基于Stacking集成元模型的作战体系能力图谱生成方法

doi:10.12305/j.issn.1001-506X.2022.01.20

Abstract

Abstract:

Operational system of system (SoS) capability graph is an effective method to analyze operational SoS capability as a whole. Aiming at the problem of timeliness caused by the need to simulate the massive experimental space when generating the operational SoS capability graph, a method of generating the operational SoS capability graph based on the Stacking integrated meta-model is proposed. The method generated the operational SoS capability graph quickly and accurately by building the meta-model instead of the simulation model. Aiming at the problems of limited application scenarios and fluctuating performance of various meta-model, the Stacking method is proposed to integrate multiple meta-models to improve the robustness of meta-models in different application environments. Aiming at the contradiction between accuracy and efficiency in the meta-model building, a sequential sampling strategy is proposed for the generation of operational SoS capability graph. By calculating the meta-model uncertainty, high-value samples are selected to reduce the number of sampling while achieving the same accuracy index. Finally, an experimental case analysis proves the proposed effectiveness of the method.

Key words: operational system of systems, capability graph, Stacking ensemble learning, meta-model

CLC Number:

E917
TP391.9

Jun MA, Jingyu YANG, Liyan ZOU. Generation method of operational system of systems capability graph based on Stacking integrated meta-model[J]. Systems Engineering and Electronics, 2022, 44(1): 154-163.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Table 1

Fig.8

Table 2

References 35

1	刘虹麟. 作战体系能力图谱仿真实验方法研究[D]. 北京: 国防大学, 2018.
	LIU H L. Operations simulation experiment method based on SoS capability map[D]. Beijing: National Defense University, 2018.
2	唐建, 田福庆. 面向作战实验分析的智能集成仿真元建模方法[M]. 北京: 国防工业出版社, 2018.
	TANG J , TIAN F Q . An intelligent integrated simulation meta-modeling method for combat experimental analysis[M]. Beijing: National Defense Industry Press, 2018.
3	MICHAEL A. ZEIMER J D. Tew metamodel applications using TERSM[C]//Proc. of the Winter Simulation Conference 1995: 1421-1428.
4	KILMER R A . Applications of artificial neural networks to combat simulations[J]. Mathematical & Computer Modelling, 1996, 23 (2): 91- 99.
5	CASSANDRAS C G, GONG W B, LIU C C, et al. Simulation driven metamodeling of complex systems using neural networks[C]// Proc. of the International Society for Optical Engineering, 1998: 218-227.
6	JACK P C , KLEIJNEN H . Case study: statistical validation of simulation models[J]. European Journal of Operational Research, 1995, 87 (1): 21- 34. doi: 10.1016/0377-2217(95)00132-A
7	CAMPBELL P W . The development of a metamodel for a major weapon system cost model[J]. Rand Corporation, 1995, 14 (2): 1421- 1425.
8	PAUL K , DAVIS , JAMES H . Bigelow, motivated metamodels: synthesis of cause-effect reasoning and statistical metamodeling[J]. Rand Corporation, 2003, 21 (2): 143- 144.
9	李建平. 仿真元建模中的拟合方法及其应用研究[D]. 长沙: 国防科学技术大学, 2007.
	LI J P. Study on fitting methods of simulation metamodelling and its application[D]. Changsha: National University of Defense Technology, 2007.
10	张伟. 基于支持向量机的主动元建模方法研究[D]. 长沙: 国防科学技术大学, 2010.
	ZHANG W. Study on motivated metamodelling based on support vector machines[D]. Changsha: National University of Defense Technology, 2007.
11	唐建, 田福庆. 面向作战实验分析的智能集成仿真元建模方法[M]. 北京: 国防工业出版社, 2018: 71- 85.
	TANG J , TIAN F Q . An intelligent integrated simulation meta-modeling method for combat experimental analysis[M]. Beijing: National Defense Industry Press, 2018: 71- 85.
12	PAUL K. DAVIS, RUSSELL D. Shaver, justin beck. portfolio-analysis methods for assessing capability options. RAND MG662[EB/OL]. [2021-03-01] https://www.rand.org/pubs/monographs/MG662.html.
13	曹裕华. 作战实验理论与技术[M]. 北京: 国防工业出版社, 2013: 86- 94.
	CAO Y H . Operational experimental theory and technology[M]. Beijing: National Defense Industry Press, 2013: 86- 94.
14	PAUL K. DAVI S. Analytic architecture for capabilities-based planning, mission-system analysis, and transformation[EB/OL]. [2021-03-01]. https://www.rand.org/content/dam/rand/pubs/monograph_reports/2005/MR1513.pdf
15	KLEIJNEN J P C , SARGENT R G . A methodology for fitting and validating metamodels in simulation[J]. European Journal of Operational Research, 2000, 120 (1): 14- 29. doi: 10.1016/S0377-2217(98)00392-0
16	周志华. 集成学习基础与算法[M]. 北京: 电子工业出版社, 2020: 64- 65.
	ZHOU Z H . Ensemble methods foundations and algorithms[M]. Beijing: Publishing House of Electronic Industry, 2020: 64- 65.
17	SIMPSON T W , MAUERY T M , KORTE J J , et al. Kriging models for global approximation in simulation-based multidisciplinary design optimization[J]. Journal of American Institute of Aeronautics and Astionautics, 2001, 39, 2233- 2241. doi: 10.2514/2.1234
18	JONES D R , SCHONLAU M , WELCH W J . Global optimization of expensive black-box functions[J]. Journal of Global Optimization, 1998, 13 (4): 455- 492. doi: 10.1023/A:1008306431147
19	JONES D R . A Taxonomy of global optimization methods based on response surfaces[J]. Journal of Global Optimization, 2001, 21 (4): 345- 383. doi: 10.1023/A:1012771025575
20	MURPHY, B. S. PyKrige: development of a Kriging toolkit for python[C]//Proc. of the Agu Fall Meeting. AGU Fall Meeting Abstracts, 2014, 12: 573.
21	CLARKE S M , GRIEBSCH J H , SIMPSON T W . Analysis of support vector regression for approximation of complex engineering analyses[J]. Journal of Mechanical Design, 2005, 127 (6): 1077- 1086. doi: 10.1115/1.1897403
22	POGGIOT, GIROSI F. A theory of networks for approximation and learning[EB/OL]. [2020-09-29]. https://www.researchgate.net/profile/Federico_Girosi/publication/2526896_A_Theory_of_Networks_for_Approximation_and_Learning/links/02e7e52b37859111fb000000.pdf
23	TING K M , WITTEN I H . Issues in stacked generalization[J]. Journal of Artificial Intelligence Research, 1999, 10, 271- 289. doi: 10.1613/jair.594
24	GOEL T , HAFTKA R T , SHYY W , et al. Ensemble of surrogates[J]. Structural and Multi-diplinary Optimization, 2007, 33 (3): 199- 216. doi: 10.1007/s00158-006-0051-9
25	GIUNTA A A , DUDLEY J , NARDUCCI R , et al. Noisy aerodynamic response and smooth approximations in HSCT design[J]. Proc.of the 5th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1994, 9, 1117- 1128.
26	JONES D R , SCHONLAU M , WELCH W J . Efficient global optimization of expensive black-box functions[J]. Journal of Global Optimization, 1998, 13 (4): 455- 492. doi: 10.1023/A:1008306431147
27	LOEPPKY J L , WELCH S W J . Special issue on computer modeling Ⅱ choosing the sample size of a computer experiment: a practical guide[J]. Technometrics, 2009, 51 (4): 366- 376. doi: 10.1198/TECH.2009.08040
28	REGIS , ROMMEL G , SHOEMAKER , et al. A stochastic radial basis function method for the global optimization of expensive functions[J]. INFORMS Journal on Computing, 2007, 19 (4): 497- 509. doi: 10.1287/ijoc.1060.0182
29	GUTMANN H M . A radial basis function method for global optimization[J]. Journal of Global Optimization, 2000, 19 (3): 201- 227.
30	RAZAVI S , TOLSON B A , BURN D H . Numerical assessment of metamodeling strategies in computationally intensive optimization[J]. Environmental Modelling & Software, 2012, 34 (6): 67- 86.
31	WANG C , DUAN Q W , GONG W , et al. An evaluation of adaptive surrogate modeling based optimization with two benchmark problems[J]. Environmental Modelling & Software, 2014, 60 (10): 167- 179.
32	FORRESTER A I J , SOBESTER A , KEANE A J . Engineering design via surrogate modelling: a practical guide[M]. London: Data Base System and Logic Programming, 2008: 13- 28.
33	MICHAEL S . Large sample properties of simulations using latin hypercube sampling[J]. Technometrics, 1987, 29 (2): 143- 151. doi: 10.1080/00401706.1987.10488205
34	杨镜宇, 胡晓峰. 基于体系仿真试验床的新质作战能力评估[J]. 军事运筹与系统工程, 2016, (30): 5- 9.
	YANG J Y , HU X F . New quality combat capability evaluation based on system simulation test-bed[J]. Military Operations Research and Systems Engineering, 2016, (30): 5- 9.
35	SCTYHE. Proceedings and bulletin of the international data farming community[EB/OL]. [2021-04-14]https://Core.ac.uk/downloaol/pdf/36738474.pdf.

实验案例		PRS-model	Kriging-model	RBF-model	SVR-model	Stacking-model
目标指示	案例1	0.905 7±0.017 5	0.889 3±0.036 5	0.901 6±0.031 1	0.908 0±0.058 7	0.920 1±0.016 4
	案例2	0.539 9±0.039 1	0.763 1±0.175 7	0.889 3±0.158 4	0.834 0±0.092 5	0.931 2±0.019 8
	案例3	0.826 0±0.137 3	0.792 0±0.044 9	0.897 2±0.049 6	0.941 2±0.023 6	0.933 4±0.018 0
	案例4	0.891 2±0.059 2	0.915 0±0.007 7	0.939 9±0.023 9	0.917 8±0.025 4	0.935 2±0.022 9
目标打击	案例1	0.842 4±0.078 6	0.790 1±0.068 2	0.849 9±0.188 9	0.910 0±0.088 5	0.930 5±0.019 3
	案例2	0.505 4±0.511 2	0.685 1±0.042 2	0.761 3±0.202 8	0.919 7±0.044 9	0.927 1±0.018 7
	案例3	0.668 0±0.157 4	0.605 0±0.066 8	0.741 7±0.124 4	0.928 8±0.021 7	0.924 6±0.017 6
	案例4	0.885 3±0.051 0	0.792 0±0.044 9	0.930 8±0.047 5	0.910 8±0.032 2	0.935 3±0.022 2

案例	PRS-model	Kriging-model	RBF-model	SVR-model	Stacking-model
目标指示	0.170 8	0.073 7	0.022 5	0.046 3	0.006 8
目标打击	0.174 1	0.090 4	0.087 1	0.008 8	0.004 6
综合	0.163 4	0.100 3	0.074 7	0.032 2	0.005 4

[1]	Jun MA, Jingyu YANG, Xi WU. Evaluation of operational system of systems effectiveness based on pre-clustering active semi-supervised learning [J]. Systems Engineering and Electronics, 2022, 44(6): 1889-1896.
[2]	XU Jianguo, LI Mengjun, JIANG Jiang, LI Minghao. Supernetwork modeling and structure analyzing for warning combat system [J]. Systems Engineering and Electronics, 2018, 40(5): 1043-1049.
[3]	LI Ming-hao, YANG Ke-wei, XU Jian-guo, TAN Yue-jin. Model-driven rapid modeling and analysis methodology for crisis incidents [J]. Systems Engineering and Electronics, 2016, 38(9): 2055-2064.
[4]	LI Kang, LI Xin-ming, LIU Dong. Modeling method for weapon system of systems structure based on semantic meta-model [J]. Systems Engineering and Electronics, 2015, 37(11): 2503-2512.
[5]	TAN Xian-si,ZHU Gang,WANG Hong,BI Hong-kui,GAO Ting3. Joint demonstration meta-model based on IDEAS [J]. Systems Engineering and Electronics, 2015, 37(1): 85-92.
[6]	DENG Hai-song，MA Yi-zhong，SHAO Wen-ze. Variable selection for regression splines using hierarchical sparseness prior [J]. Journal of Systems Engineering and Electronics, 2010, 32(12): 2725-2729.

Generation method of operational system of systems capability graph based on Stacking integrated meta-model

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 35

Related Articles 6

Recommended Articles

Metrics

Comments