]. Beijing: Beijing University of Aeronautics & Astronautics Press, 2011. (in Chinese)

[1]	周伯俊, 于传强，刘志浩，柯冰. 基于高压储能的特种车辆快速起竖技术与验证[J]. 兵工学报, 2022, 43(7): 1488-1497.
[2]	高月光，冯顺山，刘云辉，黄岐. 不同端盖厚度的圆柱形装药壳体破片初速分布[J]. 兵工学报, 2022, 43(7): 1527-1536.
[3]	张伟，闫石，郭学永，任慧，焦清介. 端羟基聚叠氮缩水甘油醚与六硝基六氮杂异伍兹烷基四元混合炸药能量释放研究[J]. 兵工学报, 2018, 39(7): 1299-1307.
[4]	娄伟鹏，郑长松，李和言，陈建文，张周立，马源. 高速《Symbol》v湿式换挡离合器排油阀临界开启和关闭压力研究[J]. 兵工学报, 2017, 38(9): 1665-1672.
[5]	王宪成，杨绍卿，马宁，赵文柱. 车辆柴油机缸套动载荷磨损计算模型研究[J]. 兵工学报, 2017, 38(9): 1673-1680.
[6]	孙皓泽，常天庆，王全东，孔德鹏，戴文君. 一种基于分层多尺度卷积特征提取的坦克装甲目标图像检测方法[J]. 兵工学报, 2017, 38(9): 1681-1691.
[7]	张玉燕，孙莎莎，王振春，曹海要，战再吉. 高速载流电枢表面瞬态温度场仿真与测量[J]. 兵工学报, 2017, 38(9): 1692-1698.
[8]	李臣明，宦超，石怀龙. 某箱式火箭炮对面目标分布式杀伤最优火力分配[J]. 兵工学报, 2017, 38(9): 1699-1704.
[9]	雷娟棉，张嘉炜，谭朝明. 小攻角下船尾外形对旋转弹丸马格努斯效应影响的数值研究[J]. 兵工学报, 2017, 38(9): 1705-1715.
[10]	李泽，闫晓鹏，栗苹，郝新红，王建涛. 扫频式干扰对调频多普勒引信的干扰机理研究[J]. 兵工学报, 2017, 38(9): 1716-1722.
[11]	张浩为，谢军伟，张昭建，宗彬锋，陈唐军. 基于混合自适应遗传算法的相控阵雷达任务调度[J]. 兵工学报, 2017, 38(9): 1761-1770.
[12]	李茂，侯海量，朱锡，黄晓明，李典，陈长海，胡年明. 结构间隙对芳纶纤维增强复合装甲结构抗侵彻性能的影响[J]. 兵工学报, 2017, 38(9): 1797-1805.
[13]	王鉴, 韩焱, 王黎明, 张丕状, 陈平. 弹丸在膛内运动的回波信号瞬时频率估计方法研究[J]. 兵工学报, 2017, 38(9): 1806-1814.
[14]	刘海鸥，张文胜，徐宜，赵梓烨. 基于核密度估计的履带车辆传动轴载荷谱编制[J]. 兵工学报, 2017, 38(9): 1830-1838.
[15]	姜缪文，闫健卓，陈继民. 基于拓扑优化技术的军用头盔内胆结构三维打印[J]. 兵工学报, 2017, 38(9): 1845-1853.