基于Elman神经网络和Copula函数的多维装备效能评估模型

杨梓鑫;薛源;孙畅;徐浩军;韩欣珉

兵工学报 ›› 2020, Vol. 41 ›› Issue (8) : 1633-1645.

兵工学报 ›› 2020, Vol. 41 ›› Issue (8) : 1633-1645. DOI: 10.3969/j.issn.1000-1093.2020.08.018
论文

基于Elman神经网络和Copula函数的多维装备效能评估模型

  • 杨梓鑫1, 薛源2,3, 孙畅1, 徐浩军3, 韩欣珉3
作者信息 +

Multidimensional Equipment Effectiveness Evaluation Model Based on Elman Neural Network and Copula Function

  • YANG Zixin1, XUE Yuan2,3, SUN Chang1, XU Haojun3, HAN Xinmin3
Author information +
文章历史 +

摘要

针对当前空战装备效能评估数据呈现出的非线性、多维性和耦合性等特征,将Elman神经网络与Copula函数相结合,提出了一种多维装备效能的评估模型。基于现代化空战特点建立效能评估指标体系的同时,结合战场环境与信息化空中对抗体系的仿真数据,利用Elman神经网络的权值参数自学习能力以及对非线性数据的良好拟合性,得到了边缘分布的预测模型及分布类型;针对分布数据之间的强耦合特征,选取Gumbel Copula函数、Clayton Copula函数、T-Copula函数、Frank Copula函 数、Joe Copula函数5种常用Archimedean Copula函数对变量间的相关性进行构造,通过对参数辨识和拟合优度结果进行对比,发现基于T-Copula函数所构建的联合分布模型与原始数据分布最为契合。以概率统计指标为评估依据,将该方法与传统方法进行了对比验证,得出了该方法的预测精度及适用范围均有所提升的结论。

Abstract

For the characteristics of non-linear, multidimensionality and coupling in the current air combat equipment effectiveness evaluation data, a multidimensional equipment effectiveness evaluation model is proposed by combining Elman neural network with Copula function. An effectiveness evaluation index system is established based on the characteristics of modern air combat, and the self-learning ability of the weight parameters of Elman neural network and the good fit to the non-linear data are used to obtain the prediction model and type of distribution based on the simulation data of the battlefield environment and the information-based air confrontation system. According to the strong coupling characteristics of the distribution data, five common Archimedean Copula functions, i.e., Gumbel Copula, Clayton Copula, T-Copula, Frank Copula, and Joe Copula, are selected to construct the correlation between variables. By comparing the results of parameter identification and goodness of fit, it is found that the joint distribution model constructed by T-Copula function is most suitable for the original data distribution. The proposed method was compared with the traditional method based on the probabilistic statistics index. The result shows that the proposed method has higher prediction accuracy and a wider scope of application.

关键词

装备效能 / 相关性 / 联合分布模型 / Elman神经网络 / Copula函数

Key words

equipmenteffectiveness / correlation / jointdistributionmodel / Elmanneuralnetwork / Copulafunction

引用本文

导出引用
杨梓鑫, 薛源, 孙畅, 徐浩军, 韩欣珉. 基于Elman神经网络和Copula函数的多维装备效能评估模型. 兵工学报. 2020, 41(8): 1633-1645 https://doi.org/10.3969/j.issn.1000-1093.2020.08.018
YANG Zixin, XUE Yuan, SUN Chang, XU Haojun, HAN Xinmin. Multidimensional Equipment Effectiveness Evaluation Model Based on Elman Neural Network and Copula Function. Acta Armamentarii. 2020, 41(8): 1633-1645 https://doi.org/10.3969/j.issn.1000-1093.2020.08.018

基金

国家自然科学基金面上项目(61873351); 国家自然科学基金项目(61503406)

参考文献


[1]葛冰峰, 李际超, 赵丹玲, 等. 基于元路径的武器装备体系作战网络链路预测方法[J]. 系统工程与电子技术, 2019, 41(5): 97-102.
GE B F, LI J C, ZHAO D L, et al. Battle network link prediction method for weapon equipment system based on elementary path[J]. Systems Engineering and Electronics, 2019, 41(5): 97-102.(in Chinese)
[2]杨克巍, 杨志伟, 谭跃进, 等. 面向体系贡献率的装备体系评估方法研究综述[J]. 系统工程与电子技术, 2019, 41(2):88-98.
YANG K W, YANG Z W, TAN Y J, et al. Review of equipment system evaluation methods for system contribution rate[J]. Systems Engineering and Electronics, 2019, 41(2): 88-98. (in Chinese)
[3]宋敬华, 李亮, 郭齐胜. 武器装备体系贡献率评估方法[J]. 火力与指挥控制, 2019, 44(3):109-113.
SONG J H, LI L, GUO Q S. Evaluation method of contribution rate ofweapon equipment system[J]. Fire and Command Control, 2019, 44(3): 109-113. (in Chinese)
[4]刘婧, 冒长礼, 赵呈阳. RBF模糊神经网络在舰载C3I系统效能评估中的应用[J]. 解放军理工大学学报(自然科学版), 2013,12(6):674-678.
LIU J, MAO C L, ZHAO C Y. Application of RBF fuzzy neural network in effectiveness evaluation of shipborne C3I system[J]. Journal ofPLA University of Science and Technology (Natural Science Edition), 2013,12(6): 674-678. (in Chinese)
[5]周超, 潘平, 黄亮. 基于量子门线路神经网络的信息安全风险评估[J]. 计算机工程, 2018, 44(12):45-51.
ZHOU C, PAN P, HUANG L. Information security risk assessment based on quantum gate line neural network[J]. Computer Engineering, 2018, 44(12): 45-51. (in Chinese)
[6]赵伟, 伞冶. q-高斯的SOM神经网络在雷达抗干扰效能评估中的应用[J]. 哈尔滨工程大学学报, 2011, 32(6):767-772.
ZHAO W, SAN Y. Application of q-Gaussian SOM neural network in radar anti-jamming effectiveness evaluation[J]. Journal of Harbin Engineering University, 2011, 32(6): 767-772. (in Chinese)
[7]张静,姚养无. 基于FCM算法大口径机枪的作战效能评估[J]. 中北大学学报(自然科学版), 2016,37(2):133-136.
ZHANG J, YAO Y W. Evaluation of operational effectiveness oflarge caliber machine gun based on FCM algorithm[J]. Journal of North University of China(Natural Science Edition), 2016,37(2):133-136. (in Chinese)
[8]王国荣, 王令. 北京地区夏季短时强降水时空分布特征[J]. 暴雨灾害, 2013,32(3):276-279.
WANG G R, WANG L. Temporal and spatial distribution characteristics of short-term heavy rain of Beijing in summer [J]. Torrential Rain and Disasters, 2013,32(3):276-279. (in Chinese)
[9]李晓松, 吕彬, 肖振华. 武器装备建设军民融合发展动力系统研究[J]. 计算机仿真, 2018, 35(10):16- 20,71.
LI X S, L B, XIAO Z H. Research on the dynamic system of military and civilian integration development in weapon and equipment construction[J]. Computer Simulation, 2018, 35(10):16- 20,71. (in Chinese)
[10]胡红萍, 孙强, 白艳萍. 基于优化的Elman神经网络的类流感的预测[J]. 太原理工大学学报, 2019, 50(2):119-123.
HU H P, SUN Q, BAI Y P. Influenza-like prediction based on optimized Elman neural network[J]. Journal of Taiyuan University of Technology, 2019, 50(2): 119-123. (in Chinese)
[11]SUNY S, LI Y M, ZHANG G C, et al. Actuator fault diagnosis of autonomous underwater vehicle based on improved elman neural network[J]. Journal of Central South University, 2016,23(4):808-816.
[12]LI H J, WANG J J, WANG H, et al. An optimal method for prediction and adjustment on gasholder level and self-provided power plant gas supply in steel works[J]. Journal of Central South University, 2014,21(7):2779-2792.
[13]陈金鑫,朱元倩.基于非对称Copula函数的系统流动性风险研究[J].统计与决策,2019,35(3):162-166.
CHEN J X,ZHU Y Q.Study on system liquidity risk based on asymmetric Copula function[J]. Statistics & Decision Making,2019,35(3):162-166. (in Chinese)
[14]刘章君, 郭生练, 何绍坤,等. 基于Copula函数的多变量水文不确定性处理器[J]. 水利学报, 2018, 49(3):332-342.
LIU Z J, GUO S L, HE S K, et al. Multivariable hydrological uncertainty processor based on Copula function[J]. Journal of Hydraulic Engineering, 2018, 49(3): 332-342. (in Chinese)
[15]陈子燊,黄强,刘曾美.基于非对称Archimedean Copula的三变量洪水风险评估[J].水科学进展,2016,27(5):763-771.
CHEN Z S, HUANG Q, LIU Z M. Three-variable flood risk assessment based on asymmetric Archimedean Copula[J]. Advances in Water Science, 2016, 27(5): 763-771. (in Chinese)
[16]郭齐胜,张磊.武器装备系统效能评估方法研究综述[J].计算机仿真,2013,30(8):1-4,18.
GUO Q S, ZHANG L. Research summary of weapons equipment systems effectiveness evaluation methods[J]. Computer Simulation, 2013, 30(8): 1-4,18. (in Chinese)
[17]陈兆兵,郭劲,王兵,等.车载高架式光电探测系统的作战效能评估[J].光学精密工程, 2013, 21(1): 77-86.
CHEN Z B, GUO J, WANG B, et al. Operational effectiveness evaluation of vehicle-mounted overhead photoelectric detection system[J].Optical Precision Engineering, 2013, 21(1): 77-86. (in Chinese)
[18]LI L, LIU M, SHEN W, et al. A novel performance evaluation model for MRO management indicators of high-end equipment[J]. International Journal of Production Research, 2019(1):1-18.
[19]焦松.武器装备效能仿真评估关键问题研究 [D].哈尔滨:哈尔滨工业大学, 2014: 3,11-12.
JIAO S. Research on key issues in simulation evaluation of weapon equipment effectiveness [D]. Harbin:Harbin Institute of Technology, 2014: 3,11-12. (in Chinese)
[20]LIU Y T, JIANG S Q, JIN D H, et al. Performance comparison of Si IGBT and SiC MOSFET power devices based LCL three-phase inverter with double closed-loop control[J]. IET Power Electronics, 2019, 12(2):322-329.
[21]韦艳华. Copula理论及其在多变量金融时间序列分析上的应用研究[D]. 天津:天津大学, 2004.
WEI Y H. Copula theory and its application in multivariate financial time series analysis [D]. Tianjin: Tianjin University, 2004. (in Chinese)
[22]宋松柏. Copulas函数及其在水文中的应用[M]. 北京:科学出版社, 2012.
SONG S B. Copulas function and its application in hydrology [M].Beijing:Science Press, 2012. (in Chinese)


372

Accesses

0

Citation

Detail

段落导航
相关文章

/