Welcome to Acta Armamentarii ! Today is Share:

Acta Armamentarii ›› 2020, Vol. 41 ›› Issue (8): 1633-1645.doi: 10.3969/j.issn.1000-1093.2020.08.018

• Paper • Previous Articles     Next Articles

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

YANG Zixin1, XUE Yuan2,3, SUN Chang1, XU Haojun3, HAN Xinmin3   

  1. (1.Xichang Satellite Launch Center, Xichang 615000, Sichuan, China;2.School of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, Shaanxi, China;3.School of Aeronautical Engineering, Air Force Engineering University, Xi'an 710038, Shaanxi, China)
  • Received:2019-09-18 Revised:2019-09-18 Online:2020-09-23

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.

Key words: equipmenteffectiveness, correlation, jointdistributionmodel, Elmanneuralnetwork, Copulafunction

CLC Number: