导航

ACTA AERONAUTICAET ASTRONAUTICA SINICA ›› 2019, Vol. 40 ›› Issue (12): 323214-323214.doi: 10.7527/S1000-6893.2019.23214

• Electronics and Electrical Engineering and Control • Previous Articles     Next Articles

Sensitivity analysis of ship formation operational effectiveness based on DBN effectiveness fitting

LI Bo1,2, LUO Haoran1, TIAN Linyu1, WANG Yuanxun1   

  1. 1. School of Electronics and Information, Northwestern Polytechnical University, Xi'an 710072, China;
    2. Key Laboratory of Data Link Technology, CETC, Xi'an 710077, China
  • Received:2019-06-12 Revised:2019-07-15 Online:2019-12-15 Published:2019-09-16
  • Supported by:
    Aeronautical Science Foundation of China(2017ZC53021); the Open Project Fund of CETC Key Labratory of Data Link Technology(CLDL-20182101)

Abstract: Aiming at the problem of insufficient data utilization and high requirements for data integrity in the traditional ship formation combat effectiveness analysis analysis method, this paper proposes a performance analysis fitting model based on deep belief network. Start with the most representative sensitivity analysis method-Sobol index method, and then take characteristic learning ability of deep learning, constructing a effectiveness fitting network based on Deep Belief Network(DBN), with network training and parameter optimization combined with unsupervised pre-training and supervised tuning. Finally, the experiments are simulated and analyzed based on the formation of air defense combat. Simulation results verify the applicability and effectiveness of the model.

Key words: effectiveness analysis, effectiveness fitting model, Deep Belief Network(DBN), sensitivity analysis, ship formation air defense

CLC Number: